[l10n] update translations from Weblate

930f4d95f - 2026-08-21 - return42 <return42@noreply.codeberg.org> 45e05f3a5 - 2026-08-21 - return42 <return42@noreply.codeberg.org> f97f47265 - 2026-08-21 - return42 <return42@noreply.codeberg.org> c5de4638c - 2026-08-21 - return42 <return42@noreply.codeberg.org> 02aac306b - 2026-08-21 - return42 <return42@noreply.codeberg.org> f88e28cd0 - 2026-08-14 - Mooo <mooo@noreply.codeberg.org>
2026-09-11 16:56:05 +00:00 · 2026-08-21 20:56:43 +00:00
118 changed files with 2735 additions and 25112 deletions
--- a/.github/workflows/data-update.yml
+++ b/.github/workflows/data-update.yml
@@ -31,7 +31,7 @@ jobs:
          - update_external_bangs.py
          - update_firefox_version.py
          - update_engine_traits.py
-          - update_wikidata.py
+          - update_wikidata_units.py
          - update_engine_descriptions.py

    permissions:
--- a/client/simple/generated/pygments.less
+++ b/client/simple/generated/pygments.less
@@ -2,7 +2,7 @@

 /*
   this file is generated automatically by searxng_extra/update/update_pygments.py
-   using pygments version 2.21.0:
+   using pygments version 2.20.0:

       ./manage templates.simple.pygments
 */
@@ -114,14 +114,14 @@
    .gd { color: #FF4689 } /* Generic.Deleted */
    .ge { color: #F8F8F2; font-style: italic } /* Generic.Emph */
    .ges { color: #F8F8F2; font-weight: bold; font-style: italic } /* Generic.EmphStrong */
-    .gr { color: #FF4689 } /* Generic.Error */
+    .gr { color: #F8F8F2 } /* Generic.Error */
    .gh { color: #F8F8F2 } /* Generic.Heading */
    .gi { color: #A6E22E } /* Generic.Inserted */
    .go { color: #66D9EF } /* Generic.Output */
    .gp { color: #FF4689; font-weight: bold } /* Generic.Prompt */
    .gs { color: #F8F8F2; font-weight: bold } /* Generic.Strong */
    .gu { color: #959077 } /* Generic.Subheading */
-    .gt { color: #66D9EF } /* Generic.Traceback */
+    .gt { color: #F8F8F2 } /* Generic.Traceback */
    .kc { color: #66D9EF } /* Keyword.Constant */
    .kd { color: #66D9EF } /* Keyword.Declaration */
    .kn { color: #FF4689 } /* Keyword.Namespace */
@@ -132,7 +132,7 @@
    .m { color: #AE81FF } /* Literal.Number */
    .s { color: #E6DB74 } /* Literal.String */
    .na { color: #A6E22E } /* Name.Attribute */
-    .nb { color: #A6E22E } /* Name.Builtin */
+    .nb { color: #F8F8F2 } /* Name.Builtin */
    .nc { color: #A6E22E } /* Name.Class */
    .no { color: #66D9EF } /* Name.Constant */
    .nd { color: #A6E22E } /* Name.Decorator */
@@ -166,7 +166,7 @@
    .sr { color: #E6DB74 } /* Literal.String.Regex */
    .s1 { color: #E6DB74 } /* Literal.String.Single */
    .ss { color: #E6DB74 } /* Literal.String.Symbol */
-    .bp { color: #A6E22E } /* Name.Builtin.Pseudo */
+    .bp { color: #F8F8F2 } /* Name.Builtin.Pseudo */
    .fm { color: #A6E22E } /* Name.Function.Magic */
    .vc { color: #F8F8F2 } /* Name.Variable.Class */
    .vg { color: #F8F8F2 } /* Name.Variable.Global */
--- a/client/simple/package-lock.json
+++ b/client/simple/package-lock.json
@@ -15,12 +15,12 @@
        "swiped-events": "1.2.0"
      },
      "devDependencies": {
-        "@biomejs/biome": "2.5.9",
+        "@biomejs/biome": "2.5.7",
        "@types/node": "^26.2.0",
        "browserslist": "^4.28.8",
        "browserslist-to-esbuild": "^2.1.1",
        "edge.js": "^6.5.1",
-        "less": "^4.9.0",
+        "less": "^4.8.1",
        "mathjs": "^15.2.0",
        "sharp": "~0.35.3",
        "sort-package-json": "^4.0.0",
@@ -69,9 +69,9 @@
      }
    },
    "node_modules/@biomejs/biome": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/biome/-/biome-2.5.9.tgz",
-      "integrity": "sha512-KkgCvdHB4IhtpHpF564plA9jo6fDOwWGQ/3jvreLzgOtRLEDoPqr7QO9qejNA8jKwDsSkAKr77hqBHnyUbIw4g==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/biome/-/biome-2.5.7.tgz",
+      "integrity": "sha512-zr8K/DcY5tYsQOQwqMJ0AWElo6QgmgNI7idXgXLhevVszlt8RGVpesEJPqx3ThazLaOwjJ5Y8fz3BtH5fGZNsw==",
      "dev": true,
      "license": "MIT OR Apache-2.0",
      "bin": {
@@ -85,20 +85,20 @@
        "url": "https://opencollective.com/biome"
      },
      "optionalDependencies": {
-        "@biomejs/cli-darwin-arm64": "2.5.9",
-        "@biomejs/cli-darwin-x64": "2.5.9",
-        "@biomejs/cli-linux-arm64": "2.5.9",
-        "@biomejs/cli-linux-arm64-musl": "2.5.9",
-        "@biomejs/cli-linux-x64": "2.5.9",
-        "@biomejs/cli-linux-x64-musl": "2.5.9",
-        "@biomejs/cli-win32-arm64": "2.5.9",
-        "@biomejs/cli-win32-x64": "2.5.9"
+        "@biomejs/cli-darwin-arm64": "2.5.7",
+        "@biomejs/cli-darwin-x64": "2.5.7",
+        "@biomejs/cli-linux-arm64": "2.5.7",
+        "@biomejs/cli-linux-arm64-musl": "2.5.7",
+        "@biomejs/cli-linux-x64": "2.5.7",
+        "@biomejs/cli-linux-x64-musl": "2.5.7",
+        "@biomejs/cli-win32-arm64": "2.5.7",
+        "@biomejs/cli-win32-x64": "2.5.7"
      }
    },
    "node_modules/@biomejs/cli-darwin-arm64": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-darwin-arm64/-/cli-darwin-arm64-2.5.9.tgz",
-      "integrity": "sha512-am22pX2aBqznqq1eMyIj/bZ++riF3Lk6ct7cbv+gQK0csFhr+d8O0RkOi2FF2qSgFgANbqNkIZ0/PxlnW2pLFg==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-darwin-arm64/-/cli-darwin-arm64-2.5.7.tgz",
+      "integrity": "sha512-vxo/Ls3/PYdQWyLhYYcgMOCzQypAjcY+iihS8M0wW03l16TCLW4zqZzGo75gm1VdCMj38hTVZ31KBWrZ4G9dJw==",
      "cpu": [
        "arm64"
      ],
@@ -113,9 +113,9 @@
      }
    },
    "node_modules/@biomejs/cli-darwin-x64": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-darwin-x64/-/cli-darwin-x64-2.5.9.tgz",
-      "integrity": "sha512-l44KWDHLDvEnD0N/XcrVs7VXb3A18xL7QS3WB0eL93wbmk529ffIG55vleGCqaunpRUjLrdnjK05Qki1dsjylg==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-darwin-x64/-/cli-darwin-x64-2.5.7.tgz",
+      "integrity": "sha512-Cd3Ga61amT/Yl/0x8elP5hhGYaFy4bw6WuysTgf7oo8TA5tJ5A1k+DkVoJ2BHbTVil51gTX9VPzArnrlLJ3Kyg==",
      "cpu": [
        "x64"
      ],
@@ -130,9 +130,9 @@
      }
    },
    "node_modules/@biomejs/cli-linux-arm64": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-arm64/-/cli-linux-arm64-2.5.9.tgz",
-      "integrity": "sha512-ICaK+IYaVZvKbBxX2rwrPT0DdUDMnE9Vm3nQGe+mltQPmUg19pONzkPWGdY4FCsoreDETWDynvdt4ysCbF5gNQ==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-arm64/-/cli-linux-arm64-2.5.7.tgz",
+      "integrity": "sha512-rR2QE0yF2GYSuYuKIa7pKvODGJqnOH+2eDREAM8wV+mWKSkMQKdAp4zXEZfTaxY8PMoNONnpgSWcBCyLDPDOKg==",
      "cpu": [
        "arm64"
      ],
@@ -150,9 +150,9 @@
      }
    },
    "node_modules/@biomejs/cli-linux-arm64-musl": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-arm64-musl/-/cli-linux-arm64-musl-2.5.9.tgz",
-      "integrity": "sha512-7ImVPwBLCtkmpR5esd8RHhTqW94f0JLJQum6AneYcy94jRm18TaPPm7slaigGzFhfgt3QiD1Vj52LKmBAnKizA==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-arm64-musl/-/cli-linux-arm64-musl-2.5.7.tgz",
+      "integrity": "sha512-xPI5yB6XlpDbNkS+bm1t42olw5c4l3UrlOmLg7KtLJvjvkNF/1V4tnUgfkylGIeb3u/T+BzMGYqgQhzjAoJzuQ==",
      "cpu": [
        "arm64"
      ],
@@ -170,9 +170,9 @@
      }
    },
    "node_modules/@biomejs/cli-linux-x64": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-x64/-/cli-linux-x64-2.5.9.tgz",
-      "integrity": "sha512-z22Q/zFYSvbIJfW1CbfZPu4X8PddS6Qd2ORbc6h+aT6EcwAxUF3m6fA4HjNvA3TU4X0dTJRwNPB165ES3PJXzg==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-x64/-/cli-linux-x64-2.5.7.tgz",
+      "integrity": "sha512-FQgqJhscrqJUFptGaRSUJWlXAExwWcDwLuK49dvKfkQ1bB5SEEyFssnsxQY83Xm6jR0EbbX3+8+D5bfvYqUG2Q==",
      "cpu": [
        "x64"
      ],
@@ -190,9 +190,9 @@
      }
    },
    "node_modules/@biomejs/cli-linux-x64-musl": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-x64-musl/-/cli-linux-x64-musl-2.5.9.tgz",
-      "integrity": "sha512-RXGaD0o1/pTTguYw1aeDJh9ad6Lfrui0fI7mBderTyGr7WuUJkBIttgLkR3XJyoxOkkgfBDspaUT8wXArTqLZw==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-linux-x64-musl/-/cli-linux-x64-musl-2.5.7.tgz",
+      "integrity": "sha512-rE5VZi+qtmPgQH+l7jVxYoZ18b/TiHEhulhMpjmCZH1PltSbjRcxNWywC3HZ9tYottG7ORkeTtoscBilKSBm0g==",
      "cpu": [
        "x64"
      ],
@@ -210,9 +210,9 @@
      }
    },
    "node_modules/@biomejs/cli-win32-arm64": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-win32-arm64/-/cli-win32-arm64-2.5.9.tgz",
-      "integrity": "sha512-nHK+/HHC+D0ogAHUxomgoSTdjImb6fmNNVTKmf0tyu4eDL1DqPKIHc+i+UL8+b0RnAu8224qo8F2tCVnaT0A3w==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-win32-arm64/-/cli-win32-arm64-2.5.7.tgz",
+      "integrity": "sha512-Oq4x0CCwP4jirrcTywXs5kOGZ4v5vuEP+gWrbtjApOA2CL9F3F9GlIdQIci8AKSCa/zURanMRpX/4wQ7Am6hHg==",
      "cpu": [
        "arm64"
      ],
@@ -227,9 +227,9 @@
      }
    },
    "node_modules/@biomejs/cli-win32-x64": {
-      "version": "2.5.9",
-      "resolved": "https://registry.npmjs.org/@biomejs/cli-win32-x64/-/cli-win32-x64-2.5.9.tgz",
-      "integrity": "sha512-Yiq0H56LjXSSw/hd9YkXgSLQfzyDJzbzU2TezozxyNw+uKWAqOtqGVvBfzKRRDiaFF5avGAhHdWKx7LtDOShUw==",
+      "version": "2.5.7",
+      "resolved": "https://registry.npmjs.org/@biomejs/cli-win32-x64/-/cli-win32-x64-2.5.7.tgz",
+      "integrity": "sha512-V+0wu/nrj2S+MhP4EQ0uHNolP0IALEsz45pg0WoKkHfDeh0+ItHwP/p7bX5RPoMOl9NkpHYWdYPhIcy2mACHvQ==",
      "cpu": [
        "x64"
      ],
@@ -3233,9 +3233,9 @@
      "license": "Apache-2.0"
    },
    "node_modules/less": {
-      "version": "4.9.0",
-      "resolved": "https://registry.npmjs.org/less/-/less-4.9.0.tgz",
-      "integrity": "sha512-umRhrCH7fCi8Uj2RcwKjJdvUORTjeWqkdKx0LbcZvjIwsAVsnIAGcxHaqowPeBFBjQuWOeC/bve0AlpFzF/+SQ==",
+      "version": "4.8.1",
+      "resolved": "https://registry.npmjs.org/less/-/less-4.8.1.tgz",
+      "integrity": "sha512-jQ3lRIo1aUtiWVYXZ7mk4+V4BjCGswF3IxTLJ+4RUta8ZiHh8lhkig2G8dya2eCcyR1dYUvzuV46EkJN8PSwww==",
      "dev": true,
      "license": "Apache-2.0",
      "dependencies": {
--- a/client/simple/package.json
+++ b/client/simple/package.json
@@ -29,12 +29,12 @@
    "swiped-events": "1.2.0"
  },
  "devDependencies": {
-    "@biomejs/biome": "2.5.9",
+    "@biomejs/biome": "2.5.7",
    "@types/node": "^26.2.0",
    "browserslist": "^4.28.8",
    "browserslist-to-esbuild": "^2.1.1",
    "edge.js": "^6.5.1",
-    "less": "^4.9.0",
+    "less": "^4.8.1",
    "mathjs": "^15.2.0",
    "sharp": "~0.35.3",
    "sort-package-json": "^4.0.0",
--- a/docs/dev/quickstart.rst
+++ b/docs/dev/quickstart.rst
@@ -80,8 +80,8 @@ same environment, here are a few examples::
    # to test one of the update scripts
    (dev.env)$ searxng_extra/update/update_engine_traits.py --help

-    # to test the update of the wikidata units and property names
-    (dev.env)$ searxng_extra/update/update_wikidata.py
+    # to test the update of the wikidata units
+    (dev.env)$ searxng_extra/update/update_wikidata_units.py


 .. sidebar:: further read
--- a/docs/dev/searxng_extra/update.rst
+++ b/docs/dev/searxng_extra/update.rst
@@ -90,10 +90,10 @@ Scripts to update static data in :origin:`searx/data/`
  :members:


-``update_wikidata.py``
+``update_wikidata_units.py``
 ============================

-:origin:`[source] <searxng_extra/update/update_wikidata.py>`
+:origin:`[source] <searxng_extra/update/update_wikidata_units.py>`

-.. automodule:: searxng_extra.update.update_wikidata
+.. automodule:: searxng_extra.update.update_wikidata_units
  :members:
--- a/requirements-dev.txt
+++ b/requirements-dev.txt
@@ -1,7 +1,7 @@
 mock==5.2.0
 nose2[coverage_plugin]==0.16.0
 cov-core==1.15.0
-black==26.5.1
+black==25.9.0
 pylint==4.0.7
 splinter==0.21.0
 selenium==4.47.0
@@ -23,6 +23,6 @@ coloredlogs==15.0.1
 docutils>=0.21.2;python_version <= "3.11"
 docutils>=0.22.4; python_version > "3.11"
 parameterized==0.9.0
-granian[reload]==2.8.2
-basedpyright==1.39.10
+granian[reload]==2.8.1
+basedpyright==1.39.9
 types-lxml==2026.2.16
--- a/requirements-server.txt
+++ b/requirements-server.txt
@@ -1,2 +1,2 @@
-granian==2.8.2
-granian[pname]==2.8.2
+granian==2.8.1
+granian[pname]==2.8.1
--- a/requirements.txt
+++ b/requirements.txt
@@ -3,8 +3,8 @@ babel==2.18.0
 flask-babel==4.0.0
 flask==3.1.3
 jinja2==3.1.6
-lxml==6.1.2
-pygments==2.21.0
+lxml==6.1.1
+pygments==2.20.0
 python-dateutil==2.9.0.post0
 pyyaml==6.0.3
 httpx[http2]==0.28.1
--- a/searx/_settings.py
+++ b/searx/_settings.py
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementation of the :py:obj:`preference <searx.preference>` settings."""
-
 # pylint: disable = too-few-public-methods

 import typing as t
--- a/searx/answerers/init.py
+++ b/searx/answerers/init.py
@@ -38,6 +38,7 @@ area:

 """

+
 __all__ = ["AnswererInfo", "Answerer", "AnswerStorage"]


--- a/searx/answerers/_core.py
+++ b/searx/answerers/_core.py
@@ -13,6 +13,7 @@ from dataclasses import dataclass
 from searx.utils import load_module
 from searx.result_types.answer import BaseAnswer

+
 _default = pathlib.Path(__file__).parent
 log: logging.Logger = logging.getLogger("searx.answerers")

--- a/searx/autocomplete.py
+++ b/searx/autocomplete.py
@@ -127,17 +127,18 @@ def duckduckgo(query: str, sxng_locale: str) -> list[str]:


 def google_complete(query: str, sxng_locale: str) -> list[str]:
-    """Autocomplete from Google.  Supports Google's languages
+    """Autocomplete from Google.  Supports Google's languages and subdomains
    (:py:obj:`searx.engines.google.get_google_info`) by using the async REST
    API::

-        https://www.google.com/complete/search?{args}
+        https://{subdomain}/complete/search?{args}

    """

    data = ENGINE_TRAITS.get("google") or {}
    traits = EngineTraits(**data)
    google_info: dict[str, t.Any] = google.get_google_info({'searxng_locale': sxng_locale}, traits)
+    url = 'https://{subdomain}/complete/search?{args}'
    args = urlencode(
        {
            'q': query,
@@ -147,7 +148,7 @@ def google_complete(query: str, sxng_locale: str) -> list[str]:
    )
    results: list[str] = []

-    resp = get('https://www.google.com/complete/search?' + args)
+    resp = get(url.format(subdomain=google_info['subdomain'], args=args))
    if resp and resp.ok:
        json_txt = resp.text[resp.text.find('[') : resp.text.find(']', -3) + 1]
        data = json.loads(json_txt)
--- a/searx/botdetection/init.py
+++ b/searx/botdetection/init.py
@@ -5,6 +5,7 @@ Implementations used for bot detection.

 """

+
 __all__ = ["init", "dump_request", "get_network", "too_many_requests", "ProxyFix"]


--- a/searx/botdetection/config.py
+++ b/searx/botdetection/config.py
@@ -182,7 +182,7 @@ class Config:
            if default is UNSET:
                raise KeyError(name)
            return default
-        modulename, name = str(fqn).rsplit('.', 1)
+        (modulename, name) = str(fqn).rsplit('.', 1)
        m = __import__(modulename, {}, {}, [name], 0)
        return getattr(m, name)

--- a/searx/botdetection/http_accept.py
+++ b/searx/botdetection/http_accept.py
@@ -13,6 +13,7 @@ Accept_ header ..

 """

+
 from ipaddress import (
    IPv4Network,
    IPv6Network,
--- a/searx/botdetection/http_accept_encoding.py
+++ b/searx/botdetection/http_accept_encoding.py
@@ -14,6 +14,7 @@ bot if the Accept-Encoding_ header ..

 """

+
 from ipaddress import (
    IPv4Network,
    IPv6Network,
--- a/searx/botdetection/http_accept_language.py
+++ b/searx/botdetection/http_accept_language.py
@@ -11,6 +11,7 @@ if the Accept-Language_ header is unset.

 """

+
 from ipaddress import (
    IPv4Network,
    IPv6Network,
--- a/searx/botdetection/http_connection.py
+++ b/searx/botdetection/http_connection.py
@@ -11,6 +11,7 @@ the Connection_ header is set to ``close``.

 """

+
 from ipaddress import (
    IPv4Network,
    IPv6Network,
--- a/searx/botdetection/http_sec_fetch.py
+++ b/searx/botdetection/http_sec_fetch.py
@@ -20,7 +20,6 @@ Metadata`_.  A request is filtered out in case of:


 """
-
 # pylint: disable=unused-argument


--- a/searx/botdetection/http_user_agent.py
+++ b/searx/botdetection/http_user_agent.py
@@ -12,6 +12,7 @@ the User-Agent_ header is unset or matches the regular expression

 """

+
 import re
 from ipaddress import (
    IPv4Network,
@@ -24,6 +25,7 @@ import flask
 from . import config
 from ._helpers import too_many_requests

+
 USER_AGENT = (
    r'('
    + r'unknown'
--- a/searx/botdetection/ip_limit.py
+++ b/searx/botdetection/ip_limit.py
@@ -55,6 +55,7 @@ from ._helpers import (
    logger,
 )

+
 logger = logger.getChild('ip_limit')

 BURST_WINDOW = 20
--- a/searx/botdetection/ip_lists.py
+++ b/searx/botdetection/ip_lists.py
@@ -23,7 +23,6 @@ The ``ip_lists`` method implements :py:obj:`block-list <block_ip>` and
   ]

 """
-
 # pylint: disable=unused-argument


--- a/searx/botdetection/trusted_proxies.py
+++ b/searx/botdetection/trusted_proxies.py
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementation of a middleware to determine the real IP of an HTTP request
 (:py:obj:`flask.request.remote_addr`) behind a proxy chain."""
-
 # pylint: disable=too-many-branches


--- a/searx/botdetection/valkeydb.py
+++ b/searx/botdetection/valkeydb.py
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Providing a Valkey database for the botdetection methods."""

+
 import valkey

 __all__ = ["set_valkey_client", "get_valkey_client"]
--- a/searx/brand.py
+++ b/searx/brand.py
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementations needed for a branding of SearXNG."""
-
 # pylint: disable=too-few-public-methods

 # Struct fields aren't discovered in Python 3.14
--- a/searx/cache.py
+++ b/searx/cache.py
@@ -465,7 +465,7 @@ class ExpireCacheSQLite(sqlitedb.SQLiteAppl, ExpireCache):

        # Check if value is expired. It's possible that it's expired but has not
        # yet been automatically deleted by the periodic maintenance
-        value, expire = row
+        (value, expire) = row
        now = time.time()
        if expire < now:
            # The record is deleted during the maintenance interval. Deleting
--- a/searx/compat.py
+++ b/searx/compat.py
@@ -3,6 +3,7 @@

 import warnings

+
 # limiter backward compatibility
 # ------------------------------

--- a/searx/data/init.py
+++ b/searx/data/init.py
@@ -4,7 +4,6 @@
 make data.all

 """
-
 # pylint: disable=invalid-name

 __all__ = ["ahmia_blacklist_loader", "data_dir", "get_cache"]
@@ -33,13 +32,6 @@ class WikiDataUnitType(t.TypedDict):
    to_si_factor: float


-WikiDataPropertyNameType = str | dict[str, str]
-"""Name of a Wikidata property. Can be either the plain name or a dictionary of
-language code to property name, e.g. ``{"en": "Date of birth"}``."""
-WikiDataPropertiesType = dict[str, WikiDataPropertyNameType]
-"""Dictionary from wikidata property ID to property name."""
-
-
 class LocalesType(t.TypedDict):
    """Data structure of an item in ``locales.json``"""

@@ -49,7 +41,6 @@ class LocalesType(t.TypedDict):

 USER_AGENTS: UserAgentType
 WIKIDATA_UNITS: dict[str, WikiDataUnitType]
-WIKIDATA_PROPERTIES: WikiDataPropertiesType
 TRACKER_PATTERNS: TrackerPatternsDB
 LOCALES: LocalesType
 CURRENCIES: CurrenciesDB
@@ -61,12 +52,11 @@ ENGINE_DESCRIPTIONS: dict[str, dict[str, t.Any]]
 ENGINE_TRAITS: dict[str, dict[str, t.Any]]


-lazy_globals: dict[str, t.Any] = {
+lazy_globals = {
    "CURRENCIES": CurrenciesDB(),
    "USER_AGENTS": None,
    "EXTERNAL_URLS": None,
    "WIKIDATA_UNITS": None,
-    "WIKIDATA_PROPERTIES": None,
    "EXTERNAL_BANGS": None,
    "OSM_KEYS_TAGS": None,
    "ENGINE_DESCRIPTIONS": None,
@@ -79,7 +69,6 @@ data_json_files = {
    "USER_AGENTS": "useragents.json",
    "EXTERNAL_URLS": "external_urls.json",
    "WIKIDATA_UNITS": "wikidata_units.json",
-    "WIKIDATA_PROPERTIES": "wikidata_properties.json",
    "EXTERNAL_BANGS": "external_bangs.json",
    "OSM_KEYS_TAGS": "osm_keys_tags.json",
    "ENGINE_DESCRIPTIONS": "engine_descriptions.json",
--- a/searx/data/ahmia_blacklist.txt
+++ b/searx/data/ahmia_blacklist.txt
--- a/searx/data/engine_traits.json
+++ b/searx/data/engine_traits.json
--- a/searx/data/tracker_patterns.py
+++ b/searx/data/tracker_patterns.py
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Simple implementation to store TrackerPatterns data in a SQL database."""
-
 # pylint: disable=too-many-branches

 import typing as t
--- a/searx/data/useragents.json
+++ b/searx/data/useragents.json
@@ -5,7 +5,7 @@
    ],
    "ua": "Mozilla/5.0 ({os}; rv:{version}) Gecko/20100101 Firefox/{version}",
    "versions": [
-        "154.0",
-        "153.0"
+        "153.0",
+        "152.0"
    ]
 }
--- a/searx/data/wikidata_properties.json
+++ b/searx/data/wikidata_properties.json
--- a/searx/data/wikidata_units.json
+++ b/searx/data/wikidata_units.json
@@ -3474,6 +3474,11 @@
        "symbol": "mm⁻²",
        "to_si_factor": 1e-06
    },
+    "Q136039973": {
+        "si_name": "Q6137407",
+        "symbol": "FPS",
+        "to_si_factor": 1.0
+    },
    "Q1361854": {
        "si_name": "Q11570",
        "symbol": "dwt",
@@ -5249,11 +5254,6 @@
        "symbol": "μA",
        "to_si_factor": 1e-06
    },
-    "Q31274648": {
-        "si_name": "Q6137407",
-        "symbol": "FPS",
-        "to_si_factor": 1.0
-    },
    "Q3186734": {
        "si_name": "Q3186734",
        "symbol": "J/(m³ K)",
--- a/searx/engines/azure.py
+++ b/searx/engines/azure.py
@@ -25,7 +25,6 @@ To use this engine, add an entry similar to the following to your engine list in
    https://learn.microsoft.com/en-us/entra/identity-platform/quickstart-register-app

 """
-
 import typing as t

 from searx.enginelib import EngineCache
--- a/searx/engines/base.py
+++ b/searx/engines/base.py
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """BASE (Scholar publications)"""
-
 from datetime import datetime
 import re

--- a/searx/engines/command.py
+++ b/searx/engines/command.py
@@ -83,6 +83,7 @@ from threading import Thread
 from searx import logger
 from searx.result_types import EngineResults

+
 engine_type = 'offline'
 paging = True
 command = []
--- a/searx/engines/docker_hub.py
+++ b/searx/engines/docker_hub.py
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Docker Hub (IT)"""
-
 # pylint: disable=use-dict-literal

 from urllib.parse import urlencode
--- a/searx/engines/duckduckgo.py
+++ b/searx/engines/duckduckgo.py
@@ -164,7 +164,6 @@ Terms / phrases that you keep coming across:
   https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Headers/Accept-Language

 """
-
 # pylint: disable=global-statement

 import json
--- a/searx/engines/duckduckgo_definitions.py
+++ b/searx/engines/duckduckgo_definitions.py
@@ -12,7 +12,6 @@ least we could not find out how language support should work.  It seems that
 most of the features are based on English terms.

 """
-
 import typing as t

 from urllib.parse import urlencode, urlparse, urljoin
--- a/searx/engines/duckduckgo_weather.py
+++ b/searx/engines/duckduckgo_weather.py
@@ -17,6 +17,7 @@ from searx.result_types import EngineResults
 from searx.extended_types import SXNG_Response
 from searx import weather

+
 about = {
    "website": 'https://duckduckgo.com/',
    "wikidata_id": 'Q12805',
--- a/searx/engines/dummy-offline.py
+++ b/searx/engines/dummy-offline.py
@@ -2,6 +2,7 @@
 # pylint: disable=invalid-name
 """Dummy Offline"""

+
 # about
 about = {
    "wikidata_id": None,
--- a/searx/engines/github_code.py
+++ b/searx/engines/github_code.py
@@ -65,6 +65,7 @@ code lines are just relabeled (starting from 1) and appended (a disjoint set of
 code blocks in a single file might be returned from the API).
 """

+
 import typing as t
 from urllib.parse import urlencode

--- a/searx/engines/google.py
+++ b/searx/engines/google.py
@@ -9,15 +9,12 @@ engines:
 - :ref:`google scholar engine`
 - :ref:`google autocomplete`

-This implementation uses Nokia user agents to request an XML layout from Google.
-The normal web version requires executing JavaScript to load the results and
-therefore is currently not used here.  See `Google discussion`_ for more
-information on that topic.
-
-.. _Google discussion: https://github.com/searxng/searxng/issues/6359
 """

 import random
+import re
+import string
+import time
 import typing as t
 from urllib.parse import unquote, urlencode

@@ -47,16 +44,16 @@ about = {
    "official_api_documentation": "https://developers.google.com/custom-search/",
    "use_official_api": False,
    "require_api_key": False,
-    "results": "XML",
+    "results": "HTML",
 }

 # engine dependent config
 categories = ["general", "web"]
 paging = True
 max_page = 50
-"""Google supports up to 50 pages of results, see the `Google max_page discussion`_.
+"""`Google max 50 pages`_

-.. _Google max_page discussion: https://github.com/searxng/searxng/issues/2982
+.. _Google max 50 pages: https://github.com/searxng/searxng/issues/2982
 """
 time_range_support = True
 language_support = True
@@ -67,23 +64,38 @@ time_range_dict = {"day": "d", "week": "w", "month": "m", "year": "y"}
 # Filter results. 0: None, 1: Moderate, 2: Strict
 filter_mapping = {0: "off", 1: "medium", 2: "high"}

-# https://github.com/searxng/searxng/issues/6359
-nokia_useragents = (
-    "Nokia7610/2.0 (5.0509.0) SymbianOS/7.0s Series60/2.1 Profile/MIDP-2.0 Configuration/CLDC-1.0",
-    "Nokia7610/2.0 (7.0642.0) SymbianOS/7.0s Series60/2.1 Profile/MIDP-2.0 Configuration/CLDC-1.0",
-    "Nokia6230/2.0 (05.50) Profile/MIDP-2.0 Configuration/CLDC-1.1",
-    "Nokia6230i/2.0 (03.80) Profile/MIDP-2.0 Configuration/CLDC-1.1",
-    "Nokia6280/2.0 (03.60) Profile/MIDP-2.0 Configuration/CLDC-1.1",
-    "NokiaN72/2.0617.1.0.3 Series60/2.8 Profile/MIDP-2.0 Configuration/CLDC-1.1",
-)
-
-
 # specific xpath variables
 # ------------------------

 # Suggestions are links placed in a *card-section*, we extract only the text
 # from the links not the links itself.
-suggestion_xpath = '//table[contains(@class, "HExoMb")]//a[contains(@class, "ZWRArf")]'
+suggestion_xpath = '//div[contains(@class, "gGQDvd iIWm4b")]//a'
+
+
+_arcid_range = string.ascii_letters + string.digits + "_-"
+_arcid_random: tuple[str, int] | None = None
+
+
+def ui_async(start: int) -> str:
+    """Format of the response from UI's async request.
+
+    - ``arc_id:<...>,use_ac:true,_fmt:prog``
+
+    The arc_id is random generated every hour.
+    """
+    global _arcid_random  # pylint: disable=global-statement
+
+    use_ac = "use_ac:true"
+    # _fmt:html returns a HTTP 500 when user search for celebrities like
+    # '!google natasha allegri' or '!google chris evans'
+    _fmt = "_fmt:prog"
+
+    # create a new random arc_id every hour
+    if not _arcid_random or (int(time.time()) - _arcid_random[1]) > 3600:
+        _arcid_random = ("".join(random.choices(_arcid_range, k=23)), int(time.time()))
+    arc_id = f"arc_id:srp_{_arcid_random[0]}_1{start:02}"
+
+    return ",".join([arc_id, use_ac, _fmt])


 def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[str, t.Any]:
@@ -115,11 +127,19 @@ def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[st
            A instance of :py:obj:`babel.core.Locale` build from the
            ``searxng_locale`` value.

+        subdomain:
+            Google subdomain :py:obj:`google_domains` that fits to the country
+            code.
+
        params:
            Py-Dictionary with additional request arguments (can be passed to
            :py:func:`urllib.parse.urlencode`).

            - ``hl`` parameter: specifies the interface language of user interface.
+            - ``lr`` parameter: restricts search results to documents written in
+              a particular language.
+            - ``cr`` parameter: restricts search results to documents
+              originating in a particular country.
            - ``ie`` parameter: sets the character encoding scheme that should
              be used to interpret the query string ('utf8').
            - ``oe`` parameter: sets the character encoding scheme that should
@@ -136,6 +156,7 @@ def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[st
    ret_val: dict[str, t.Any] = {
        "language": None,
        "country": None,
+        "subdomain": None,
        "params": {},
        "headers": {},
        "cookies": {},
@@ -148,7 +169,7 @@ def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[st
    except babel.core.UnknownLocaleError:
        locale = None

-    eng_lang = eng_traits.get_language(sxng_locale) or "lang_en"
+    eng_lang = eng_traits.get_language(sxng_locale, "lang_en")
    lang_code = eng_lang.split("_")[-1]  # lang_zh-TW --> zh-TW / lang_en --> en
    country = eng_traits.get_region(sxng_locale, eng_traits.all_locale)

@@ -163,6 +184,7 @@ def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[st
    ret_val["language"] = eng_lang
    ret_val["country"] = country
    ret_val["locale"] = locale
+    ret_val["subdomain"] = eng_traits.custom["supported_domains"].get(country.upper(), "www.google.com")

    # hl parameter:
    #   The hl parameter specifies the interface language (host language) of
@@ -201,11 +223,9 @@ def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[st

    # specify a region (country) only if a region is given in the selected
    # locale --> https://github.com/searxng/searxng/issues/2672
-
-    if country is not None:
-        ret_val["params"]["cr"] = ""
-        if len(sxng_locale.split("-")) > 1:
-            ret_val["params"]["cr"] = "country" + country
+    ret_val["params"]["cr"] = ""
+    if len(sxng_locale.split("-")) > 1:
+        ret_val["params"]["cr"] = "country" + country

    # gl parameter: (mandatory by Google News)
    #   The gl parameter value is a two-letter country code. For WebSearch
@@ -280,77 +300,88 @@ def detect_google_sorry(resp: "SXNG_Response"):
        raise SearxEngineCaptchaException()


-def unwrap_google_url(raw_url: str) -> str:
-    # remove redirector from url
-    if raw_url.startswith("/url?q="):
-        return unquote(raw_url[7:].split("&sa=U")[0])
-    return raw_url
-
-
-def wml_dom(resp: "SXNG_Response"):
-    detect_google_sorry(resp)
-    text = resp.text
-    if text.lstrip().startswith("<?xml"):
-        text = text.split("?>", 1)[-1]
-    return html.fromstring(text)
-
-
-def google_request(
-    query: str,
-    params: "OnlineParams",
-    extra_args: dict[str, t.Any] | None = None,
-    *,
-    eng_traits: EngineTraits | None = None,
-    use_time_range: bool = True,
-    use_safesearch: bool = True,
-    safesearch_map: dict[int, str] | None = None,
-    use_locales: bool = True,
-) -> None:
-    google_info = get_google_info(params, eng_traits or traits)
-    if not use_locales:
-        google_info["params"].pop("lr")
-        google_info["params"].pop("cr")
-
-    start = (params["pageno"] - 1) * 10
-    args: dict[str, t.Any] = {
-        "q": query,
-        "sca_esv": "1",
-        **google_info["params"],
-        **(extra_args or {}),
-    }
-    if start:
-        args["start"] = start
-    if use_time_range and params["time_range"] in time_range_dict:
-        args["tbs"] = "qdr:" + time_range_dict[params["time_range"]]
-    if use_safesearch and params["safesearch"]:
-        args["safe"] = (safesearch_map or filter_mapping)[params["safesearch"]]
-
-    params["url"] = f"https://www.google.com/wml/search?{urlencode(args)}"
-    params["headers"]["User-Agent"] = random.choice(nokia_useragents)
-
-
 def request(query: str, params: "OnlineParams") -> None:
-    google_request(query, params)
+    """Google search request"""
+    # pylint: disable=line-too-long
+    start = (params["pageno"] - 1) * 10
+    google_info = get_google_info(params, traits)
+
+    # https://www.google.de/search?q=corona&hl=de&lr=lang_de&start=0&tbs=qdr%3Ad&safe=medium
+    query_url = (
+        "https://"
+        + google_info["subdomain"]
+        + "/search"
+        + "?"
+        + urlencode(
+            {
+                "q": query,
+                **google_info["params"],
+                "filter": "0",
+                "start": start,
+                # 'vet': '12ahUKEwik3ZbIzfn7AhXMX_EDHbUDBh0QxK8CegQIARAC..i',
+                # 'ved': '2ahUKEwik3ZbIzfn7AhXMX_EDHbUDBh0Q_skCegQIARAG',
+                # 'cs' : 1,
+                # 'sa': 'N',
+                # 'yv': 3,
+                # 'prmd': 'vin',
+                # 'ei': 'GASaY6TxOcy_xc8PtYeY6AE',
+                # 'sa': 'N',
+                # 'sstk': 'AcOHfVkD7sWCSAheZi-0tx_09XDO55gTWY0JNq3_V26cNN-c8lfD45aZYPI8s_Bqp8s57AHz5pxchDtAGCA_cikAWSjy9kw3kgg'
+                # formally known as use_mobile_ui
+                # "asearch": "arc",
+                # "async": str_async,
+            }
+        )
+    )
+
+    if params["time_range"] in time_range_dict:
+        query_url += "&" + urlencode({"tbs": "qdr:" + time_range_dict[params["time_range"]]})
+    if params["safesearch"]:
+        query_url += "&" + urlencode({"safe": filter_mapping[params["safesearch"]]})
+    params["url"] = query_url
+
+    params["cookies"] = google_info["cookies"]
+    params["headers"].update(google_info["headers"])


-def response(resp: "SXNG_Response") -> EngineResults:
+# regex match to get image map that is found inside the returned javascript:
+# (function(){var s='...';var i=['...'] ...}
+RE_DATA_IMAGE = re.compile(r"(data:image[^']*?)'[^']*?'((?:dimg|pimg|tsuid)[^']*)")
+
+
+def parse_url_images(text: str):
+    data_image_map = {}
+
+    for image_url, img_id in RE_DATA_IMAGE.findall(text):
+        data_image_map[img_id] = image_url.encode('utf-8').decode("unicode-escape")
+    logger.debug("data:image objects --> %s", list(data_image_map.keys()))
+    return data_image_map
+
+
+def response(resp: "SXNG_Response"):
+    """Get response from google's search request"""
+    # pylint: disable=too-many-branches, too-many-statements
+    detect_google_sorry(resp)
+    data_image_map = parse_url_images(resp.text)
+
    results = EngineResults()
-    dom = wml_dom(resp)
+
+    # convert the text to dom
+    dom = html.fromstring(resp.text)

    # parse results
-    for result in eval_xpath_list(dom, '//div[contains(@class, "zMzFAb")]'):
+    for result in eval_xpath_list(dom, '//a[@data-ved and not(@class)]'):
+        # pylint: disable=too-many-nested-blocks

        try:
-            title_tag = eval_xpath_getindex(
-                result, './/a[contains(@class, "fuLhoc")]//span[contains(@class, "CVA68e")]', 0, default=None
-            )
+            title_tag = eval_xpath_getindex(result, './/div[@style]', 0, default=None)
            if title_tag is None:
                # this not one of the common google results *section*
                logger.debug("ignoring item from the result_xpath list: missing title")
                continue
            title = extract_text(title_tag)

-            raw_url = eval_xpath_getindex(result, './/a[contains(@class, "fuLhoc")]/@href', 0, default=None)
+            raw_url = result.get("href")
            if raw_url is None:
                logger.debug(
                    'ignoring item from the result_xpath list: missing url of title "%s"',
@@ -358,19 +389,30 @@ def response(resp: "SXNG_Response") -> EngineResults:
                )
                continue

-            url = unwrap_google_url(raw_url)
-            content = extract_text(
-                eval_xpath(result, './/div[contains(@class, "taTFJ")]//span[contains(@class, "FrIlee")]')
-            )
-            thumbnail = eval_xpath_getindex(result, './/img[contains(@src, "encrypted-tbn")]/@src', 0, default=None)
-            results.add(
-                results.types.MainResult(
-                    url=url,
-                    title=title or "",
-                    content=content or "",
-                    thumbnail=thumbnail or "",
-                )
-            )
+            if raw_url.startswith('/url?q='):
+                url = unquote(raw_url[7:].split("&sa=U")[0])  # remove the google redirector
+            else:
+                url = raw_url
+
+            content_nodes = eval_xpath(result, '../..//div[contains(@class, "ilUpNd H66NU aSRlid")]')
+            for item in content_nodes:
+                for script in item.xpath(".//script"):
+                    script.getparent().remove(script)
+
+            content = extract_text(content_nodes[0])
+
+            # Images that are NOT the favicon
+            xpath_image = eval_xpath_getindex(result, './/img', index=0, default=None)
+
+            thumbnail = None
+            if xpath_image is not None:
+                thumbnail = xpath_image.get("src")
+                if thumbnail.startswith("data:image"):
+                    img_id = xpath_image.get("id")
+                    if img_id:
+                        thumbnail = data_image_map.get(img_id)
+
+            results.append({"url": url, "title": title, "content": content or '', "thumbnail": thumbnail})

        except Exception as e:  # pylint: disable=broad-except
            logger.error(e, exc_info=True)
@@ -378,8 +420,10 @@ def response(resp: "SXNG_Response") -> EngineResults:

    # parse suggestion
    for suggestion in eval_xpath_list(dom, suggestion_xpath):
-        results.add(results.types.LegacyResult(suggestion=extract_text(suggestion)))
+        # append suggestion
+        results.append({"suggestion": extract_text(suggestion)})

+    # return results
    return results


@@ -412,12 +456,14 @@ skip_countries = [
 ]


-def fetch_traits(engine_traits: EngineTraits):
+def fetch_traits(engine_traits: EngineTraits, add_domains: bool = True):
    """Fetch languages from Google."""
    # pylint: disable=import-outside-toplevel, too-many-branches

    from searx.network import get  # see https://github.com/searxng/searxng/issues/762

+    engine_traits.custom["supported_domains"] = {}
+
    resp = get("https://www.google.com/preferences", timeout=5)
    if not resp.ok:
        raise RuntimeError("Response from Google preferences is not OK.")
@@ -468,3 +514,22 @@ def fetch_traits(engine_traits: EngineTraits):

    # alias regions
    engine_traits.regions["zh-CN"] = "HK"
+
+    # supported domains
+
+    if add_domains:
+        resp = get("https://www.google.com/supported_domains", timeout=5)
+        if not resp.ok:
+            raise RuntimeError("Response from Google supported domains is not OK.")
+
+        for domain in resp.text.split():
+            domain = domain.strip()
+            if not domain or domain in [
+                ".google.com",
+            ]:
+                continue
+            region = domain.split(".")[-1].upper()
+            engine_traits.custom["supported_domains"][region] = "www" + domain
+            if region == "HK":
+                # There is no google.cn, we use .com.hk for zh-CN
+                engine_traits.custom["supported_domains"]["CN"] = "www" + domain
--- a/searx/engines/google_cse.py
+++ b/searx/engines/google_cse.py
@@ -95,11 +95,12 @@ def request(query: str, params: "OnlineParams") -> None:
    token = _cse_token()

    google_info = get_google_info(params, traits)
+    info: dict[str, str] = google_info["params"]

    args = {
        "rsz": "filtered_cse",
        "num": str(page_size),
-        "hl": google_info["params"]["hl"],
+        "hl": info["hl"],
        "cselibv": token["cselibv"],
        "cx": CX,
        "q": query,
@@ -113,6 +114,10 @@ def request(query: str, params: "OnlineParams") -> None:
        start_date, end_date = _get_start_and_end_date_str(params["time_range"])
        args["sort"] = f"date:r:{start_date}:{end_date}"

+    if info.get("lr"):
+        args["lr"] = info["lr"]
+    if info.get("cr"):
+        args["cr"] = info["cr"]
    if google_info["country"] not in (None, "ZZ"):
        args["gl"] = google_info["country"]
    if token["exp"]:
--- a/searx/engines/google_images.py
+++ b/searx/engines/google_images.py
@@ -1,75 +1,122 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""Google Images: see :py:obj:`searx.engines.google`."""
+"""This is the implementation of the Google Images engine using the internal
+Google API used by the Google Go Android app.

-import typing as t
-from urllib.parse import parse_qs, unquote, urlparse
+This internal API offer results in
+
+- JSON (``_fmt:json``)
+- Protobuf_ (``_fmt:pb``)
+- Protobuf_ compressed? (``_fmt:pc``)
+- HTML (``_fmt:html``)
+- Protobuf_ encoded in JSON (``_fmt:jspb``).
+
+.. _Protobuf: https://en.wikipedia.org/wiki/Protocol_Buffers
+"""
+
+from urllib.parse import urlencode
+from json import loads

 from searx.engines.google import fetch_traits  # pylint: disable=unused-import
-from searx.engines.google import google_request, wml_dom
-from searx.result_types import EngineResults
-from searx.utils import eval_xpath_list
-
-if t.TYPE_CHECKING:
-    from searx.extended_types import SXNG_Response
-    from searx.search.processors import OnlineParams
+from searx.engines.google import (
+    get_google_info,
+    time_range_dict,
+    detect_google_sorry,
+)

 # about
 about = {
-    "website": "https://images.google.com",
-    "wikidata_id": "Q521550",
-    "official_api_documentation": "https://developers.google.com/custom-search",
+    "website": 'https://images.google.com',
+    "wikidata_id": 'Q521550',
+    "official_api_documentation": 'https://developers.google.com/custom-search',
    "use_official_api": False,
    "require_api_key": False,
-    "results": "XML",
+    "results": 'JSON',
 }

 # engine dependent config
-categories = ["images", "web"]
+categories = ['images', 'web']
 paging = True
 max_page = 50
-"""Google supports up to 50 pages of results, see the `Google max_page discussion`_.
+"""`Google max 50 pages`_

-.. _Google max_page discussion: https://github.com/searxng/searxng/issues/2982
+.. _Google max 50 pages: https://github.com/searxng/searxng/issues/2982
 """

 time_range_support = True
 language_support = True
 safesearch = True

-filter_mapping = {0: "images", 1: "active", 2: "active"}
+filter_mapping = {0: 'images', 1: 'active', 2: 'active'}


-def request(query: str, params: "OnlineParams") -> None:
-    google_request(
-        query,
-        params,
-        {"tbm": "isch"},
-        eng_traits=traits,
-        safesearch_map=filter_mapping,
-        use_locales=False,
+def request(query, params):
+    """Google-Image search request"""
+
+    google_info = get_google_info(params, traits)
+
+    query_url = (
+        'https://'
+        + google_info['subdomain']
+        + '/search'
+        + '?'
+        + urlencode({'q': query, 'tbm': "isch", **google_info['params'], 'asearch': 'isch'})
+        # don't urlencode this because wildly different AND bad results
+        # pagination uses Zero-based numbering
+        + f'&async=_fmt:json,p:1,ijn:{params["pageno"] - 1}'
    )

+    if params['time_range'] in time_range_dict:
+        query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
+    if params['safesearch']:
+        query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
+    params['url'] = query_url
+    params['cookies'] = google_info['cookies']
+    params['headers'].update(google_info['headers'])
+    # this ua will allow getting ~50 results instead of 10. #1641
+    params['headers']['User-Agent'] = (
+        'NSTN/3.60.474802233.release Dalvik/2.1.0 (Linux; U; Android 12;' f' {google_info.get("country", "US")}) gzip'
+    )

-def response(resp: "SXNG_Response") -> EngineResults:
-    results = EngineResults()
-    dom = wml_dom(resp)
+    return params

-    for link in eval_xpath_list(dom, '//a[contains(@href, "/imgres?")]'):
-        qs = parse_qs(urlparse(link.get("href", "")).query)
-        img_src = qs.get("imgurl", [""])[0]
-        url = qs.get("imgrefurl", [""])[0]
-        if not img_src or not url:
-            continue
-        width, height = qs.get("w", [""])[0], qs.get("h", [""])[0]
-        tbnid = qs.get("tbnid", [""])[0]
-        results.add(
-            results.types.Image(
-                url=url,
-                title=unquote(urlparse(img_src).path.rsplit("/", 1)[-1]) or urlparse(url).netloc,
-                img_src=img_src,
-                thumbnail_src=f"https://encrypted-tbn0.gstatic.com/images?q=tbn:{tbnid}",
-                resolution=f"{width} x {height}" if width and height else "",
-            )
-        )
+
+def response(resp):
+    """Get response from google's search request"""
+    results = []
+
+    detect_google_sorry(resp)
+
+    json_start = resp.text.find('{"ischj":')
+    json_data = loads(resp.text[json_start:])
+
+    for item in json_data["ischj"].get("metadata", []):
+        result_item = {
+            'url': item["result"]["referrer_url"],
+            'title': item["result"]["page_title"],
+            'content': item["text_in_grid"]["snippet"],
+            'source': item["result"]["site_title"],
+            'resolution': f'{item["original_image"]["width"]} x {item["original_image"]["height"]}',
+            'img_src': item["original_image"]["url"],
+            'thumbnail_src': item["thumbnail"]["url"],
+            'template': 'images.html',
+        }
+
+        author = item["result"].get('iptc', {}).get('creator')
+        if author:
+            result_item['author'] = ', '.join(author)
+
+        copyright_notice = item["result"].get('iptc', {}).get('copyright_notice')
+        if copyright_notice:
+            result_item['source'] += ' | ' + copyright_notice
+
+        freshness_date = item["result"].get("freshness_date")
+        if freshness_date:
+            result_item['source'] += ' | ' + freshness_date
+
+        file_size = item.get('gsa', {}).get('file_size')
+        if file_size:
+            result_item['source'] += ' (%s)' % file_size
+
+        results.append(result_item)

    return results
--- a/searx/engines/google_news.py
+++ b/searx/engines/google_news.py
@@ -1,91 +1,324 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""Google News: see :py:obj:`searx.engines.google`."""
+"""This is the implementation of the Google News engine.

+Google News has a different region handling compared to Google WEB.
+
+- the ``ceid`` argument has to be set (:py:obj:`ceid_list`)
+- the hl_ argument has to be set correctly (and different to Google WEB)
+- the gl_ argument is mandatory
+
+If one of this argument is not set correctly, the request is redirected to
+CONSENT dialog::
+
+  https://consent.google.com/m?continue=
+
+The google news API ignores some parameters from the common :ref:`google API`:
+
+- num_ : the number of search results is ignored / there is no paging all
+  results for a query term are in the first response.
+- save_ : is ignored / Google-News results are always *SafeSearch*
+
+.. _hl: https://developers.google.com/custom-search/docs/xml_results#hlsp
+.. _gl: https://developers.google.com/custom-search/docs/xml_results#glsp
+.. _num: https://developers.google.com/custom-search/docs/xml_results#numsp
+.. _save: https://developers.google.com/custom-search/docs/xml_results#safesp
+"""
 import typing as t

-from searx.engines.google import fetch_traits  # pylint: disable=unused-import
-from searx.engines.google import google_request, unwrap_google_url, wml_dom
-from searx.result_types import EngineResults
+import json
+import base64
+from urllib.parse import urlencode
+from lxml import html
+import babel
+
+from searx import locales
 from searx.utils import (
-    eval_xpath_getindex,
+    eval_xpath,
    eval_xpath_list,
+    eval_xpath_getindex,
    extract_text,
 )

+from searx.engines.google import fetch_traits as _fetch_traits  # pylint: disable=unused-import
+from searx.engines.google import (
+    get_google_info,
+    detect_google_sorry,
+)
+from searx.enginelib.traits import EngineTraits
+
+from searx.result_types import EngineResults
+
 if t.TYPE_CHECKING:
    from searx.extended_types import SXNG_Response
    from searx.search.processors import OnlineParams

 # about
 about = {
-    "website": "https://www.google.com",
+    "website": "https://news.google.com",
    "wikidata_id": "Q12020",
    "official_api_documentation": "https://developers.google.com/custom-search",
    "use_official_api": False,
    "require_api_key": False,
-    "results": "XML",
+    "results": "HTML",
 }

 # engine dependent config
 categories = ["news"]
-paging = True
-max_page = 50
-"""Google supports up to 50 pages of results, see the `Google max_page discussion`_.
-
-.. _Google max_page discussion: https://github.com/searxng/searxng/issues/2982
-"""
+paging = False
 time_range_support = False
 language_support = True
-safesearch = False
+
+# Google-News results are always *SafeSearch*. Option 'safesearch' is set to
+# False here.
+#
+#  safesearch : results are identical for safesearch=0 and safesearch=2
+safesearch = True
+base_url: str = "https://news.google.com"


 def request(query: str, params: "OnlineParams") -> None:
-    google_request(
-        query,
-        params,
-        {"tbm": "nws"},
-        eng_traits=traits,
-        use_time_range=False,
-        use_safesearch=False,
-        use_locales=False,
+    """Google-News search request"""
+
+    sxng_locale = params.get("searxng_locale", "en-US")
+    ceid: str = locales.get_engine_locale(
+        sxng_locale, traits.custom["ceid"], default="US:en"
+    )  # pyright: ignore[reportAssignmentType]
+    google_info = get_google_info(params, traits)
+    google_info["subdomain"] = "news.google.com"  # google news has only one domain
+
+    ceid_region, ceid_lang = ceid.split(":")
+    ceid_lang, ceid_suffix = (
+        ceid_lang.split(":")
+        + [
+            "",
+        ]
+    )[:2]
+
+    google_info["params"]["hl"] = ceid_lang
+
+    if ceid_suffix and ceid_suffix not in ["Hans", "Hant"]:
+
+        if ceid_region.lower() == ceid_lang:
+            google_info["params"]["hl"] = ceid_lang + "-" + ceid_region
+        else:
+            google_info["params"]["hl"] = ceid_lang + "-" + ceid_suffix
+
+    elif ceid_region.lower() != ceid_lang:
+
+        if ceid_region in ["AT", "BE", "CH", "IL", "SA", "IN", "BD", "PT"]:
+            google_info["params"]["hl"] = ceid_lang
+        else:
+            google_info["params"]["hl"] = ceid_lang + "-" + ceid_region
+
+    google_info["params"]["lr"] = "lang_" + ceid_lang.split("-")[0]
+    google_info["params"]["gl"] = ceid_region
+
+    query_url = (
+        "https://"
+        + google_info["subdomain"]
+        + "/search?"
+        + urlencode(
+            {"q": query, **google_info["params"]},
+        )
+        # ceid includes a ':' character which must not be urlencoded
+        + ("&ceid=%s" % ceid)
    )

-
-def _span_text(link, css_class: str):
-    return extract_text(
-        eval_xpath_getindex(link, f'.//span[contains(@class, "{css_class}")]', 0, default=None),
-        allow_none=True,
-    )
+    params["url"] = query_url
+    params["cookies"] = google_info["cookies"]
+    params["headers"].update(google_info["headers"])


 def response(resp: "SXNG_Response") -> EngineResults:
-    results = EngineResults()
-    seen = set()
-    for link in eval_xpath_list(wml_dom(resp), '//a[contains(@href, "/url?q=")]'):
-        href = link.get("href")
-        if not href:
+    """Get response from google's search request"""
+
+    res = EngineResults()
+
+    detect_google_sorry(resp)
+
+    # convert the text to dom
+    dom = html.fromstring(resp.text)
+
+    for result in eval_xpath_list(dom, "//div[@jslog and @data-n-tid and @jsdata]"):
+
+        url: str = eval_xpath_getindex(result, "./a[@target='_blank']/@href", 0, default=0)
+        if not url:
+            continue
+        if url.startswith("./"):
+            url = base_url + url[1:]
+
+        # The real URL is often encoded in the "jslog" attribute
+        jslog: str | None = eval_xpath_getindex(result, "./a[@target='_blank']/@jslog", 0, default=None)
+
+        # Try to extract the real URL from jslog
+        real_url: str | None = None
+        if jslog:
+            # jslog format is usually: "95014; 5:<base64>; track:click,vis".  We
+            # want the second part (index 1) after splitting by ";"
+            parts: list[str] = jslog.split(";")
+            if len(parts) > 1:
+                b64_data: str = parts[1].split(":")[-1].strip()
+                # Pad base64 if necessary
+                b64_data += "=" * (-len(b64_data) % 4)
+                decoded_data: list[str | None] = json.loads(base64.b64decode(b64_data).decode("utf-8"))
+                # The URL is typically the last element in the decoded array
+                if (
+                    isinstance(decoded_data, list)
+                    and isinstance(decoded_data[-1], str)
+                    and decoded_data[-1].startswith("http")
+                ):
+                    real_url = decoded_data[-1]
+        if real_url:
+            url = real_url
+        else:
+            logger.error(f"no real-url found: {url}")
            continue

-        url = unwrap_google_url(href)
-        if url in seen or "google.com/search" in url:
-            continue
+        title = extract_text(eval_xpath(result, "./h4")) or ""

-        title = _span_text(link, "M3vVJe") or _span_text(link, "fuLhoc")
-        if not title:
-            continue
+        # The pub_date is mostly a string like 'yesterday', not a real timezone
+        # date or time.  Therefore we can't use publishedDate and place the
+        # *pub* sting into the content.

-        source = _span_text(link, "dXDvrc")
-        pub_date = _span_text(link, "YVIcad")
-        thumbnail = eval_xpath_getindex(link, './/img[contains(@src, "encrypted-tbn")]/@src', 0, default=None)
+        pub_date = extract_text(eval_xpath(result, ".//time"))
+        pub_origin = extract_text(eval_xpath(result, ".//div[contains(@class, 'vr1PYe')]"))
+        content = " / ".join([x for x in [pub_origin, pub_date] if x])

-        seen.add(url)
-        results.add(
-            results.types.MainResult(
+        thumbnail: str = eval_xpath_getindex(result, ".//figure/img/@src", 0, default="")
+        if thumbnail and thumbnail.startswith("/"):
+            thumbnail = base_url + thumbnail
+
+        res.add(
+            res.types.MainResult(
                url=url,
                title=title,
-                content=" / ".join(x for x in [source, pub_date] if x),
-                thumbnail=thumbnail or "",
+                content=content,
+                thumbnail=thumbnail,
            )
        )

-    return results
+    return res
+
+
+ceid_list = [
+    "AE:ar",
+    "AR:es-419",
+    "AT:de",
+    "AU:en",
+    "BD:bn",
+    "BE:fr",
+    "BE:nl",
+    "BG:bg",
+    "BR:pt-419",
+    "BW:en",
+    "CA:en",
+    "CA:fr",
+    "CH:de",
+    "CH:fr",
+    "CL:es-419",
+    "CN:zh-Hans",
+    "CO:es-419",
+    "CU:es-419",
+    "CZ:cs",
+    "DE:de",
+    "EE:et",
+    "EG:ar",
+    "ES:ca",
+    "ES:es",
+    "ET:en",
+    "FI:fi",
+    "FR:fr",
+    "GB:en",
+    "GH:en",
+    "GR:el",
+    "HK:zh-Hant",
+    "HU:hu",
+    "ID:en",
+    "ID:id",
+    "IE:en",
+    "IL:en",
+    "IL:he",
+    "IN:bn",
+    "IN:en",
+    "IN:gu",
+    "IN:hi",
+    "IN:ml",
+    "IN:mr",
+    "IN:pa",
+    "IN:ta",
+    "IN:te",
+    "IT:it",
+    "JP:ja",
+    "KE:en",
+    "KR:ko",
+    "LB:ar",
+    "LT:lt",
+    "LV:en",
+    "LV:lv",
+    "MA:fr",
+    "MY:en",
+    "MY:ms",
+    "NA:en",
+    "NG:en",
+    "NL:nl",
+    "NO:no",
+    "NZ:en",
+    "PH:en",
+    "PK:en",
+    "PL:pl",
+    "RO:ro",
+    "RS:sr",
+    "RU:ru",
+    "SA:ar",
+    "SE:sv",
+    "SG:en",
+    "SI:sl",
+    "SK:sk",
+    "SN:fr",
+    "TH:th",
+    "TR:tr",
+    "TZ:en",
+    "UA:ru",
+    "UA:uk",
+    "UG:en",
+    "US:en",
+    "VN:vi",
+    "ZA:en",
+    "ZW:en",
+]
+"""List of region/language combinations supported by Google News.  Values of the
+``ceid`` argument of the Google News REST API."""
+
+
+_skip_values = [
+    "ET:en",  # english (ethiopia)
+    "ID:en",  # english (indonesia)
+    "LV:en",  # english (latvia)
+]
+
+_ceid_locale_map = {"NO:no": "nb-NO"}
+
+
+def fetch_traits(engine_traits: EngineTraits):
+    _fetch_traits(engine_traits, add_domains=False)
+
+    engine_traits.custom["ceid"] = {}
+
+    for ceid in ceid_list:
+        if ceid in _skip_values:
+            continue
+
+        region, lang = ceid.split(":")
+        x = lang.split("-")
+        if len(x) > 1:
+            if x[1] not in ["Hant", "Hans"]:
+                lang = x[0]
+
+        sxng_locale = _ceid_locale_map.get(ceid, lang + "-" + region)
+        try:
+            locale = babel.Locale.parse(sxng_locale, sep="-")
+        except babel.UnknownLocaleError:
+            print("ERROR: %s -> %s is unknown by babel" % (ceid, sxng_locale))
+            continue
+
+        engine_traits.custom["ceid"][locales.region_tag(locale)] = ceid
--- a/searx/engines/google_scholar.py
+++ b/searx/engines/google_scholar.py
@@ -77,6 +77,8 @@ def request(query: str, params: "OnlineParams") -> None:
    """Google-Scholar search request"""

    google_info = get_google_info(params, traits)
+    # subdomain is: scholar.google.xy
+    google_info["subdomain"] = google_info["subdomain"].replace("www.", "scholar.")

    args = {
        "q": query,
@@ -87,7 +89,7 @@ def request(query: str, params: "OnlineParams") -> None:
    }
    args.update(time_range_args(params))

-    params["url"] = "https://scholar.google.com/scholar?" + urlencode(args)
+    params["url"] = "https://" + google_info["subdomain"] + "/scholar?" + urlencode(args)
    params["cookies"] = google_info["cookies"]
    params["headers"].update(google_info["headers"])

--- a/searx/engines/google_videos.py
+++ b/searx/engines/google_videos.py
@@ -1,87 +1,185 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""Google Videos: see :py:obj:`searx.engines.google`."""
+"""This is the implementation of the Google Videos engine.

-import typing as t
+.. admonition:: Content-Security-Policy (CSP)
+
+   This engine needs to allow images from the `data URLs`_ (prefixed with the
+   ``data:`` scheme)::
+
+     Header set Content-Security-Policy "img-src 'self' data: ;"
+
+.. _data URLs:
+   https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URIs
+"""
+import re
+from urllib.parse import urlencode, urlparse, parse_qs, unquote
+from lxml import html

-from searx.engines.google import fetch_traits  # pylint: disable=unused-import
-from searx.engines.google import google_request, unwrap_google_url, wml_dom
-from searx.result_types import EngineResults
 from searx.utils import (
-    eval_xpath_getindex,
    eval_xpath_list,
+    eval_xpath_getindex,
    extract_text,
-    get_embeded_stream_url,
-    parse_duration_string,
 )

-if t.TYPE_CHECKING:
-    from searx.extended_types import SXNG_Response
-    from searx.search.processors import OnlineParams
+from searx.engines.google import fetch_traits  # pylint: disable=unused-import
+from searx.engines.google import (
+    get_google_info,
+    time_range_dict,
+    filter_mapping,
+    suggestion_xpath,
+    detect_google_sorry,
+    ui_async,
+)
+from searx.utils import get_embeded_stream_url

 # about
 about = {
-    "website": "https://www.google.com",
-    "wikidata_id": "Q219885",
-    "official_api_documentation": "https://developers.google.com/custom-search",
+    "website": 'https://www.google.com',
+    "wikidata_id": 'Q219885',
+    "official_api_documentation": 'https://developers.google.com/custom-search',
    "use_official_api": False,
    "require_api_key": False,
-    "results": "XML",
+    "results": 'HTML',
 }

 # engine dependent config
-categories = ["videos", "web"]
+categories = ['videos', 'web']
 paging = True
 max_page = 50
-"""Google supports up to 50 pages of results, see the `Google max_page discussion`_.
-
-.. _Google max_page discussion: https://github.com/searxng/searxng/issues/2982
-"""
 language_support = True
 time_range_support = True
 safesearch = True


-def request(query: str, params: "OnlineParams") -> None:
-    google_request(
-        query,
-        params,
-        {"tbm": "vid"},
-        eng_traits=traits,
-        use_locales=False,
+# =26;[3,"dimg_ZNMiZPCqE4apxc8P3a2tuAQ_137"]a87;data:image/jpeg;base64,/9j/4AAQSkZJRgABA
+# ...6T+9Nl4cnD+gr9OK8I56/tX3l86nWYw//2Q==26;
+RE_DATA_IMAGE = re.compile(r'"(dimg_[^"]*)"[^;]*;(data:image[^;]*;[^;]*);?')
+
+
+def parse_data_images(text: str):
+    data_image_map = {}
+
+    for img_id, data_image in RE_DATA_IMAGE.findall(text):
+        end_pos = data_image.rfind("=")
+        if end_pos > 0:
+            data_image = data_image[: end_pos + 1]
+        data_image_map[img_id] = data_image
+    logger.debug("data:image objects --> %s", list(data_image_map.keys()))
+    return data_image_map
+
+
+def request(query, params):
+    """Google-Video search request"""
+    google_info = get_google_info(params, traits)
+    start = (params['pageno'] - 1) * 10
+
+    query_url = (
+        'https://'
+        + google_info['subdomain']
+        + '/search'
+        + "?"
+        + urlencode(
+            {
+                'q': query,
+                'tbm': "vid",
+                'start': start,
+                **google_info['params'],
+                'asearch': 'arc',
+                'async': ui_async(start),
+            }
+        )
    )

+    if params['time_range'] in time_range_dict:
+        query_url += '&' + urlencode({'tbs': 'qdr:' + time_range_dict[params['time_range']]})
+    if 'safesearch' in params:
+        query_url += '&' + urlencode({'safe': filter_mapping[params['safesearch']]})
+    params['url'] = query_url

-def response(resp: "SXNG_Response") -> EngineResults:
-    results = EngineResults()
+    params['cookies'] = google_info['cookies']
+    params['headers'].update(google_info['headers'])
+    return params

-    for result in eval_xpath_list(wml_dom(resp), '//div[contains(@class, "zMzFAb")]'):
+
+def response(resp):
+    """Get response from google's search request"""
+    results = []
+
+    detect_google_sorry(resp)
+    data_image_map = parse_data_images(resp.text)
+
+    # convert the text to dom
+    dom = html.fromstring(resp.text)
+
+    result_divs = eval_xpath_list(dom, '//div[contains(@class, "MjjYud")]')
+
+    # parse results
+    for result in result_divs:
        title = extract_text(
-            eval_xpath_getindex(result, './/span[contains(@class, "CVA68e")]', 0, default=None),
+            eval_xpath_getindex(result, './/h3[contains(@class, "LC20lb")] | .//div[@role="heading"]', 0, default=None),
            allow_none=True,
        )
-        raw_url = eval_xpath_getindex(result, './/a[contains(@class, "fuLhoc")]/@href', 0, default=None)
-        if not title or not raw_url:
-            continue
-
-        url = unwrap_google_url(raw_url)
-        thumbnail = eval_xpath_getindex(result, './/img[contains(@class, "SygO9d")]/@src', 0, default="")
-        if "/default.jpg" in thumbnail:
-            thumbnail = thumbnail.split("?")[0].replace("/default.jpg", "/hqdefault.jpg")
-        length = None
-        for span in eval_xpath_list(result, './/span[contains(@class, "YVIcad")]'):
-            length = parse_duration_string(extract_text(span) or "")
-            if length:
-                break
-
-        results.add(
-            results.types.MainResult(
-                url=url,
-                title=title,
-                thumbnail=thumbnail,
-                length=length,
-                iframe_src=get_embeded_stream_url(url) or "",
-                template="videos.html",
-            )
+        url = eval_xpath_getindex(
+            result, './/a[@jsname="UWckNb"]/@href | .//a[contains(@href, "/url?q=")]/@href', 0, default=None
        )
+        if url and url.startswith('/url?q='):
+            url = unquote(url[7:].split('&sa=U')[0])
+
+        content = extract_text(
+            eval_xpath_getindex(result, './/div[contains(@class, "ITZIwc")]', 0, default=None), allow_none=True
+        )
+        pub_info = extract_text(
+            eval_xpath_getindex(
+                result, './/div[contains(@class, "gqF9jc")] | .//div[contains(@class, "WRu9Cd")]', 0, default=None
+            ),
+            allow_none=True,
+        )
+        # Broader XPath to find any <img> element
+        thumbnail = eval_xpath_getindex(result, './/img/@src', 0, default=None)
+        duration = extract_text(
+            eval_xpath_getindex(result, './/span[contains(@class, "k1U36b")]', 0, default=None), allow_none=True
+        )
+        video_id = eval_xpath_getindex(result, './/div[@jscontroller="rTuANe"]/@data-vid', 0, default=None)
+
+        # Fallback for video_id from URL if not found via XPath
+        if not video_id and url and 'youtube.com' in url:
+            parsed_url = urlparse(url)
+            video_id = parse_qs(parsed_url.query).get('v', [None])[0]
+
+        # Handle thumbnail
+        if thumbnail and thumbnail.startswith('data:image'):
+            img_id = eval_xpath_getindex(result, './/img/@id', 0, default=None)
+            if img_id and img_id in data_image_map:
+                thumbnail = data_image_map[img_id]
+            else:
+                thumbnail = None
+        if not thumbnail and video_id:
+            thumbnail = f"https://img.youtube.com/vi/{video_id}/hqdefault.jpg"
+
+        # Handle video embed URL
+        embed_url = None
+        if video_id:
+            embed_url = get_embeded_stream_url(f"https://www.youtube.com/watch?v={video_id}")
+        elif url:
+            embed_url = get_embeded_stream_url(url)
+
+        # Only append results with valid title and url
+        if title and url:
+            results.append(
+                {
+                    'url': url,
+                    'title': title,
+                    'content': content or '',
+                    'author': pub_info,
+                    'thumbnail': thumbnail,
+                    'length': duration,
+                    'iframe_src': embed_url,
+                    'template': 'videos.html',
+                }
+            )
+
+    # parse suggestion
+    for suggestion in eval_xpath_list(dom, suggestion_xpath):
+        results.append({'suggestion': extract_text(suggestion)})

    return results
--- a/searx/engines/hex.py
+++ b/searx/engines/hex.py
@@ -4,6 +4,7 @@
 from urllib.parse import urlencode
 from dateutil import parser

+
 about = {
    # pylint: disable=line-too-long
    "website": "https://hex.pm/",
--- a/searx/engines/jisho.py
+++ b/searx/engines/jisho.py
@@ -108,12 +108,14 @@ def get_infobox(alt_forms, result_url, definitions):
        infobox_content.append(f'<p><i>Other forms:</i> {", ".join(alt_forms[1:])}</p>')

    # definitions
-    infobox_content.append('''
+    infobox_content.append(
+        '''
        <small><a href="https://www.edrdg.org/wiki/index.php/JMdict-EDICT_Dictionary_Project">JMdict</a>
        and <a href="https://www.edrdg.org/enamdict/enamdict_doc.html">JMnedict</a>
        by <a href="https://www.edrdg.org/edrdg/licence.html">EDRDG</a>, CC BY-SA 3.0.</small>
        <ul>
-    ''')
+    '''
+    )
    for pos, engdef, extra in definitions:
        if pos == 'Wikipedia definition':
            infobox_content.append('</ul><small>Wikipedia, CC BY-SA 3.0.</small><ul>')
--- a/searx/engines/mongodb.py
+++ b/searx/engines/mongodb.py
@@ -49,6 +49,7 @@ except ImportError:

 from searx.result_types import EngineResults

+
 engine_type = 'offline'

 # mongodb connection variables
--- a/searx/engines/npm.py
+++ b/searx/engines/npm.py
@@ -4,6 +4,7 @@
 from urllib.parse import urlencode
 from dateutil import parser

+
 about = {
    "website": "https://npms.io/",
    "wikidata_id": "Q7067518",
--- a/searx/engines/open_meteo.py
+++ b/searx/engines/open_meteo.py
@@ -9,6 +9,7 @@ from datetime import datetime
 from searx.result_types import EngineResults, WeatherAnswer
 from searx import weather

+
 about = {
    "website": "https://open-meteo.com",
    "wikidata_id": None,
--- a/searx/engines/openstreetmap.py
+++ b/searx/engines/openstreetmap.py
@@ -10,8 +10,7 @@ from flask_babel import gettext

 from searx.data import OSM_KEYS_TAGS, CURRENCIES
 from searx.external_urls import get_external_url
-from searx.wikidata import send_wikidata_query
-from searx.engines.wikidata import sparql_string_escape, get_thumbnail
+from searx.engines.wikidata import send_wikidata_query, sparql_string_escape, get_thumbnail
 from searx.result_types import EngineResults

 # about
@@ -291,8 +290,7 @@ def get_title_address(result):
                'house_number': address_raw.get('house_number'),
                'road': address_raw.get('road'),
                'locality': address_raw.get(
-                    'city',
-                    address_raw.get('town', address_raw.get('village')),  # noqa
+                    'city', address_raw.get('town', address_raw.get('village'))  # noqa
                ),  # noqa
                'postcode': address_raw.get('postcode'),
                'country': address_raw.get('country'),
--- a/searx/engines/openverse.py
+++ b/searx/engines/openverse.py
@@ -8,6 +8,7 @@ Openverse (formerly known as: Creative Commons search engine) [Images]
 from json import loads
 from urllib.parse import urlencode

+
 about = {
    "website": 'https://openverse.org/',
    "wikidata_id": None,
--- a/searx/engines/pexels.py
+++ b/searx/engines/pexels.py
@@ -12,6 +12,7 @@ from searx.enginelib import EngineCache
 from searx.exceptions import SearxEngineAPIException, SearxEngineAccessDeniedException
 from searx.network import get

+
 # about
 about = {
    "website": 'https://www.pexels.com',
--- a/searx/engines/piped.py
+++ b/searx/engines/piped.py
@@ -48,6 +48,7 @@ Implementations

 """

+
 import time
 import random
 from urllib.parse import urlencode
--- a/searx/engines/privacywall.py
+++ b/searx/engines/privacywall.py
@@ -18,6 +18,7 @@ from searx.utils import eval_xpath_list, eval_xpath, extract_text, get_embeded_s
 from searx.locales import region_tag
 from searx.result_types import EngineResults

+
 if t.TYPE_CHECKING:
    from lxml.etree import ElementBase
    from searx.extended_types import SXNG_Response
--- a/searx/engines/recoll.py
+++ b/searx/engines/recoll.py
@@ -35,7 +35,6 @@ Implementations
 ===============

 """
-
 import typing as t

 from datetime import date, timedelta
--- a/searx/engines/solr.py
+++ b/searx/engines/solr.py
@@ -34,6 +34,7 @@ from searx.exceptions import SearxEngineAPIException
 from searx.result_types import EngineResults
 from searx.extended_types import SXNG_Response

+
 base_url = 'http://localhost:8983'
 collection = ''
 rows = 10
--- a/searx/engines/soundcloud.py
+++ b/searx/engines/soundcloud.py
@@ -117,7 +117,7 @@ def response(resp):

 def init(engine_settings):  # pylint: disable=unused-argument
    global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])  # type: ignore
+    CACHE = EngineCache(engine_settings["name"])  # type:ignore


 def get_client_id() -> str | None:
--- a/searx/engines/sqlite.py
+++ b/searx/engines/sqlite.py
@@ -44,7 +44,6 @@ Implementations
 ===============

 """
-
 import typing as t
 import sqlite3
 import contextlib
--- a/searx/engines/startpage.py
+++ b/searx/engines/startpage.py
@@ -82,7 +82,6 @@ Startpage's category (for Web-search, News, Videos, ..) is set by
  Supported categories are ``web``, ``news`` and ``images``.

 """
-
 # pylint: disable=too-many-statements

 import re
--- a/searx/engines/tubearchivist.py
+++ b/searx/engines/tubearchivist.py
@@ -74,6 +74,7 @@ Implementations
 ===============
 """

+
 from urllib.parse import urlencode
 from dateutil.parser import parse
 from searx.utils import html_to_text, humanize_number
--- a/searx/engines/vuhuv.py
+++ b/searx/engines/vuhuv.py
@@ -12,6 +12,7 @@ from lxml import html
 from searx.result_types import EngineResults
 from searx.utils import eval_xpath_list, eval_xpath, extract_text

+
 if t.TYPE_CHECKING:
    from lxml.etree import ElementBase
    from searx.extended_types import SXNG_Response
--- a/searx/engines/wikidata.py
+++ b/searx/engines/wikidata.py
@@ -3,34 +3,28 @@

 Some implementations are shared from :ref:`wikipedia engine`.
 """
-
 # pylint: disable=missing-class-docstring

 import typing as t

+import os
 from hashlib import md5
 from urllib.parse import urlencode, unquote
 from json import loads

+from dateutil.parser import isoparse
+from babel.dates import format_datetime, format_date, format_time, get_datetime_format

+from searx.enginelib import EngineCache
+from searx.data import WIKIDATA_UNITS
 from searx.network import post, get
-from searx.utils import get_string_replaces_function
-from searx.external_urls import area_to_osm_zoom
+from searx.utils import searxng_useragent, get_string_replaces_function
+from searx.external_urls import get_external_url, get_earth_coordinates_url, area_to_osm_zoom
 from searx.engines.wikipedia import (
    fetch_wikimedia_traits,
    get_wiki_params,
 )
 from searx.enginelib.traits import EngineTraits
-from searx.wikidata_properties import (
-    QUERY_TEMPLATE,
-    WDArticle,
-    WDAttrList,
-    WDGeoAttribute,
-    WDImageAttribute,
-    WDURLAttribute,
-    get_attributes,
-)
-from searx.wikidata import SPARQL_ENDPOINT_URL, SPARQL_EXPLAIN_URL, get_wikidata_headers

 if t.TYPE_CHECKING:
    from searx.extended_types import SXNG_Response
@@ -53,6 +47,78 @@ display_type = ["infobox"]
 one will add a hit to the result list.  The first one will show a hit in the
 info box.  Both values can be set, or one of the two can be set."""

+CACHE: EngineCache
+"""Persistent (SQLite) key/value cache that deletes its values after ``expire``
+seconds."""
+
+# SPARQL
+SPARQL_ENDPOINT_URL = "https://query.wikidata.org/sparql"
+SPARQL_EXPLAIN_URL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql?explain"
+WDPType = dict[str | tuple[str, str], str]
+WIKIDATA_PROPERTIES: WDPType = {
+    "P434": "MusicBrainz",
+    "P435": "MusicBrainz",
+    "P436": "MusicBrainz",
+    "P966": "MusicBrainz",
+    "P345": "IMDb",
+    "P2397": "YouTube",
+    "P1651": "YouTube",
+    "P2002": "Twitter",
+    "P2013": "Facebook",
+    "P2003": "Instagram",
+    "P4033": "Mastodon",
+    "P11947": "Lemmy",
+    "P12622": "PeerTube",
+}
+
+# SERVICE wikibase:mwapi : https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual/MWAPI
+# SERVICE wikibase:label: https://en.wikibooks.org/wiki/SPARQL/SERVICE_-_Label#Manual_Label_SERVICE
+# https://en.wikibooks.org/wiki/SPARQL/WIKIDATA_Precision,_Units_and_Coordinates
+# https://www.mediawiki.org/wiki/Wikibase/Indexing/RDF_Dump_Format#Data_model
+# optimization:
+# * https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service/query_optimization
+# * https://github.com/blazegraph/database/wiki/QueryHints
+QUERY_TEMPLATE = """
+SELECT ?item ?itemLabel ?itemDescription ?lat ?long %SELECT%
+WHERE
+{
+  SERVICE wikibase:mwapi {
+        bd:serviceParam wikibase:endpoint "www.wikidata.org";
+        wikibase:api "EntitySearch";
+        wikibase:limit 1;
+        mwapi:search "%QUERY%";
+        mwapi:language "%LANGUAGE%".
+        ?item wikibase:apiOutputItem mwapi:item.
+  }
+  hint:Prior hint:runFirst "true".
+
+  %WHERE%
+
+  SERVICE wikibase:label {
+      bd:serviceParam wikibase:language "%LANGUAGE%,en".
+      ?item rdfs:label ?itemLabel .
+      ?item schema:description ?itemDescription .
+      %WIKIBASE_LABELS%
+  }
+
+}
+GROUP BY ?item ?itemLabel ?itemDescription ?lat ?long %GROUP_BY%
+"""
+
+# Get the calendar names and the property names
+QUERY_PROPERTY_NAMES = """
+SELECT ?item ?name
+WHERE {
+    {
+      SELECT ?item
+      WHERE { ?item wdt:P279* wd:Q12132 }
+    } UNION {
+      VALUES ?item { %ATTRIBUTES% }
+    }
+    OPTIONAL { ?item rdfs:label ?name. }
+}
+"""
+
 # see the property "dummy value" of https://www.wikidata.org/wiki/Q2013 (Wikidata)
 # hard coded here to avoid to an additional SPARQL request when the server starts
 DUMMY_ENTITY_URLS = set(
@@ -64,13 +130,357 @@ DUMMY_ENTITY_URLS = set(
 # https://lists.w3.org/Archives/Public/public-rdf-dawg/2011OctDec/0175.html
 sparql_string_escape = get_string_replaces_function(
    # fmt: off
-    {"\t": "\\\t", "\n": "\\\n", "\r": "\\\r", "\b": "\\\b", "\f": "\\\f", "\"": "\\\"", "'": "\\'", "\\": "\\\\"}
+    {
+        "\t": "\\\t",
+        "\n": "\\\n",
+        "\r": "\\\r",
+        "\b": "\\\b",
+        "\f": "\\\f",
+        "\"": "\\\"",
+        "\'": "\\\'",
+        "\\": "\\\\"
+    }
    # fmt: on
 )

 replace_http_by_https = get_string_replaces_function({"http:": "https:"})


+class WDAttribute:
+
+    def __init__(self, name: str):
+        self.name: str = name
+
+    def get_select(self):
+        return "(group_concat(distinct ?{name};separator=', ') as ?{name}s)".replace("{name}", self.name)
+
+    def get_label(self, language: str):
+        return get_label_for_entity(self.name, language)
+
+    def get_where(self):
+        return "OPTIONAL { ?item wdt:{name} ?{name} . }".replace("{name}", self.name)
+
+    def get_wikibase_label(self) -> str:
+        return ""
+
+    def get_group_by(self) -> str:
+        return ""
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:  # pylint: disable=unused-argument
+        return result.get(self.name + "s")
+
+    def __repr__(self):
+        return "<" + str(type(self).__name__) + ":" + self.name + ">"
+
+
+class WDAmountAttribute(WDAttribute):
+    def get_select(self) -> str:
+        return "?{name} ?{name}Unit".replace("{name}", self.name)
+
+    def get_where(self):
+        return """  OPTIONAL { ?item p:{name} ?{name}Node .
+    ?{name}Node rdf:type wikibase:BestRank ; ps:{name} ?{name} .
+    OPTIONAL { ?{name}Node psv:{name}/wikibase:quantityUnit ?{name}Unit. } }""".replace(
+            '{name}', self.name
+        )
+
+    def get_group_by(self) -> str:
+        return self.get_select()
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        value: str | None = result.get(self.name)
+        unit: str | None = result.get(self.name + "Unit")
+        if unit is not None:
+            unit = unit.replace("http://www.wikidata.org/entity/", "")
+            return str(value) + " " + get_label_for_entity(unit, language)
+        return value
+
+
+class WDArticle(WDAttribute):
+
+    def __init__(self, language: str, kwargs: dict[str, t.Any] | None = None):
+        super().__init__("wikipedia")
+        self.language: str = language
+        self.kwargs: dict[str, t.Any] = kwargs or {}
+
+    def get_label(self, language: str):
+        # language parameter is ignored
+        return "Wikipedia ({language})".replace("{language}", self.language)
+
+    def get_select(self):
+        return "?article{language} ?articleName{language}".replace("{language}", self.language)
+
+    def get_where(self):
+        return """OPTIONAL { ?article{language} schema:about ?item ;
+             schema:inLanguage "{language}" ;
+             schema:isPartOf <https://{language}.wikipedia.org/> ;
+             schema:name ?articleName{language} . }""".replace(
+            '{language}', self.language
+        )
+
+    def get_group_by(self):
+        return self.get_select()
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        key = "article{language}".replace("{language}", self.language)
+        return result.get(key)
+
+
+class WDLabelAttribute(WDAttribute):
+    def get_select(self):
+        return "(group_concat(distinct ?{name}Label;separator=', ') as ?{name}Labels)".replace("{name}", self.name)
+
+    def get_where(self):
+        return "OPTIONAL { ?item wdt:{name} ?{name} . }".replace("{name}", self.name)
+
+    def get_wikibase_label(self) -> str:
+        return "?{name} rdfs:label ?{name}Label .".replace("{name}", self.name)
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        return result.get(self.name + "Labels")
+
+
+class WDURLAttribute(WDAttribute):
+
+    HTTP_WIKIMEDIA_IMAGE: str = "http://commons.wikimedia.org/wiki/Special:FilePath/"
+
+    def __init__(
+        self,
+        name: str,
+        url_id: str | None = None,
+        url_path_prefix: str | None = None,
+        kwargs: dict[str, t.Any] | None = None,
+    ):
+        """
+        :param url_id: ID matching one key in ``external_urls.json`` for
+            converting IDs to full URLs.
+
+        :param url_path_prefix: Path prefix if the values are of format
+            ``account@domain``.  If provided, value are rewritten to
+            ``https://<domain><url_path_prefix><account>``.  For example::
+
+              WDURLAttribute('P4033', url_path_prefix='/@')
+
+            Adds Property `P4033 <https://www.wikidata.org/wiki/Property:P4033>`_
+            to the wikidata query.  This field might return for example
+            ``libreoffice@fosstodon.org`` and the URL built from this is then:
+
+            - account: ``libreoffice``
+            - domain: ``fosstodon.org``
+            - result url: https://fosstodon.org/@libreoffice
+        """
+
+        super().__init__(name)
+        self.url_id: str | None = url_id
+        self.url_path_prefix: str | None = url_path_prefix
+        self.kwargs: dict[str, t.Any] = kwargs or {}
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        value: str | None = result.get(self.name + "s")
+        if not value:
+            return None
+
+        value = value.split(",")[0]
+        if self.url_id:
+            url_id = self.url_id
+            if value.startswith(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE):
+                value = value[len(WDURLAttribute.HTTP_WIKIMEDIA_IMAGE) :]
+                url_id = "wikimedia_image"
+            return get_external_url(url_id, value)
+
+        if self.url_path_prefix:
+            [account, domain] = [x.strip("@ ") for x in value.rsplit("@", 1)]
+            return f"https://{domain}{self.url_path_prefix}{account}"
+
+        return value
+
+
+class WDGeoAttribute(WDAttribute):
+    def get_label(self, language: str):
+        return "OpenStreetMap"
+
+    def get_select(self):
+        return "?{name}Lat ?{name}Long".replace("{name}", self.name)
+
+    def get_where(self):
+        return """OPTIONAL { ?item p:{name}/psv:{name} [
+    wikibase:geoLatitude ?{name}Lat ;
+    wikibase:geoLongitude ?{name}Long ] }""".replace(
+            '{name}', self.name
+        )
+
+    def get_group_by(self):
+        return self.get_select()
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        latitude: str | None = result.get(self.name + "Lat")
+        longitude: str | None = result.get(self.name + "Long")
+        if latitude and longitude:
+            return latitude + " " + longitude
+        return None
+
+    def get_geo_url(self, result: dict[str, t.Any], osm_zoom: int = 19) -> str | None:
+        latitude: str | None = result.get(self.name + "Lat")
+        longitude: str | None = result.get(self.name + "Long")
+        if latitude and longitude:
+            return get_earth_coordinates_url(latitude, longitude, osm_zoom)
+        return None
+
+
+class WDImageAttribute(WDURLAttribute):
+
+    def __init__(self, name: str, url_id: str | None = None, priority: int = 100):
+        super().__init__(name, url_id)
+        self.priority: int = priority
+
+
+class WDDateAttribute(WDAttribute):
+    def get_select(self):
+        return "?{name} ?{name}timePrecision ?{name}timeZone ?{name}timeCalendar".replace("{name}", self.name)
+
+    def get_where(self):
+        # To remove duplicate, add
+        # FILTER NOT EXISTS { ?item p:{name}/psv:{name}/wikibase:timeValue ?{name}bis FILTER (?{name}bis < ?{name}) }
+        # this filter is too slow, so the response function ignore duplicate results
+        # (see the seen_entities variable)
+        return """OPTIONAL { ?item p:{name}/psv:{name} [
+    wikibase:timeValue ?{name} ;
+    wikibase:timePrecision ?{name}timePrecision ;
+    wikibase:timeTimezone ?{name}timeZone ;
+    wikibase:timeCalendarModel ?{name}timeCalendar ] . }
+    hint:Prior hint:rangeSafe true;""".replace(
+            '{name}', self.name
+        )
+
+    def get_group_by(self):
+        return self.get_select()
+
+    def format_8(self, value: str, locale: str) -> str:  # pylint: disable=unused-argument
+        # precision: less than a year
+        return value
+
+    def format_9(self, value: str, locale: str) -> str:
+        year = int(value)
+        # precision: year
+        if year < 1584:
+            if year < 0:
+                return str(year - 1)
+            return str(year)
+        timestamp = isoparse(value)
+        return format_date(timestamp, format="yyyy", locale=locale)
+
+    def format_10(self, value: str, locale: str) -> str:
+        # precision: month
+        timestamp = isoparse(value)
+        return format_date(timestamp, format="MMMM y", locale=locale)
+
+    def format_11(self, value: str, locale: str) -> str:
+        # precision: day
+        timestamp = isoparse(value)
+        return format_date(timestamp, format="full", locale=locale)
+
+    def format_13(self, value: str, locale: str) -> str:
+        timestamp = isoparse(value)
+        # precision: minute
+        return (
+            get_datetime_format(format, locale=locale)
+            .replace("'", "")
+            .replace("{0}", format_time(timestamp, "full", tzinfo=None, locale=locale))
+            .replace("{1}", format_date(timestamp, "short", locale=locale))
+        )
+
+    def format_14(self, value: str, locale: str) -> str:
+        # precision: second.
+        return format_datetime(isoparse(value), format="full", locale=locale)
+
+    DATE_FORMAT: dict[str, tuple[str, int]] = {
+        "0": ("format_8", 1000000000),
+        "1": ("format_8", 100000000),
+        "2": ("format_8", 10000000),
+        "3": ("format_8", 1000000),
+        "4": ("format_8", 100000),
+        "5": ("format_8", 10000),
+        "6": ("format_8", 1000),
+        "7": ("format_8", 100),
+        "8": ("format_8", 10),
+        "9": ("format_9", 1),  # year
+        "10": ("format_10", 1),  # month
+        "11": ("format_11", 0),  # day
+        "12": ("format_13", 0),  # hour (not supported by babel, display minute)
+        "13": ("format_13", 0),  # minute
+        "14": ("format_14", 0),  # second
+    }
+
+    def get_str(self, result: dict[str, t.Any], language: str) -> str | None:
+        value: str | None = result.get(self.name)
+        if value == "" or value is None:
+            return None
+        _p: str = result.get(self.name + "timePrecision") or "1"
+        date_format = WDDateAttribute.DATE_FORMAT.get(_p)
+        if date_format is not None:
+            format_method = getattr(self, date_format[0])
+            precision: int = date_format[1]
+            try:
+                if precision >= 1:
+                    _t = value.split("-")
+                    if value.startswith("-"):
+                        value = "-" + _t[1]
+                    else:
+                        value = _t[0]
+                return format_method(value, language)
+            except Exception:  # pylint: disable=broad-except
+                return value
+        return value
+
+
+WDAttrType = (
+    WDAttribute
+    | WDAmountAttribute
+    | WDArticle
+    | WDLabelAttribute
+    | WDURLAttribute
+    | WDGeoAttribute
+    | WDImageAttribute
+    | WDDateAttribute
+)
+WDAttrList = list[WDAttrType]
+
+
+def get_headers() -> dict[str, str]:
+    # user agent: https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual#Query_limits
+    return {
+        "Accept": "application/sparql-results+json",
+        "User-Agent": f"wikidata engine - {searxng_useragent()}",
+    }
+
+
+def get_label_for_entity(entity_id: str, language: str) -> str:
+    name = WIKIDATA_PROPERTIES.get(entity_id)
+    if name is None:
+        name = WIKIDATA_PROPERTIES.get((entity_id, language))
+    if name is None:
+        name = WIKIDATA_PROPERTIES.get((entity_id, language.split("-")[0]))
+    if name is None:
+        name = WIKIDATA_PROPERTIES.get((entity_id, "en"))
+    if name is None:
+        name = entity_id
+    return name
+
+
+def send_wikidata_query(query: str, method: str = "GET", **kwargs: dict[str, t.Any]) -> dict[str, t.Any]:
+    if method == "GET":
+        # query will be cached by wikidata
+        http_response = get(SPARQL_ENDPOINT_URL + "?" + urlencode({"query": query}), headers=get_headers(), **kwargs)
+    else:
+        # query won't be cached by wikidata
+        http_response = post(SPARQL_ENDPOINT_URL, data={"query": query}, headers=get_headers(), **kwargs)
+    if http_response.status_code != 200:
+        logger.debug("SPARQL endpoint error %s", http_response.content.decode())
+    logger.debug("request time %s", str(http_response.elapsed))
+    http_response.raise_for_status()
+    return loads(http_response.content.decode())
+
+
 def request(query: str, params: "OnlineParams") -> None:

    attributes: WDAttrList
@@ -81,7 +491,7 @@ def request(query: str, params: "OnlineParams") -> None:
    params["method"] = "POST"
    params["url"] = SPARQL_ENDPOINT_URL
    params["data"] = {"query": query}
-    params["headers"] = get_wikidata_headers()
+    params["headers"] = get_headers()

    # additional parameters (not a part of OnlineParams)
    params["language"] = eng_tag  # type: ignore
@@ -174,6 +584,7 @@ def get_results(
    for attribute in attributes:
        value: str | None = attribute.get_str(attribute_result, language)
        if value is not None and value != "":
+
            if isinstance(attribute, (WDURLAttribute, WDArticle)):
                # get_select() method : there is group_concat(distinct ...;separator=", ")
                # split the value here
@@ -259,15 +670,212 @@ def get_query(query: str, language: str) -> tuple[str, WDAttrList]:
    return query, attributes


+def get_attributes(language: str):
+    # pylint: disable=too-many-statements
+    attributes: WDAttrList = []
+
+    def add_value(name: str):
+        attributes.append(WDAttribute(name))
+
+    def add_amount(name: str):
+        attributes.append(WDAmountAttribute(name))
+
+    def add_label(name: str):
+        attributes.append(WDLabelAttribute(name))
+
+    def add_url(name: str, url_id: str | None = None, url_path_prefix: str | None = None, **kwargs: dict[str, t.Any]):
+        attributes.append(WDURLAttribute(name, url_id, url_path_prefix, kwargs))
+
+    def add_image(name: str, url_id: str | None = None, priority: int = 1):
+        attributes.append(WDImageAttribute(name, url_id, priority))
+
+    def add_date(name: str):
+        attributes.append(WDDateAttribute(name))
+
+    # Dates
+    for p in [
+        "P571",  # inception date
+        "P576",  # dissolution date
+        "P580",  # start date
+        "P582",  # end date
+        "P569",  # date of birth
+        "P570",  # date of death
+        "P619",  # date of spacecraft launch
+        "P620",
+    ]:  # date of spacecraft landing
+        add_date(p)
+
+    for p in [
+        "P27",  # country of citizenship
+        "P495",  # country of origin
+        "P17",  # country
+        "P159",
+    ]:  # headquarters location
+        add_label(p)
+
+    # Places
+    for p in [
+        "P36",  # capital
+        "P35",  # head of state
+        "P6",  # head of government
+        "P122",  # basic form of government
+        "P37",
+    ]:  # official language
+        add_label(p)
+
+    add_value("P1082")  # population
+    add_amount("P2046")  # area
+    add_amount("P281")  # postal code
+    add_label("P38")  # currency
+    add_amount("P2048")  # height (building)
+
+    # Media
+    for p in [
+        "P400",  # platform (videogames, computing)
+        "P50",  # author
+        "P170",  # creator
+        "P57",  # director
+        "P175",  # performer
+        "P178",  # developer
+        "P162",  # producer
+        "P176",  # manufacturer
+        "P58",  # screenwriter
+        "P272",  # production company
+        "P264",  # record label
+        "P123",  # publisher
+        "P449",  # original network
+        "P750",  # distributed by
+        "P86",
+    ]:  # composer
+        add_label(p)
+
+    add_date("P577")  # publication date
+    add_label("P136")  # genre (music, film, artistic...)
+    add_label("P364")  # original language
+    add_value("P212")  # ISBN-13
+    add_value("P957")  # ISBN-10
+    add_label("P275")  # copyright license
+    add_label("P277")  # programming language
+    add_value("P348")  # version
+    add_label("P840")  # narrative location
+
+    # Languages
+    add_value("P1098")  # number of speakers
+    add_label("P282")  # writing system
+    add_label("P1018")  # language regulatory body
+    add_value("P218")  # language code (ISO 639-1)
+
+    # Other
+    add_label("P169")  # ceo
+    add_label("P112")  # founded by
+    add_label("P1454")  # legal form (company, organization)
+    add_label("P137")  # operator (service, facility, ...)
+    add_label("P1029")  # crew members (tripulation)
+    add_label("P225")  # taxon name
+    add_value("P274")  # chemical formula
+    add_label("P1346")  # winner (sports, contests, ...)
+    add_value("P1120")  # number of deaths
+    add_value("P498")  # currency code (ISO 4217)
+
+    # URL
+    kwargs: dict[str, t.Any] = {"official": True}
+    add_url("P856", **kwargs)  # official website
+    attributes.append(WDArticle(language))  # wikipedia (user language)
+    if not language.startswith("en"):
+        attributes.append(WDArticle("en"))  # wikipedia (english)
+
+    add_url("P1324")  # source code repository
+    add_url("P1581")  # blog
+    add_url("P434", url_id="musicbrainz_artist")
+    add_url("P435", url_id="musicbrainz_work")
+    add_url("P436", url_id="musicbrainz_release_group")
+    add_url("P966", url_id="musicbrainz_label")
+    add_url("P345", url_id="imdb_id")
+    add_url("P2397", url_id="youtube_channel")
+    add_url("P1651", url_id="youtube_video")
+    add_url("P2002", url_id="twitter_profile")
+    add_url("P2013", url_id="facebook_profile")
+    add_url("P2003", url_id="instagram_profile")
+
+    # Fediverse
+    add_url("P4033", url_path_prefix="/@")  # Mastodon user
+    add_url("P11947", url_path_prefix="/c/")  # Lemmy community
+    add_url("P12622", url_path_prefix="/c/")  # PeerTube channel
+
+    # Map
+    attributes.append(WDGeoAttribute("P625"))
+
+    # Image
+    add_image("P15", priority=1, url_id="wikimedia_image")  # route map
+    add_image("P242", priority=2, url_id="wikimedia_image")  # locator map
+    add_image("P154", priority=3, url_id="wikimedia_image")  # logo
+    add_image("P18", priority=4, url_id="wikimedia_image")  # image
+    add_image("P41", priority=5, url_id="wikimedia_image")  # flag
+    add_image("P2716", priority=6, url_id="wikimedia_image")  # collage
+    add_image("P2910", priority=7, url_id="wikimedia_image")  # icon
+
+    return attributes
+
+
 def debug_explain_wikidata_query(query: str, method: str = "GET"):
    if method == "GET":
-        http_response = get(SPARQL_EXPLAIN_URL + "&" + urlencode({"query": query}), headers=get_wikidata_headers())
+        http_response = get(SPARQL_EXPLAIN_URL + "&" + urlencode({"query": query}), headers=get_headers())
    else:
-        http_response = post(SPARQL_EXPLAIN_URL, data={"query": query}, headers=get_wikidata_headers())
+        http_response = post(SPARQL_EXPLAIN_URL, data={"query": query}, headers=get_headers())
    http_response.raise_for_status()
    return http_response.content


+def init(_):
+    global CACHE  # pylint: disable=global-statement
+    CACHE = EngineCache("wikidata")
+
+    # In an environment with competing processes, the initial loading of the
+    # cache is required only once.
+    eng_state: str | None = CACHE.get("eng_state")
+    if not eng_state or not eng_state.startswith("STATE:"):
+        CACHE.set("eng_state", f"STATE: being initialized by PID {os.getpid()}")
+        try:
+            init_wikidata_properties()
+        except Exception:
+            CACHE.set("eng_state", f"ERROR: initialization by PID {os.getpid()} failed.")
+            raise
+    else:
+        logger.debug(eng_state)
+
+
+def init_wikidata_properties():
+    global WIKIDATA_PROPERTIES  # pylint: disable=global-statement
+    p: WDPType = CACHE.get(key="WIKIDATA_PROPERTIES")
+    if p:
+        WIKIDATA_PROPERTIES = p
+        return
+
+    # WIKIDATA_PROPERTIES : add unit symbols
+    for k, v in WIKIDATA_UNITS.items():
+        WIKIDATA_PROPERTIES[k] = v["symbol"]
+
+    # WIKIDATA_PROPERTIES : add property labels
+    wikidata_property_names: list[str] = []
+    for attribute in get_attributes("en"):
+        if type(attribute) in (WDAttribute, WDAmountAttribute, WDURLAttribute, WDDateAttribute, WDLabelAttribute):
+            if attribute.name not in WIKIDATA_PROPERTIES:
+                wikidata_property_names.append("wd:" + attribute.name)
+    query = QUERY_PROPERTY_NAMES.replace("%ATTRIBUTES%", " ".join(wikidata_property_names))
+    kwargs: dict[str, t.Any] = {"timeout": 20}
+    jsonresponse = send_wikidata_query(query, **kwargs)
+    for result in jsonresponse.get("results", {}).get("bindings", {}):
+        name_field = result.get("name")
+        if not name_field:
+            continue
+        name = name_field["value"]
+        lang = name_field["xml:lang"]
+        entity_id = result["item"]["value"].replace("http://www.wikidata.org/entity/", "")
+        WIKIDATA_PROPERTIES[(entity_id, lang)] = name.capitalize()
+
+    CACHE.set(key="WIKIDATA_PROPERTIES", value=WIKIDATA_PROPERTIES)
+
+
 def fetch_traits(engine_traits: EngineTraits):
    """Uses languages evaluated from :py:obj:`wikipedia.fetch_wikimedia_traits
    <searx.engines.wikipedia.fetch_wikimedia_traits>` and removes
--- a/searx/engines/wolframalpha_noapi.py
+++ b/searx/engines/wolframalpha_noapi.py
@@ -3,6 +3,7 @@
 Wolfram|Alpha (Science)
 """

+
 from json import loads
 from urllib.parse import urlencode

@@ -52,7 +53,7 @@ seconds."""

 def init(engine_settings):
    global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])  # type: ignore
+    CACHE = EngineCache(engine_settings["name"])  # type:ignore


 def obtain_token() -> str:
--- a/searx/engines/yacy.py
+++ b/searx/engines/yacy.py
@@ -50,7 +50,6 @@ the engine).
 Implementations
 ===============
 """
-
 # pylint: disable=fixme


--- a/searx/engines/yandex.py
+++ b/searx/engines/yandex.py
@@ -8,6 +8,7 @@ from lxml import html
 from searx.exceptions import SearxEngineCaptchaException
 from searx.utils import humanize_bytes, eval_xpath, eval_xpath_list, extract_text, extr

+
 # Engine metadata
 about = {
    "website": 'https://yandex.com/',
--- a/searx/extended_types.py
+++ b/searx/extended_types.py
@@ -19,7 +19,6 @@
   :members:

 """
-
 # pylint: disable=invalid-name

 __all__ = ["SXNG_Request", "sxng_request", "SXNG_Response"]
--- a/searx/external_urls.py
+++ b/searx/external_urls.py
@@ -5,6 +5,7 @@ import math

 from searx.data import EXTERNAL_URLS

+
 IMDB_PREFIX_TO_URL_ID = {
    'tt': 'imdb_title',
    'mn': 'imdb_name',
--- a/searx/favicons/init.py
+++ b/searx/favicons/init.py
@@ -8,6 +8,7 @@ an example in which the command line is called in the development environment::
  (py3) python -m searx.favicons --help
 """

+
 __all__ = ["init", "favicon_url", "favicon_proxy"]

 import pathlib
--- a/searx/favicons/proxy.py
+++ b/searx/favicons/proxy.py
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementations for a favicon proxy"""

+
 from typing import Callable

 import importlib
--- a/searx/favicons/resolvers.py
+++ b/searx/favicons/resolvers.py
@@ -6,6 +6,7 @@ timeout``) and returns a tuple ``(data, mime)``.

 """

+
 __all__ = ["DEFAULT_RESOLVER_MAP", "allesedv", "duckduckgo", "google", "kagi", "yandex"]

 from typing import Callable
--- a/searx/infopage/init.py
+++ b/searx/infopage/init.py
@@ -36,6 +36,7 @@ from .. import get_setting
 from ..version import GIT_URL
 from ..locales import LOCALE_NAMES

+
 logger = logging.getLogger('searx.infopage')
 _INFO_FOLDER = os.path.abspath(os.path.dirname(__file__))
 INFO_PAGES: 'InfoPageSet'
--- a/searx/locales.py
+++ b/searx/locales.py
@@ -26,6 +26,7 @@ SearXNG’s locale implementations
 ================================
 """

+
 import typing as t
 from pathlib import Path

--- a/searx/metrics/error_recorder.py
+++ b/searx/metrics/error_recorder.py
@@ -16,6 +16,7 @@ from searx.exceptions import (
 from searx import searx_parent_dir, settings
 from searx.engines import engines

+
 errors_per_engines: dict[str, t.Any] = {}

 LogParametersType = tuple[str, ...]
--- a/searx/metrics/models.py
+++ b/searx/metrics/models.py
@@ -8,6 +8,7 @@ import threading

 from searx import logger

+
 __all__ = ["Histogram", "HistogramStorage", "CounterStorage"]

 logger = logger.getChild('searx.metrics')
--- a/searx/network/network.py
+++ b/searx/network/network.py
@@ -20,6 +20,7 @@ from searx.extended_types import SXNG_Response
 from .client import new_client, get_loop, AsyncHTTPTransportNoHttp
 from .raise_for_httperror import raise_for_httperror

+
 logger = logger.getChild('network')
 DEFAULT_NAME = '__DEFAULT__'
 NETWORKS: dict[str, "Network"] = {}
--- a/searx/plugins/init.py
+++ b/searx/plugins/init.py
@@ -94,6 +94,7 @@ Implementation
   :members:
 """

+
 __all__ = ["PluginInfo", "Plugin", "PluginStorage", "PluginCfg"]


--- a/searx/plugins/tor_check.py
+++ b/searx/plugins/tor_check.py
@@ -4,7 +4,6 @@ user searches for ``tor-check``.  It fetches the tor exit node list from
 :py:obj:`url_exit_list` and parses all the IPs into a list, then checks if the
 user's IP address is in it.
 """
-
 from ipaddress import ip_address
 import typing

--- a/searx/plugins/unit_converter.py
+++ b/searx/plugins/unit_converter.py
@@ -8,7 +8,6 @@ converters, each converter is one item in the list (compare
 of measurement are evaluated.  The weighting in the evaluation results from the
 sorting of the :py:obj:`list of unit converters<symbol_to_si>`.
 """
-
 import typing
 import re
 import babel.numbers
--- a/searx/preferences.py
+++ b/searx/preferences.py
@@ -6,7 +6,7 @@
 import typing as t

 from base64 import urlsafe_b64encode, urlsafe_b64decode
-from zlib import compress, decompressobj
+from zlib import compress, decompress
 from urllib.parse import parse_qs, urlencode
 from collections import OrderedDict
 from collections.abc import Iterable
@@ -517,7 +517,7 @@ class Preferences:

    def parse_encoded_data(self, input_data: str):
        """parse (base64) preferences from request (``flask.request.form['preferences']``)"""
-        bin_data = decompressobj().decompress(urlsafe_b64decode(input_data), 16 * 1024)
+        bin_data = decompress(urlsafe_b64decode(input_data))
        dict_data = {}
        for x, y in parse_qs(bin_data.decode('ascii'), keep_blank_values=True).items():
            dict_data[x] = y[0]
--- a/searx/result_types/init.py
+++ b/searx/result_types/init.py
@@ -9,7 +9,6 @@
   gradually.  For more, please read :ref:`result types`.

 """
-
 # pylint: disable=too-few-public-methods


--- a/searx/result_types/answer.py
+++ b/searx/result_types/answer.py
@@ -26,7 +26,6 @@ template.
   :members:
   :show-inheritance:
 """
-
 # pylint: disable=too-few-public-methods


--- a/searx/result_types/code.py
+++ b/searx/result_types/code.py
@@ -12,7 +12,6 @@ template.  For highlighting the code passages, Pygments_ is used.
   :show-inheritance:

 """
-
 # pylint: disable=too-few-public-methods, disable=invalid-name

 __all__ = ["Code"]
@@ -27,6 +26,7 @@ from pygments.formatters import HtmlFormatter  # pylint: disable=no-name-in-modu

 from ._base import MainResult

+
 _pygments_languages: list[str] = []


--- a/searx/result_types/file.py
+++ b/searx/result_types/file.py
@@ -11,7 +11,6 @@ template.
   :show-inheritance:

 """
-
 # pylint: disable=too-few-public-methods


--- a/searx/result_types/image.py
+++ b/searx/result_types/image.py
@@ -11,7 +11,6 @@ template.
   :members:

 """
-
 # pylint: disable=too-few-public-methods
 __all__ = ["Image", "ImageRef"]

--- a/searx/result_types/keyvalue.py
+++ b/searx/result_types/keyvalue.py
@@ -11,7 +11,6 @@ template.
   :show-inheritance:

 """
-
 # pylint: disable=too-few-public-methods


--- a/searx/result_types/paper.py
+++ b/searx/result_types/paper.py
@@ -19,7 +19,6 @@ Related topics:
   :show-inheritance:

 """
-
 # pylint: disable=too-few-public-methods, disable=invalid-name

 __all__ = ["Paper"]
--- a/searx/searxng.msg
+++ b/searx/searxng.msg
@@ -8,6 +8,7 @@ from searx import webutils
 from searx import engines
 from searx.weather import WeatherConditionType

+
 __all__ = [
    'CONSTANT_NAMES',
    'CATEGORY_NAMES',
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -1217,12 +1217,12 @@ engines:
  - name: google
    engine: google
    shortcut: go
-    disabled: true
+    inactive: true

  - name: google images
    engine: google_images
    shortcut: goi
-    disabled: true
+    inactive: true

  - name: google news
    engine: google_news
@@ -1231,6 +1231,7 @@ engines:
  - name: google videos
    engine: google_videos
    shortcut: gov
+    inactive: true

  - name: google cse
    engine: google_cse
--- a/searx/settings_defaults.py
+++ b/searx/settings_defaults.py
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementation of the default settings."""
-
 from __future__ import annotations

 import typing as t
--- a/searx/static/themes/simple/sxng-ltr.min.css
+++ b/searx/static/themes/simple/sxng-ltr.min.css
--- a/searx/static/themes/simple/sxng-rtl.min.css
+++ b/searx/static/themes/simple/sxng-rtl.min.css
--- a/searx/weather.py
+++ b/searx/weather.py
@@ -1,6 +1,5 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Implementations used for weather conditions and forecast."""
-
 # pylint: disable=too-few-public-methods

 __all__ = [
--- a/searx/webapp.py
+++ b/searx/webapp.py
@@ -1,7 +1,6 @@
 #!/usr/bin/env python
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """WebApp"""
-
 # pylint: disable=use-dict-literal

 import json
@@ -119,6 +118,7 @@ from searx.sxng_locales import sxng_locales
 import searx.search
 from searx.network import stream as http_stream, set_context_network_name

+
 logger = logger.getChild('webapp')

 warnings.simplefilter("always")
@@ -484,14 +484,14 @@ def pre_request():
        if k not in sxng_request.form:
            sxng_request.form[k] = v

-    try:
-        if sxng_request.form.get('preferences'):
-            preferences.parse_encoded_data(sxng_request.form['preferences'])
-        else:
+    if sxng_request.form.get('preferences'):
+        preferences.parse_encoded_data(sxng_request.form['preferences'])
+    else:
+        try:
            preferences.parse_dict(sxng_request.form)
-    except Exception as e:  # pylint: disable=broad-except
-        logger.exception(e, exc_info=True)
-        sxng_request.errors.append(gettext('Invalid settings'))
+        except Exception as e:  # pylint: disable=broad-except
+            logger.exception(e, exc_info=True)
+            sxng_request.errors.append(gettext('Invalid settings'))

    # language is defined neither in settings nor in preferences
    # use browser headers
@@ -1119,13 +1119,17 @@ def stats():

    technical_report = []
    for error in engine_reliabilities.get(selected_engine_name, {}).get('errors', []):
-        technical_report.append(f"\
+        technical_report.append(
+            f"\
            Error: {error['exception_classname'] or error['log_message']} \
            Parameters: {error['log_parameters']} \
            File name: {error['filename'] }:{ error['line_no'] } \
            Error Function: {error['function']} \
            Code: {error['code']} \
-            ".replace(' ' * 12, '').strip())
+            ".replace(
+                ' ' * 12, ''
+            ).strip()
+        )
    technical_report = ' '.join(technical_report)

    engine_stats['time'] = sorted(engine_stats['time'], reverse=reverse, key=get_key)
--- a/searx/wikidata.py
+++ b/searx/wikidata.py
@@ -1,34 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""Shared methods for accessing Wikidata."""
-
-import typing as t
-from urllib.parse import urlencode
-
-from searx.network import get, post
-from searx.utils import gen_useragent
-
-# SPARQL
-SPARQL_ENDPOINT_URL = "https://query.wikidata.org/sparql"
-SPARQL_EXPLAIN_URL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql?explain"
-
-
-def send_wikidata_query(query: str, method: str = "GET", **kwargs: dict[str, t.Any]) -> dict[str, t.Any]:
-    if method == "GET":
-        # query will be cached by wikidata
-        http_response = get(
-            SPARQL_ENDPOINT_URL + "?" + urlencode({"query": query}), headers=get_wikidata_headers(), **kwargs
-        )
-    else:
-        # query won't be cached by wikidata
-        http_response = post(SPARQL_ENDPOINT_URL, data={"query": query}, headers=get_wikidata_headers(), **kwargs)
-
-    http_response.raise_for_status()
-    return http_response.json()
-
-
-def get_wikidata_headers() -> dict[str, str]:
-    # user agent: https://www.mediawiki.org/wiki/Wikidata_Query_Service/User_Manual#Query_limits
-    return {
-        "Accept": "application/sparql-results+json",
-        "User-Agent": gen_useragent(),
-    }
--- a/Show More
+++ b/Show More