[mod] py: format

Bumps [black](https://github.com/psf/black) from 25.9.0 to 26.5.1.
- [Release notes](https://github.com/psf/black/releases)
- [Changelog](https://github.com/psf/black/blob/main/CHANGES.md)
- [Commits](https://github.com/psf/black/compare/25.9.0...26.5.1)

---
updated-dependencies:
- dependency-name: black
  dependency-version: 26.5.1
  dependency-type: direct:development
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/workflows/container.yml

@@ -62,7 +62,7 @@ jobs:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Setup QEMU
-        uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8  # v4.2.0
+        uses: docker/setup-qemu-action@1f40c72289eff860ee54a304f1438e3cff362e0a  # v4.3.0
 
       - name: Checkout
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1  # v7.0.1
@@ -105,8 +105,9 @@ jobs:
             arch: amd64
           - runner: ubuntu-26.04-arm
             arch: arm64
-          - runner: ubuntu-26.04-arm
+            #  FIXME: https://github.com/searxng/searxng/pull/6655#issuecomment-5550293085
-            arch: armv7
+            # - runner: ubuntu-26.04-arm
+            #   arch: armv7
 
     steps:
       - name: Login to GHCR
@@ -117,7 +118,7 @@ jobs:
           password: "${{ secrets.GITHUB_TOKEN }}"
 
       - name: Setup QEMU
-        uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8  # v4.2.0
+        uses: docker/setup-qemu-action@1f40c72289eff860ee54a304f1438e3cff362e0a  # v4.3.0
 
       - name: Checkout
         uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1  # v7.0.1

client/simple/package.json

@@ -29,14 +29,14 @@
     "swiped-events": "1.2.0"
   },
   "devDependencies": {
-    "@biomejs/biome": "2.5.10",
+    "@biomejs/biome": "2.5.12",
-    "@types/node": "^26.3.0",
+    "@types/node": "^26.5.0",
     "browserslist": "^4.28.8",
     "browserslist-to-esbuild": "^2.1.1",
     "edge.js": "^6.5.1",
     "less": "^4.9.0",
     "mathjs": "^15.2.0",
-    "sharp": "~0.35.3",
+    "sharp": "~0.35.4",
     "sort-package-json": "^4.0.0",
     "stylelint": "^17.14.1",
     "stylelint-config-standard-less": "^4.1.0",

docs/admin/settings/settings_engines.rst

@@ -58,10 +58,9 @@ engine is shown.  Most of the options have a default value or even are optional.
 
      # overwrite values from section 'outgoing:'
      enable_http2: false
+     enable_http3: false
      retries: 1
      max_connections: 100
-     max_keepalive_connections: 10
-     keepalive_expiry: 5.0
      using_tor_proxy: false
      proxies:
        http:
@@ -163,6 +162,16 @@ engine is shown.  Most of the options have a default value or even are optional.
 ``enable_http`` : optional
   Enable HTTP for this engine (by default only HTTPS is enabled).
 
+``enable_http3`` : optional
+  Use HTTP/3 (falls back to HTTP/2).  Default ``false``.
+  Ignored when a proxy is set.
+
+  .. hint::
+
+     HTTP/3 places demands on the IP infrastructure that are not met in every
+     environment.  Enable this option only if you are aware of these requirements
+     and the extent to which they are met.
+
 ``retry_on_http_error`` : optional
   Retry request on some HTTP status code.
 
@@ -179,20 +188,12 @@ engine is shown.  Most of the options have a default value or even are optional.
   Using tor proxy (``true``) or not (``false``) for this engine.  The default is
   taken from ``using_tor_proxy`` of the :ref:`settings outgoing`.
 
-.. _Pool limit configuration: https://www.python-httpx.org/advanced/#pool-limit-configuration
+.. _Pool limit configuration: https://curl-cffi.readthedocs.io/en/latest/api.html#sessions
-
-``max_keepalive_connection#s`` :
-  `Pool limit configuration`_, overwrites value ``pool_maxsize`` from
-   :ref:`settings outgoing` for this engine.
 
 ``max_connections`` :
   `Pool limit configuration`_, overwrites value ``pool_connections`` from
   :ref:`settings outgoing` for this engine.
 
-``keepalive_expiry`` :
-  `Pool limit configuration`_, overwrites value ``keepalive_expiry`` from
-  :ref:`settings outgoing` for this engine.
-
 
 .. _private engines:
 

docs/admin/settings/settings_outgoing.rst

@@ -12,20 +12,12 @@ Communication with search engines.
      request_timeout: 2.0       # default timeout in seconds, can be override by engine
      max_request_timeout: 10.0  # the maximum timeout in seconds
      useragent_suffix: ""       # information like an email address to the administrator
-     pool_connections: 100      # Maximum number of allowable connections, or null
+     pool_connections: 100      # Maximum number of concurrent connections (default: 100)
-                                # for no limits. The default is 100.
+     enable_http2: true         # Enables the use of HTTP2
-     pool_maxsize: 10           # Number of allowable keep-alive connections, or null
-                                # to always allow. The default is 10.
-     enable_http2: true         # See https://www.python-httpx.org/http2/
      # uncomment below section if you want to use a custom server certificate
-     # see https://www.python-httpx.org/advanced/#changing-the-verification-defaults
-     # and https://www.python-httpx.org/compatibility/#ssl-configuration
      #  verify: ~/.mitmproxy/mitmproxy-ca-cert.cer
      #
-     # uncomment below section if you want to use a proxyq see: SOCKS proxies
+     # uncomment below section if you want to use a proxy
-     #   https://2.python-requests.org/en/latest/user/advanced/#proxies
-     # are also supported: see
-     #   https://2.python-requests.org/en/latest/user/advanced/#socks
      #
      #  proxies:
      #    all://:
@@ -46,30 +38,26 @@ Communication with search engines.
   timeout to load).  Can be override by ``timeout`` in the :ref:`settings engines`.
 
 ``useragent_suffix`` :
-  Suffix to the user-agent SearXNG uses to send requests to others engines.  If an
+  Suffix to add when an engine's User-Agent is set via searxng_useragent().
-  engine wish to block you, a contact info here may be useful to avoid that.
+  Contact info here may be useful to avoid an engine blocking you.
 
-.. _Pool limit configuration: https://www.python-httpx.org/advanced/#pool-limit-configuration
+.. _Pool limit configuration: https://curl-cffi.readthedocs.io/en/latest/api.html#sessions
-
-``pool_maxsize``:
-  Number of allowable keep-alive connections, or ``null`` to always allow.  The
-  default is 10.  See ``max_keepalive_connections`` `Pool limit configuration`_.
 
 ``pool_connections`` :
-  Maximum number of allowable connections, or ``null`` # for no limits.  The
+  Maximum number of concurrent connections.  The default is 100.
-  default is 100.  See ``max_connections`` `Pool limit configuration`_.
+  See ``max_clients`` `Pool limit configuration`_.
 
-``keepalive_expiry`` :
+.. _curl_cffi proxies: https://curl-cffi.readthedocs.io/en/latest/quick_start.html
-  Number of seconds to keep a connection in the pool.  By default 5.0 seconds.
-  See ``keepalive_expiry`` `Pool limit configuration`_.
-
-.. _httpx proxies: https://www.python-httpx.org/advanced/#http-proxying
 
 ``proxies`` :
-  Define one or more proxies you wish to use, see `httpx proxies`_.
+  Define one or more proxies you wish to use, see `curl_cffi proxies`_.
   If there are more than one proxy for one protocol (http, https),
   requests to the engines are distributed in a round-robin fashion.
 
+  HTTP, HTTPS, SOCKS4, SOCKS5 and SOCKS5h proxies are supported
+  (``http://``, ``https://``, ``socks4://``, ``socks5://``, ``socks5h://``). You should
+  use ``socks5h://`` when using Tor so hostnames are resolved by the proxy.
+
 ``source_ips`` :
   If you use multiple network interfaces, define from which IP the requests must
   be made. Example:
@@ -87,18 +75,15 @@ Communication with search engines.
   different proxy and source ip.
 
 ``enable_http2`` :
-  Enable by default. Set to ``false`` to disable HTTP/2.
+  Enable by default (HTTP/2).  Set to ``false`` to force HTTP/1.1.
-
+  HTTP/3 is opt-in per engine (``enable_http3``).
-.. _httpx verification defaults: https://www.python-httpx.org/advanced/#changing-the-verification-defaults
-.. _httpx ssl configuration: https://www.python-httpx.org/compatibility/#ssl-configuration
 
 ``verify``: : ``$SSL_CERT_FILE``, ``$SSL_CERT_DIR``
-  Allow to specify a path to certificate.
+  HTTPS verification uses the OS's trust store by default.
-  see `httpx verification defaults`_.
+  Set a path to use a custom CA file.
 
   In addition to ``verify``, SearXNG supports the ``$SSL_CERT_FILE`` (for a file) and
   ``$SSL_CERT_DIR`` (for a directory) OpenSSL variables.
-  see `httpx ssl configuration`_.
 
 ``max_redirects`` :
   30 by default. Maximum redirect before it is an error.

docs/dev/engines/engine_overview.rst

@@ -143,7 +143,7 @@ parameters with default value can be redefined for special purposes.
    data                   dict           ``{}``
    cookies                dict           ``{}``
    verify                 bool           ``True``
-   headers.User-Agent     str            a random User-Agent
+   headers.User-Agent     str            ``''``
    category               str            current category, like ``'general'``
    safesearch             int            ``0``, between ``0`` and ``2`` (normal, moderate, strict)
    time_range             Optional[str]  ``None``, can be ``day``, ``week``, ``month``, ``year``
@@ -229,6 +229,8 @@ following parameters can be used to specify a search request:
    max_redirects       int         maximum redirects, hard limit
    soft_max_redirects  int         maximum redirects, soft limit. Record an error but don't stop the engine
    raise_for_httperror bool        True by default: raise an exception if the HTTP code of response is >= 300
+   impersonate         str         curl_cffi impersonate target (default: chrome, none to disable)
+   curl_options        dict        Any extra libcurl options for the request
    =================== =========== ==========================================================================
 
 

docs/dev/engines/online/cara.rst

@@ -1,8 +0,0 @@
-.. _cara engine:
-
-===========
-Cara Images
-===========
-
-.. automodule:: searx.engines.cara
-   :members:

docs/dev/engines/online/europepmc.rst

@@ -0,0 +1,8 @@
+.. _europepmc engine:
+
+==========
+Europe PMC
+==========
+
+.. automodule:: searx.engines.europepmc
+   :members:

docs/dev/reST.rst

@@ -286,7 +286,7 @@ content becomes smart.
    files & folders origin     :origin:`docs/dev/reST.rst`        ``:origin:`docs/dev/reST.rst```
    pull request               :pull:`4`                          ``:pull:`4```
    patch                      :patch:`af2cae6`                   ``:patch:`af2cae6```
-   PyPi package               :pypi:`httpx`                      ``:pypi:`httpx```
+   PyPi package               :pypi:`curl_cffi`                  ``:pypi:`curl_cffi```
    manual page man            :man:`bash`                        ``:man:`bash```
    intersphinx_
    --------------------------------------------------------------------------------------------------

requirements-dev.txt

@@ -1,10 +1,10 @@
 mock==5.2.0
 nose2[coverage_plugin]==0.16.0
 cov-core==1.15.0
-black==25.9.0
+black==26.5.1
-pylint==4.0.7
+pylint==4.0.8
 splinter==0.21.0
-selenium==4.47.0
+selenium==4.48.0
 Sphinx==8.2.3;python_version <= "3.11"
 Sphinx==9.1.0; python_version > "3.11"
 sphinx-issues==6.0.0

requirements.txt

@@ -7,13 +7,11 @@ lxml==6.1.2
 pygments==2.21.0
 python-dateutil==2.9.0.post0
 pyyaml==6.0.3
-httpx[http2]==0.28.1
+curl_cffi==0.16.1
-httpx-socks[asyncio]==0.13.1
-sniffio==1.3.1
 valkey==6.1.1
 markdown-it-py==4.2.0
 msgspec==0.21.1
-typer==0.27.1
+typer==0.27.2
 isodate==0.7.2
 whitenoise==6.12.0
 typing-extensions==4.16.0

searx/_settings.py

@@ -1,5 +1,6 @@
 # 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

searx/answerers/__init__.py

@@ -38,7 +38,6 @@ area:
 
 """
 
-
 __all__ = ["AnswererInfo", "Answerer", "AnswerStorage"]
 
 

searx/answerers/_core.py

@@ -13,7 +13,6 @@ 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")
 

searx/autocomplete.py

@@ -11,7 +11,7 @@ from urllib.parse import urlencode
 
 import lxml.etree
 import lxml.html
-from httpx import HTTPError
+from curl_cffi.requests.exceptions import RequestException
 
 from searx import settings
 from searx.engines import (
@@ -63,7 +63,7 @@ def bing(query: str, _sxng_locale: str) -> list[str]:
     base_url = "https://www.bing.com/AS/Suggestions?"
     # cvid has to be a 32 character long string consisting of numbers and uppsercase characters
     cvid = ''.join(random.choices(string.ascii_uppercase + string.digits, k=32))
-    response = get(base_url + urlencode({'qry': query, 'csr': 1, 'cvid': cvid}))
+    response = get(base_url + urlencode({'qry': query, 'csr': 1, 'cvid': cvid}), enable_http3=True)
     results: list[str] = []
 
     if response.ok:
@@ -83,7 +83,7 @@ def brave(query: str, _sxng_locale: str) -> list[str]:
     url = 'https://search.brave.com/api/suggest?'
     url += urlencode({'q': query})
     country = 'all'
-    kwargs = {'cookies': {'country': country}}
+    kwargs = {'cookies': {'country': country}, 'enable_http3': True}
     resp = get(url, **kwargs)
     results: list[str] = []
 
@@ -147,7 +147,7 @@ def google_complete(query: str, sxng_locale: str) -> list[str]:
     )
     results: list[str] = []
 
-    resp = get('https://www.google.com/complete/search?' + args)
+    resp = get('https://www.google.com/complete/search?' + args, enable_http3=True)
     if resp and resp.ok:
         json_txt = resp.text[resp.text.find('[') : resp.text.find(']', -3) + 1]
         data = json.loads(json_txt)
@@ -418,5 +418,5 @@ def search_autocomplete(backend_name: str, query: str, sxng_locale: str) -> list
         return []
     try:
         return backend(query, sxng_locale)
-    except (HTTPError, SearxEngineResponseException):
+    except (RequestException, SearxEngineResponseException):
         return []

searx/botdetection/__init__.py

@@ -5,7 +5,6 @@ Implementations used for bot detection.
 
 """
 
-
 __all__ = ["init", "dump_request", "get_network", "too_many_requests", "ProxyFix"]
 
 

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)
 

searx/botdetection/http_accept.py

@@ -13,7 +13,6 @@ Accept_ header ..
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_accept_encoding.py

@@ -14,7 +14,6 @@ bot if the Accept-Encoding_ header ..
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_accept_language.py

@@ -11,7 +11,6 @@ if the Accept-Language_ header is unset.
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_connection.py

@@ -11,7 +11,6 @@ the Connection_ header is set to ``close``.
 
 """
 
-
 from ipaddress import (
     IPv4Network,
     IPv6Network,

searx/botdetection/http_sec_fetch.py

@@ -20,6 +20,7 @@ Metadata`_.  A request is filtered out in case of:
 
 
 """
+
 # pylint: disable=unused-argument
 
 

searx/botdetection/http_user_agent.py

@@ -12,7 +12,6 @@ the User-Agent_ header is unset or matches the regular expression
 
 """
 
-
 import re
 from ipaddress import (
     IPv4Network,
@@ -25,7 +24,6 @@ import flask
 from . import config
 from ._helpers import too_many_requests
 
-
 USER_AGENT = (
     r'('
     + r'unknown'

searx/botdetection/ip_limit.py

@@ -55,7 +55,6 @@ from ._helpers import (
     logger,
 )
 
-
 logger = logger.getChild('ip_limit')
 
 BURST_WINDOW = 20

searx/botdetection/ip_lists.py

@@ -23,6 +23,7 @@ The ``ip_lists`` method implements :py:obj:`block-list <block_ip>` and
    ]
 
 """
+
 # pylint: disable=unused-argument
 
 

searx/botdetection/trusted_proxies.py

@@ -1,6 +1,7 @@
 # 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
 
 

searx/botdetection/valkeydb.py

@@ -1,7 +1,6 @@
 # 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"]

searx/brand.py

@@ -1,5 +1,6 @@
 # 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

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

searx/compat.py

@@ -3,7 +3,6 @@
 
 import warnings
 
-
 # limiter backward compatibility
 # ------------------------------
 

searx/data/__init__.py

@@ -4,6 +4,7 @@
 make data.all
 
 """
+
 # pylint: disable=invalid-name
 
 __all__ = ["ahmia_blacklist_loader", "data_dir", "get_cache"]

searx/data/tracker_patterns.py

@@ -1,5 +1,6 @@
 # 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
@@ -10,7 +11,7 @@ import re
 from collections.abc import Iterator
 from urllib.parse import urlparse, urlunparse, parse_qsl, urlencode
 
-from httpx import HTTPError
+from curl_cffi.requests.exceptions import RequestException
 
 from searx.data.core import get_cache, log
 from searx.network import get as http_get
@@ -87,8 +88,8 @@ class TrackerPatternsDB:
             try:
                 resp = http_get(url, timeout=3)
 
-            except HTTPError as exc:
+            except RequestException as exc:
-                log.warning("TRACKER_PATTERNS: HTTPError (%s) occured while fetching %s", url, exc)
+                log.warning("TRACKER_PATTERNS: RequestException while fetching %s: %s", url, exc)
                 continue
 
             if resp.status_code != 200:

searx/enginelib/__init__.py

@@ -305,7 +305,7 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
 
     region: str = ""
     """For an engine, when there is ``region: ...`` in the YAML settings the engine
-    does support only this one region::
+    does support only this one region:
 
     .. code:: yaml
 
@@ -317,6 +317,9 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
     enable_http: bool
     """Enable HTTP (by default only HTTPS is enabled)."""
 
+    enable_http3: bool = False
+    """Enables the use of HTTP/3 if available"""
+
     shortcut: str
     """Code used to execute bang requests (``!foo``)"""
 

searx/engines/__builtins__.pyi

@@ -26,6 +26,7 @@ categories: list[str]
 disabled: bool
 display_error_messages: bool
 enable_http: bool
+enable_http3: bool
 engine_type: str
 inactive: bool
 max_page: int

searx/engines/adobe_stock.py

@@ -35,6 +35,7 @@ Implementation
 ==============
 
 """
+
 import typing as t
 from datetime import datetime, timedelta
 from urllib.parse import urlencode

searx/engines/azure.py

@@ -25,6 +25,7 @@ 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

searx/engines/base.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """BASE (Scholar publications)"""
+
 from datetime import datetime
 import re
 

searx/engines/bing.py

@@ -40,6 +40,7 @@ about: dict[str, t.Any] = {
 # engine dependent config
 categories = ["general", "web"]
 safesearch = True
+enable_http3 = True
 _safesearch_map: dict[int, str] = {
     0: "off",
     1: "moderate",
@@ -61,8 +62,8 @@ def get_locale_params(engine_region: str | None) -> dict[str, str] | None:
 
     The ``mkt`` parameter takes a full ``<language>-<country>`` code.
 
-    This function is shared with :py:mod:`searx.engines.bing_images`,
+    This function is shared with :py:mod:`searx.engines.bing_news`, and
-    :py:mod:`searx.engines.bing_news`, and :py:mod:`searx.engines.bing_videos`.
+    :py:mod:`searx.engines.bing_videos`.
     """
 
     if not engine_region or engine_region == "clear":
@@ -71,43 +72,21 @@ def get_locale_params(engine_region: str | None) -> dict[str, str] | None:
     return {"mkt": engine_region}
 
 
-def override_accept_language(params: "OnlineParams", engine_region: str | None) -> None:
-    """Override the ``Accept-Language`` header.
-
-    The default header built by :py:class:`~searx.search.processors.online.OnlineProcessor`
-    appends ``en;q=0.3`` as a fallback language::
-
-        Accept-Language: de,de-DE;q=0.7,en;q=0.3
-
-    Bing seems to better select the results locale based on the
-    ``Accept-Language`` value header.
-
-    This function is shared with :py:mod:`searx.engines.bing_images`,
-    :py:mod:`searx.engines.bing_news`, and :py:mod:`searx.engines.bing_videos`.
-    """
-
-    if not engine_region or engine_region == "clear":
-        return
-
-    lang = engine_region.split("-")[0]
-    params["headers"]["Accept-Language"] = f"{engine_region},{lang};q=0.9"
-
-
 def request(query: str, params: "OnlineParams"):
     """Assemble a Bing-Web request."""
 
     engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
 
-    override_accept_language(params, engine_region)
-
     query_params: dict[str, str | int] = {
         "q": query,
         "adlt": _safesearch_map.get(params.get("safesearch", 0), "off"),
     }
 
-    locale_params = get_locale_params(engine_region)
+    if engine_region and engine_region != "clear":
-    if locale_params:
+        lang, _, cc = engine_region.partition("-")
-        query_params.update(locale_params)
+        query_params["setlang"] = lang
+        if cc and cc not in ("us", "cn", "ru"):  # bing just sends junk for these
+            query_params["cc"] = cc
 
     params["url"] = f"{base_url}/search?{urlencode(query_params)}"
 

searx/engines/bing_images.py

@@ -1,18 +1,20 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Bing-Images: description see :py:obj:`searx.engines.bing`."""
 
+import typing as t
 import json
 from urllib.parse import urlencode
 
 from lxml import html
 
-from searx.engines.bing import (  # pylint: disable=unused-import
+from searx.engines.bing import fetch_traits  # pylint: disable=unused-import
-    fetch_traits,
+from searx.result_types import EngineResults
-    get_locale_params,
+
-    override_accept_language,
+if t.TYPE_CHECKING:
-)
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
+
 
-# about
 about = {
     "website": "https://www.bing.com/images",
     "wikidata_id": "Q182496",
@@ -22,9 +24,9 @@ about = {
     "results": "HTML",
 }
 
-# engine dependent config
 categories = ["images", "web"]
 paging = True
+enable_http3 = True
 safesearch = True
 time_range_support = True
 time_map = {
@@ -38,26 +40,27 @@ base_url = "https://www.bing.com"
 """Bing-Image search URL"""
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams"):
     """Assemble a Bing-Image request."""
 
     engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
 
-    override_accept_language(params, engine_region)
+    # build URL query / example:
+    # https://www.bing.com/images/async?q=foo&mmasync=1&first=1&count=35
 
-    # build URL query
-    # - example: https://www.bing.com/images/async?q=foo&async=1&first=1&count=35
     query_params = {
         "q": query,
-        "async": "1",
+        "mmasync": "1",
         # to simplify the page count lets use the default of 35 images per page
         "first": (int(params.get("pageno", 1)) - 1) * 35 + 1,
         "count": 35,
     }
 
-    locale_params = get_locale_params(engine_region)
+    if engine_region and engine_region != "clear":
-    if locale_params:
+        lang, _, cc = engine_region.partition("-")
-        query_params.update(locale_params)
+        query_params["setlang"] = lang
+        if cc:
+            query_params["cc"] = cc
 
     # time range
     # - example: one year (525600 minutes) 'qft=filterui:age-lt525600'
@@ -67,10 +70,10 @@ def request(query, params):
     params["url"] = base_url + "/images/async?" + urlencode(query_params)
 
 
-def response(resp):
+def response(resp: "SXNG_Response") -> EngineResults:
     """Get response from Bing-Image"""
 
-    results = []
+    res = EngineResults()
 
     dom = html.fromstring(resp.text)
 
@@ -81,19 +84,22 @@ def response(resp):
 
         metadata = json.loads(result.xpath('.//a[@class="iusc"]/@m')[0])
         title = " ".join(result.xpath('.//div[@class="infnmpt"]//a/text()')).strip()
+        if not title:
+            title = result.xpath('.//div[@class="infnmpt"]//a/@title')[0]
+
         img_format = " ".join(result.xpath('.//div[@class="imgpt"]/div/span/text()')).strip().split(" · ")
         source = " ".join(result.xpath('.//div[@class="imgpt"]//div[@class="lnkw"]//a/text()')).strip()
-        results.append(
+
-            {
+        res.add(
-                "template": "images.html",
+            res.types.Image(
-                "url": metadata["purl"],
+                title=title,
-                "thumbnail_src": metadata["turl"],
+                url=metadata["purl"],
-                "img_src": metadata["murl"],
+                thumbnail_src=metadata["turl"],
-                "content": metadata.get("desc"),
+                img_src=metadata["murl"],
-                "title": title,
+                content=metadata.get("desc"),
-                "source": source,
+                source=source,
-                "resolution": img_format[0],
+                resolution=img_format[0],
-                "img_format": img_format[1] if len(img_format) >= 2 else None,
+                img_format=img_format[1] if len(img_format) >= 2 else "",
-            }
             )
-    return results
+        )
+    return res

searx/engines/bing_news.py

@@ -12,10 +12,7 @@ from urllib.parse import urlencode
 from lxml import html
 
 from searx.enginelib.traits import EngineTraits
-from searx.engines.bing import (
+from searx.engines.bing import get_locale_params
-    get_locale_params,
-    override_accept_language,
-)
 from searx.utils import eval_xpath, eval_xpath_getindex, eval_xpath_list, extract_text
 
 # about
@@ -33,6 +30,7 @@ categories = ["news"]
 paging = True
 """If go through the pages and there are actually no new results for another
 page, then bing returns the results from the last page again."""
+enable_http3 = True
 
 time_range_support = True
 time_map = {
@@ -53,8 +51,6 @@ def request(query, params):
 
     engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
 
-    override_accept_language(params, engine_region)
-
     # build URL query
     # - example: https://www.bing.com/news/infinitescrollajax?q=london&first=1
     page = int(params.get("pageno", 1)) - 1

searx/engines/bing_videos.py

@@ -9,7 +9,6 @@ from lxml import html
 from searx.engines.bing import (  # pylint: disable=unused-import
     fetch_traits,
     get_locale_params,
-    override_accept_language,
 )
 from searx.engines.bing_images import time_map
 from searx.utils import eval_xpath, eval_xpath_getindex
@@ -26,6 +25,7 @@ about = {
 # engine dependent config
 categories = ["videos", "web"]
 paging = True
+enable_http3 = True
 safesearch = True
 time_range_support = True
 
@@ -38,8 +38,6 @@ def request(query, params):
 
     engine_region = traits.get_region(params["searxng_locale"], traits.all_locale)
 
-    override_accept_language(params, engine_region)
-
     # build URL query
     # - example: https://www.bing.com/videos/asyncv2?q=foo&async=content&first=1&count=35
     query_params = {

searx/engines/brave.py

@@ -151,6 +151,7 @@ about = {
 
 base_url = "https://search.brave.com/"
 categories = []
+enable_http3 = True
 brave_category: t.Literal["search", "videos", "images", "news", "goggles"] = "search"
 """Brave supports common web-search, videos, images, news, and goggles search.
 
@@ -247,13 +248,13 @@ def extract_json_data(text: str) -> dict[str, t.Any]:
     #    node_ids: [0, 19],
     #    data: [{type:"data",data: .... ["q","goggles_id"],route:1,url:1}}]
     #          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-    text = text[text.index("<script") : text.index("</script")]
+    #    form: null,
-    if not text:
+    #    error: null
-        raise ValueError("can't find JS/JSON data in the given text")
+    # });
     start = text.index("data: [{")
-    end = text.rindex("}}]")
+    newline = text.index("\n", start)
-    js_obj_str = text[start:end]
+    end = text.rindex("}}]", start, newline)
-    js_obj_str = "{" + js_obj_str + "}}]}"
+    js_obj_str = "{" + text[start:end] + "}}]}"
     # js_obj_str = js_obj_str.replace("\xa0", "")  # remove ASCII for &nbsp;
     # js_obj_str = js_obj_str.replace(r"\u003C", "<").replace(r"\u003c", "<")  # fix broken HTML tags in strings
     json_str = js_obj_str_to_json_str(js_obj_str)
@@ -353,14 +354,14 @@ def _parse_news(resp: SXNG_Response) -> EngineResults:
     res = EngineResults()
     dom = html.fromstring(resp.text)
 
-    for result in eval_xpath_list(dom, "//div[contains(@class, 'results')]//div[@data-type='news']"):
+    for result in eval_xpath_list(dom, "//div[@data-type='news']"):
-        url = eval_xpath_getindex(result, ".//a[contains(@class, 'result-header')]/@href", 0, default=None)
+        url = eval_xpath_getindex(result, ".//a/@href", 0, default=None)
         if url is None:
             continue
 
-        title = eval_xpath_list(result, ".//span[contains(@class, 'snippet-title')]")
+        title = eval_xpath_list(result, ".//div[contains(@class, 'title')]")
-        content = eval_xpath_list(result, ".//p[contains(@class, 'desc')]")
+        content = eval_xpath_list(result, ".//div[contains(@class, 'description')]")
-        thumbnail = eval_xpath_getindex(result, ".//div[contains(@class, 'image-wrapper')]//img/@src", 0, default="")
+        thumbnail = eval_xpath_getindex(result, ".//a[contains(@class, 'thumbnail')]//img/@src", 0, default="")
 
         item = res.types.LegacyResult(
             template="default.html",

searx/engines/braveapi.py

@@ -91,6 +91,7 @@ def request(query: str, params: "OnlineParams") -> None:
 
     params["url"] = f"{base_url}?{urlencode(search_args)}"
     params["headers"]["X-Subscription-Token"] = api_key
+    params["headers"]["Accept"] = "application/json"
 
 
 def _extract_published_date(published_date_raw: str):

searx/engines/cara.py

@@ -1,85 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-# pylint: disable=invalid-name
-"""Cara_ is a social media and portfolio-sharing platform for artists and art
-enthusiasts.
-
-With the widespread use of generative AI, Cara_ decided to build a place that
-filters out gen AI images so that people searching for authentic creatives and
-images can do so easily.
-
-.. _Cara: https://cara.app/about
-"""
-
-from urllib.parse import urlencode
-
-import typing as t
-
-from searx.result_types import EngineResults
-
-if t.TYPE_CHECKING:
-    from searx.extended_types import SXNG_Response
-    from searx.search.processors import OnlineParams
-
-
-about = {
-    "website": "https://cara.app",
-    "official_api_documentation": None,
-    "use_official_api": False,
-    "require_api_key": False,
-    "results": "JSON",
-}
-
-base_url = "https://cara.app"
-images_url = "https://images.cara.app"
-
-categories = ["images"]
-paging = True
-results_per_page = 24
-
-# if using HTTP2, we get blocked immediately
-enable_http2 = False
-
-
-def request(query: str, params: "OnlineParams") -> None:
-    args = {
-        "q": query,
-        "sortBy": "Top",
-        "take": results_per_page,
-        "skip": (params["pageno"] - 1) * results_per_page,
-    }
-    params["url"] = f"{base_url}/api/search/portfolio-posts?{urlencode(args)}"
-
-
-def response(resp: "SXNG_Response"):
-    res = EngineResults()
-    json_data: list[dict[str, t.Any]] = resp.json()
-
-    for result in json_data:
-        thumbnail, img = None, None
-
-        i: dict[str, str]
-        for i in result["images"]:
-            if thumbnail is None or i["isCoverImg"]:
-                thumbnail = i
-
-            if img is None or not i["isCoverImg"]:
-                img = i
-
-        if not thumbnail or not img:
-            continue
-
-        res.add(
-            res.types.LegacyResult(
-                {
-                    "template": "images.html",
-                    "url": f"{base_url}/post/{result['id']}",
-                    "thumbnail_src": f"{images_url}/{thumbnail['src']}?height=256",
-                    "img_src": f"{images_url}/{img['src']}",
-                    "title": result["title"],
-                    "content": result["content"],
-                    "author": result["name"],
-                }
-            )
-        )
-
-    return res

searx/engines/chatnoir.py

@@ -84,6 +84,7 @@ def request(query: str, params: "OnlineParams"):
 
     params["url"] = f"{base_url}/api/v1/_search"
     params["method"] = "POST"
+    params["impersonate"] = "none"
 
     json_data = {
         "query": query,

searx/engines/command.py

@@ -84,7 +84,6 @@ from threading import Thread
 from searx import logger
 from searx.result_types import EngineResults
 
-
 engine_type = 'offline'
 paging = True
 command = []

searx/engines/core.py

@@ -141,12 +141,13 @@ def response(resp: "SXNG_Response") -> EngineResults:
             if name:
                 authors.add(name)
 
+        tag = result.get("fieldOfStudy")
         res.add(
             res.types.Paper(
                 title=result.get("title"),
                 url=url,
                 content=result.get("fullText", "") or "",
-                tags=result.get("fieldOfStudy", []),
+                tags=[tag] if tag else [],
                 publishedDate=published_date,
                 type=result.get("documentType", "") or "",
                 authors=authors,

searx/engines/docker_hub.py

@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Docker Hub (IT)"""
+
 # pylint: disable=use-dict-literal
 
 from urllib.parse import urlencode

searx/engines/dogpile.py

@@ -8,6 +8,9 @@ import typing as t
 from datetime import datetime, timezone
 import html
 
+from searx.enginelib import EngineCache
+from searx.exceptions import SearxEngineAPIException
+from searx.network import post
 from searx.utils import format_duration, html_to_text, humanize_number
 from searx.result_types import EngineResults
 
@@ -35,15 +38,35 @@ dogpile_categ = "search"
 base_url = "https://www.dogpile.com"
 safe_search_map = {0: "none", 1: "moderate", 2: "heavy"}
 
+CACHE: EngineCache
+"""Cache for the API token from dogpile"""
+
 
 def setup(_: dict[str, t.Any]) -> bool | None:
     if dogpile_categ not in ("search", "images", "videos", "news"):
         raise ValueError("invalid search type: %s" % dogpile_categ)
+    global CACHE  # pylint: disable=global-statement
+    CACHE = EngineCache("dogpile")  # one token for images/videos/news
+    return True
+
+
+def _obtain_token() -> str:
+    token = CACHE.get("token")
+    if token:
+        return token
+    resp = post(f"{base_url}/api/token/refresh", headers={"Origin": base_url}, cookies={"dp_api_token": "1"})
+    if not resp.ok:
+        raise SearxEngineAPIException("failed to obtain dogpile token")
+    token = resp.json()["token"]
+    CACHE.set("token", token, expire=240)  # 300s ttl
+    return token
 
 
 def request(query: str, params: "OnlineParams"):
     params["url"] = f"{base_url}/api/{dogpile_categ}"
     params["headers"]["Origin"] = base_url
+    params["cookies"]["dp_api_token"] = "1"
+    params["headers"]["x-dogpile-token"] = _obtain_token()
 
     params["method"] = "POST"
     params["json"] = {"q": query, "qadf": safe_search_map[params["safesearch"]], "page": params["pageno"]}

searx/engines/duckduckgo.py

@@ -164,6 +164,7 @@ 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

searx/engines/duckduckgo_definitions.py

@@ -12,6 +12,7 @@ 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

searx/engines/duckduckgo_extra.py

@@ -98,6 +98,7 @@ def request(query: str, params: "OnlineParams") -> None:
     # The vqd value is generated from the query and the UA header. To be able to
     # reuse the vqd value, the UA header must be static.
     headers["User-Agent"] = _HTTP_User_Agent
+    params["impersonate"] = "none"
     vqd = get_vqd(query=query, params=params) or fetch_vqd(query=query, params=params)
 
     headers["Accept"] = "*/*"

searx/engines/duckduckgo_weather.py

@@ -17,7 +17,6 @@ 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',

searx/engines/duckduckgo_web.py

@@ -14,11 +14,12 @@ can't build it ourselves and must scrape it from the HTML pages.
 """
 
 import typing as t
+import re
 
-from urllib.parse import quote_plus
+from urllib.parse import quote_plus, urljoin
 from lxml import html
 
-from searx.utils import html_to_text, gen_useragent, extract_text, eval_xpath
+from searx.utils import html_to_text, extract_text, eval_xpath
 from searx.result_types import EngineResults
 from searx.enginelib import EngineCache
 from searx.network import get
@@ -38,7 +39,6 @@ about = {
 # engine dependent config
 categories = ["general"]
 paging = True
-_HTTP_User_Agent: str = gen_useragent()
 
 base_url = "https://duckduckgo.com"
 
@@ -73,6 +73,8 @@ def _fetch_first_page_link(
     resp = get(
         url=f"{base_url}/?q={quote_plus(query)}&t=h_&ia=web",
         headers=headers,
+        impersonate="firefox",
+        default_headers=False,
         timeout=2,
     )
 
@@ -96,6 +98,43 @@ def _cache_key(query: str, pageno: int) -> str:
     return f"nextpage_url|{query}|{pageno}"
 
 
+def _solve_jsa(resp: "SXNG_Response") -> "SXNG_Response":
+    """Duckduckgo sometimes issues a challenge instead of json."""
+
+    # length that a real browser would report for where the broken snippet is
+    html_len = {
+        "<p><div></p><p></div": 32,
+        "<li><div></li><li></div": 29,
+        "<div><div></div><div></div": 33,
+        "<br><div></br><br></div": 23,
+    }
+
+    js = resp.text or ""
+    jsa_match = re.search(r"let jsa = (\d+);.*?DDG\.deep\.initialize\('([^']+)'", js, re.S)
+    if not jsa_match:
+        return resp
+
+    js_functions = dict(re.findall(r"let (\w+) = function\(num\) \{([^}]*)\};", js))
+    jsa = int(jsa_match.group(1))
+    try:
+        for name in re.findall(r"jsa = (\w+)\(jsa\);", js):
+            body = js_functions[name]
+            mul = re.search(r"num \* (\d+)", body)
+            jsa = jsa * int(mul.group(1)) if mul else jsa + html_len[re.search(r"`([^`]+)`", body).group(1)]
+    except (KeyError, AttributeError):
+        return resp
+
+    params = resp.search_params
+    follow = get(
+        urljoin("https://links.duckduckgo.com", jsa_match.group(2) + str(jsa)),
+        headers=params["headers"],
+        impersonate="firefox",
+        default_headers=False,
+    )
+    follow.search_params = params
+    return follow
+
+
 def request(query: str, params: "OnlineParams") -> None:
 
     if len(query) >= 500:
@@ -103,25 +142,15 @@ def request(query: str, params: "OnlineParams") -> None:
         params["url"] = None
         return
 
-    headers = params["headers"]
+    # firefox TLS only
-
+    params["impersonate"] = "firefox"
-    # The vqd value is generated from the query and the UA header.  To be able
+    params["default_headers"] = False
-    # to reuse the vqd value, the UA header must be static.
-    headers["User-Agent"] = _HTTP_User_Agent
-    headers["Accept"] = "*/*"
-    headers["Referer"] = f"{base_url}/"
-    headers["Host"] = "duckduckgo.com"
-
-    # Sec-Fetch headers are required to not get blocked when sending a Firefox user agent
-    headers["Sec-Fetch-Dest"] = "script"
-    headers["Sec-Fetch-Mode"] = "no-cors"
-    headers["Sec-Fetch-Site"] = "same-site"
 
     api_url = ""
     if params["pageno"] > 1:
         api_url = CACHE.get(_cache_key(query, params["pageno"]))
     else:
-        api_url = _fetch_first_page_link(query, headers)
+        api_url = _fetch_first_page_link(query, params["headers"])
 
     if not api_url:
         params["url"] = None
@@ -129,14 +158,27 @@ def request(query: str, params: "OnlineParams") -> None:
 
     params["url"] = api_url.replace("/d.js?", "/d.js?o=json&")
 
+    # loads as a script
+    headers = params["headers"]
+    headers["Accept"] = "*/*"
+    headers["Sec-Fetch-Dest"] = "script"
+    headers["Sec-Fetch-Mode"] = "no-cors"
+    headers["Sec-Fetch-Site"] = "same-site"
+    headers["Referer"] = f"{base_url}/"
+
     # TODO: support safesearch, timerange and engine traits  # pylint:disable=fixme
 
 
 def response(resp: "SXNG_Response"):
     res = EngineResults()
-    res_json = resp.json()
 
-    for result in res_json["results"]:
+    # check if ddg returns a challenge
+    # e.g. 'site:github.com searxng'
+    if "let jsa =" in (resp.text or ""):
+        resp = _solve_jsa(resp)
+
+    results = resp.json()["results"]
+    for result in results:
         if "u" not in result:
             continue
 
@@ -144,8 +186,8 @@ def response(resp: "SXNG_Response"):
             res.types.MainResult(url=result["u"], title=html_to_text(result["t"]), content=html_to_text(result["a"]))
         )
 
-    # link to next page
+    if results:
-    next_page_path = res_json["results"][-1].get("n")
+        next_page_path = results[-1].get("n")
         if next_page_path:
             CACHE.set(
                 _cache_key(resp.search_params["query"], resp.search_params["pageno"] + 1),

searx/engines/dummy-offline.py

@@ -2,7 +2,6 @@
 # pylint: disable=invalid-name
 """Dummy Offline"""
 
-
 # about
 about = {
     "wikidata_id": None,

searx/engines/europepmc.py

@@ -0,0 +1,150 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""`Europe PMC`_ provides comprehensive access to life sciences literature from
+trusted sources.  With Europe PMC you can search and read millions of
+publications, preprints and other documents enriched with links to supporting
+data, reviews, protocols, and other relevant resources.
+
+.. _Europe PMC: https://europepmc.org/
+
+Configuration
+=============
+
+.. code:: yaml
+
+   - name: europepmc
+     engine: europepmc
+     shortcut: epmc
+
+Implementations
+===============
+
+"""
+
+import typing as t
+
+from datetime import datetime
+from urllib.parse import urlencode
+
+from dateutil.parser import isoparse
+
+from searx.enginelib import EngineCache
+from searx.result_types import EngineResults
+from searx.utils import html_to_text
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
+
+
+about = {
+    "website": "https://europepmc.org/",
+    "wikidata_id": "Q5412157",
+    "official_api_documentation": "https://europepmc.org/RestfulWebService",
+    "use_official_api": True,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+categories = ["science", "scientific publications"]
+paging = True
+
+# engine dependent config
+search_url = "https://www.ebi.ac.uk/europepmc/webservices/rest/search"
+article_url = "https://europepmc.org/article/"
+
+page_size = 20
+
+CACHE: EngineCache
+"""Cache for storing the pagination cursor."""
+
+
+def setup(engine_settings: dict[str, t.Any]):
+    global CACHE  # pylint: disable=global-statement
+    CACHE = EngineCache(engine_settings["name"])
+
+
+def _cache_key(query: str, page: int) -> str:
+    return f"{query}|{page}"
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    args = {
+        "query": query,
+        "format": "json",
+        "resultType": "core",
+        "pageSize": page_size,
+    }
+
+    if params["pageno"] > 1:
+        if cursor := CACHE.get(_cache_key(query, params["pageno"])):
+            args["cursorMark"] = cursor
+        else:
+            # no cached cursor for that page
+            params["url"] = None
+            return
+
+    params["url"] = f"{search_url}?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    res = EngineResults()
+
+    json_resp = resp.json()
+
+    # store pagination cursor for loading next pages in cache
+    if next_cursor := json_resp.get("nextCursorMark"):
+        next_page = resp.search_params["pageno"] + 1
+        query = resp.search_params["query"]
+        CACHE.set(_cache_key(query, next_page), next_cursor)
+
+    all_results = json_resp.get("resultList", {}).get("result", [])
+
+    for item in all_results:
+        source = item.get("source", "")
+        identifier = item.get("id", "")
+        url = f"{article_url}{source}/{identifier}" if source and identifier else ""
+
+        journal_info: dict[str, t.Any] = item.get("journalInfo", {})
+        journal: dict[str, t.Any] = journal_info.get("journal", {})
+
+        res.add(
+            res.types.Paper(
+                url=url,
+                title=html_to_text(item.get("title", "")),
+                content=html_to_text(item.get("abstractText", "")),
+                journal=journal.get("title", ""),
+                issn=[journal.get("issn", "")],
+                authors=_get_authors(item),
+                doi=item.get("doi", ""),
+                publishedDate=_get_published_date(item),
+                type=", ".join((item.get("pubTypeList", {})).get("pubType", [])),
+                pdf_url=_get_pdf_url(item),
+                html_url=url,
+            )
+        )
+
+    return res
+
+
+def _get_authors(item: dict[str, t.Any]) -> list:
+    """Extract the list of authors from the item."""
+    if authors := item.get("authorString", None):
+        authors = [author.strip().rstrip(".") for author in authors.split(",") if author.strip()]
+    else:
+        authors = []
+    return authors
+
+
+def _get_pdf_url(item: dict[str, t.Any]) -> str:
+    """Extract the PDF URL in case it is open access."""
+    for url_info in (item.get("fullTextUrlList", {})).get("fullTextUrl", []):
+        if url_info.get("documentStyle") == "pdf" and url_info.get("availabilityCode") == "OA":
+            return url_info.get("url", "")
+    return ""
+
+
+def _get_published_date(item: dict[str, t.Any]) -> datetime | None:
+    """Extract the published date from the item and convert it to a datetime object."""
+    if unformatted_date := item.get("firstPublicationDate"):
+        return isoparse(unformatted_date)
+    return None

searx/engines/github_code.py

@@ -65,7 +65,6 @@ 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
 

searx/engines/google.py

@@ -327,6 +327,7 @@ def google_request(
 
     params["url"] = f"https://www.google.com/wml/search?{urlencode(args)}"
     params["headers"]["User-Agent"] = random.choice(nokia_useragents)
+    params["impersonate"] = "chrome99_android"
 
 
 def request(query: str, params: "OnlineParams") -> None:

searx/engines/google_cse.py

@@ -30,6 +30,7 @@ about = {
 
 categories = ["general", "web"]
 paging = True
+enable_http3 = True
 max_page = 5
 page_size = 20
 time_range_support = True

searx/engines/google_images.py

@@ -26,6 +26,7 @@ about = {
 # engine dependent config
 categories = ["images", "web"]
 paging = True
+enable_http3 = True
 max_page = 50
 """Google supports up to 50 pages of results, see the `Google max_page discussion`_.
 

searx/engines/google_play.py

@@ -20,6 +20,7 @@ about = {
 }
 
 play_categ = None  # apps|movies
+enable_http3 = True
 base_url = 'https://play.google.com'
 search_url = base_url + "/store/search?{query}&c={play_categ}"
 

searx/engines/google_scholar.py

@@ -27,7 +27,7 @@ import typing as t
 from urllib.parse import urlencode
 from datetime import datetime
 from lxml import html
-import httpx
+from curl_cffi.requests.exceptions import TooManyRedirects
 
 from searx.utils import (
     eval_xpath,
@@ -63,6 +63,7 @@ about = {
 # engine dependent config
 categories = ["science", "scientific publications"]
 paging = True
+enable_http3 = True
 max_page = 50
 """`Google max 50 pages`_
 
@@ -102,7 +103,7 @@ def response(resp: "SXNG_Response") -> EngineResults:  # pylint: disable=too-man
             raise SearxEngineAccessDeniedException(
                 message="google_scholar: unusual traffic detected",
             )
-        raise httpx.TooManyRedirects(f"location {resp.headers['Location'].split('?')[0]}")
+        raise TooManyRedirects(f"location {resp.headers['Location'].split('?')[0]}")
 
     res = EngineResults()
     dom = html.fromstring(resp.text)

searx/engines/hex.py

@@ -4,7 +4,6 @@
 from urllib.parse import urlencode
 from dateutil import parser
 
-
 about = {
     # pylint: disable=line-too-long
     "website": "https://hex.pm/",

searx/engines/jisho.py

@@ -108,14 +108,12 @@ 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>')

searx/engines/luxxle.py

@@ -37,17 +37,13 @@ about = {
 }
 
 categories = []
-safeseach = True
+safesearch = True
 
 base_url = "https://luxxle.com"
 
 luxxle_categ = "search"
 """Supported categories: "search", "news", "images", "videos"."""
 
-# otherwise all requests get blocked (http2-fingerprinted probably)
-enable_http2 = False
-
-
 safe_search_map = {0: "Off", 1: "Moderate", 2: "Strict"}
 
 

searx/engines/marginalia.py

@@ -10,7 +10,7 @@ Lofgren .
 .. _marginalia filters:
 
 Marginalia Filters
-=================
+==================
 
 Custom filters enable server-side customization of Marginalia search results.
 Filter definitions are written in XML and scoped to an API key.  Filters can
@@ -82,7 +82,7 @@ api_key = None
    https://about.marginalia-search.com/article/api/
 
 """
-filter_name: str | None = None
+filter_name: str = ""
 """The name of the custom filter to apply to each search."""
 
 

searx/engines/mongodb.py

@@ -49,7 +49,6 @@ except ImportError:
 
 from searx.result_types import EngineResults
 
-
 engine_type = 'offline'
 
 # mongodb connection variables

searx/engines/neosearch.py

@@ -6,10 +6,14 @@
 
 from json import loads
 import typing as t
-from urllib.parse import urlencode
 
+from lxml import html
+
+from searx.exceptions import SearxEngineAPIException
 from searx.extended_types import SXNG_Response
+from searx.network import get
 from searx.result_types import EngineResults
+from searx.utils import eval_xpath, extract_text
 
 if t.TYPE_CHECKING:
     from searx.enginelib.traits import EngineTraits
@@ -25,18 +29,33 @@ about = {
     "results": "JSON",
 }
 
+paging = False
+enable_http3 = True
+
 base_url = "https://neosearch.org"
 categories = ["general"]
 
-paging = False
+
+def _obtain_xsrf_token() -> str:
+    resp = get(base_url)
+    doc = html.fromstring(resp.text)
+
+    xsrf_token = extract_text(eval_xpath(doc, "//meta[@name='xsrf-token']/@content"))
+    if not xsrf_token:
+        raise SearxEngineAPIException("failed to obtain xsrf token")
+    return xsrf_token
 
 
 def request(query: str, params: "OnlineParams"):
+    params["url"] = f"{base_url}/search"
+    params["headers"]["X-XSRF-TOKEN"] = _obtain_xsrf_token()
+    params["method"] = "POST"
+
     args = {"q": query, "generate": "auto"}
     countrycode = params["searxng_locale"].split("-")[-1].upper()
     if countrycode in traits.custom["countrycodes"]:
         args["loc"] = countrycode
-    params["url"] = f"{base_url}/search?{urlencode(args)}"
+    params["json"] = args
 
 
 def response(resp: "SXNG_Response") -> EngineResults:
@@ -67,7 +86,6 @@ def response(resp: "SXNG_Response") -> EngineResults:
 
 def fetch_traits(engine_traits: "EngineTraits") -> None:
     # pylint: disable=import-outside-toplevel
-    from searx.network import get
     from searx.utils import extr, js_obj_str_to_python
     from babel.core import get_global
 

searx/engines/npm.py

@@ -4,7 +4,6 @@
 from urllib.parse import urlencode
 from dateutil import parser
 
-
 about = {
     "website": "https://npms.io/",
     "wikidata_id": "Q7067518",

searx/engines/open_meteo.py

@@ -9,7 +9,6 @@ from datetime import datetime
 from searx.result_types import EngineResults, WeatherAnswer
 from searx import weather
 
-
 about = {
     "website": "https://open-meteo.com",
     "wikidata_id": None,

searx/engines/openverse.py

@@ -8,7 +8,6 @@ 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,

searx/engines/pexels.py

@@ -8,12 +8,11 @@ from urllib.parse import urlencode
 from lxml import html
 
 from searx.result_types import EngineResults
-from searx.utils import eval_xpath_list, gen_useragent
+from searx.utils import eval_xpath_list
 from searx.enginelib import EngineCache
 from searx.exceptions import SearxEngineAPIException, SearxEngineAccessDeniedException
 from searx.network import get
 
-
 # about
 about = {
     "website": 'https://www.pexels.com',
@@ -44,8 +43,6 @@ SECRET_KEY_DB_KEY = "secret-key"
 CACHE: EngineCache
 """Cache to store the secret API key for the engine."""
 
-enable_http2 = False
-
 
 def setup(engine_settings: dict[str, t.Any]) -> bool:
     global CACHE  # pylint: disable=global-statement
@@ -56,13 +53,7 @@ def setup(engine_settings: dict[str, t.Any]) -> bool:
 def _get_secret_key():
     resp = get(
         base_url,
-        headers={
+        headers={"Referer": base_url},
-            # circumvents Cloudflare bot protections
-            "User-Agent": gen_useragent(),
-            "Referer": base_url,
-            "Sec-GPC": "1",
-            "Connection": "keep-alive",
-        },
     )
 
     if resp.status_code != 200:
@@ -105,8 +96,6 @@ def request(query, params):
 
     params["headers"]["secret-key"] = secret_key
 
-    return params
-
 
 def response(resp):
     res = EngineResults()

searx/engines/pinterest.py

@@ -2,72 +2,85 @@
 """Pinterest (images)"""
 
 from json import dumps
+import typing as t
+from searx.result_types import EngineResults
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
 
 about = {
-    "website": 'https://www.pinterest.com/',
+    "website": "https://www.pinterest.com/",
-    "wikidata_id": 'Q255381',
+    "wikidata_id": "Q255381",
-    "official_api_documentation": 'https://developers.pinterest.com/docs/api/v5/',
+    "official_api_documentation": "https://developers.pinterest.com/docs/api/v5/",
     "use_official_api": False,
     "require_api_key": False,
-    "results": 'JSON',
+    "results": "JSON",
 }
 
-categories = ['images']
+categories = ["images"]
 paging = True
 
-base_url = 'https://www.pinterest.com'
+base_url = "https://www.pinterest.com"
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams") -> None:
+
     args = {
-        'options': {
+        "options": {
-            'query': query,
+            "query": query,
-            'bookmarks': [params['engine_data'].get('bookmark', '')],
+            "bookmarks": [params["engine_data"].get("bookmark", "")],
         },
-        'context': {},
+        "context": {},
     }
-    params['url'] = f"{base_url}/resource/BaseSearchResource/get/?data={dumps(args)}"
+    params["url"] = f"{base_url}/resource/BaseSearchResource/get/?data={dumps(args)}"
-    params['headers'] = {
+    params["headers"] = {
-        'X-Pinterest-AppState': 'active',
+        "X-Requested-With": "XMLHttpRequest",
-        'X-Pinterest-Source-Url': '/ideas/',
+        "X-Pinterest-AppState": "active",
-        'X-Pinterest-PWS-Handler': 'www/ideas.js',
+        "X-Pinterest-Source-Url": "/ideas/",
+        "X-Pinterest-PWS-Handler": "www/ideas.js",
     }
 
-    return params
 
+def response(resp: "SXNG_Response") -> EngineResults:
+    res = EngineResults()
+    json_resp: dict[str, t.Any] = resp.json()  # type: ignore
 
-def response(resp):
+    res.add(
-    results = []
-
-    json_resp = resp.json()
-
-    results.append(
         {
-            'engine_data': json_resp['resource_response']['bookmark'],
+            "engine_data": json_resp["resource_response"]["bookmark"],
             # it's called bookmark by pinterest, but it's rather a nextpage
             # parameter to get the next results
-            'key': 'bookmark',
+            "key": "bookmark",
         }
     )
 
-    for result in json_resp['resource_response']['data']['results']:
+    for result in json_resp["resource_response"]["data"]["results"]:
 
-        if result['type'] == 'story':
+        if result["type"] == "story":
             continue
 
-        main_image = result['images']['orig']
+        main_image = result["images"]["orig"]
-        results.append(
+
-            {
+        title = result.get("title") or result.get("grid_title") or ""
-                'template': 'images.html',
+        if len(title) < 5:
-                'url': result.get('link') or f"{base_url}/pin/{result['id']}/",
+            visual_annotation = result.get("pin_join", {}).get("visual_annotation")
-                'title': result.get('title') or result.get('grid_title'),
+            if visual_annotation:
-                'content': (result.get('rich_summary') or {}).get('display_description') or "",
+                title = visual_annotation[0]
-                'img_src': main_image['url'],
+            else:
-                'thumbnail_src': result['images']['236x']['url'],
+                title = result.get("name") or result.get("auto_alt_text") or ""
-                'source': (result.get('rich_summary') or {}).get('site_name'),
+
-                'resolution': f"{main_image['width']}x{main_image['height']}",
+        res.add(
-                'author': f"{result['pinner'].get('full_name')} ({result['pinner']['username']})",
+            res.types.Image(
-            }
+                url=result.get("link") or f"{base_url}/pin/{result['id']}/",
+                title=title,
+                content=(result.get("rich_summary") or {}).get("display_description") or "",
+                img_src=main_image["url"],
+                thumbnail_src=result["images"]["236x"]["url"],
+                source=(result.get("rich_summary") or {}).get("site_name") or "",
+                resolution=f"{main_image['width']}x{main_image['height']}",
+                author=f"{result['pinner'].get('full_name')} ({result['pinner']['username']})",
+            )
         )
 
-    return results
+    return res

searx/engines/piped.py

@@ -48,7 +48,6 @@ Implementations
 
 """
 
-
 import time
 import random
 from urllib.parse import urlencode

searx/engines/pixabay.py

@@ -27,9 +27,6 @@ time_range_support = True
 safesearch_map = {0: 'off', 1: '1', 2: '1'}
 time_range_map = {'day': '1d', 'week': '1w', 'month': '1m', 'year': '1y'}
 
-# using http2 returns forbidden errors
-enable_http2 = False
-
 
 def request(query, params):
     args = {
@@ -50,8 +47,6 @@ def request(query, params):
     # prevent automatic redirects to first page on pagination
     params['allow_redirects'] = False
 
-    return params
-
 
 def _image_result(result):
     return {

searx/engines/privacywall.py

@@ -18,7 +18,6 @@ from searx.utils import eval_xpath_list, eval_xpath, extract_text, extr
 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

searx/engines/recoll.py

@@ -35,6 +35,7 @@ Implementations
 ===============
 
 """
+
 import typing as t
 
 from datetime import date, timedelta

searx/engines/resulthunter.py

@@ -10,6 +10,7 @@ from urllib.parse import urlencode
 from lxml import html
 
 from searx import locales
+from searx.exceptions import SearxEngineResponseException
 from searx.result_types import EngineResults
 from searx.utils import eval_xpath_list, eval_xpath, extract_text
 
@@ -52,6 +53,7 @@ def request(query: str, params: "OnlineParams") -> None:
         "q": query,
         "search_type": resulthunter_categ,
         "offset": params["pageno"] - 1,
+        "search_source": "other",
     }
 
     # uses Brave's engine traits
@@ -111,6 +113,11 @@ def _image_results(doc: "ElementBase") -> EngineResults:
 def response(resp: "SXNG_Response") -> EngineResults:
     doc = html.fromstring(resp.text)
 
+    # if the request was wrong (e.g. missing params), the site doesn't contain a result container
+    # and instead shows an "Installation required" page to download the resulthunter browser extension
+    if not eval_xpath(doc, "//div[contains(@class, 'organic-results-container')]"):
+        raise SearxEngineResponseException()
+
     match resulthunter_categ:
         case "web":
             return _general_results(doc)

searx/engines/s1search_rampjs.py

@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""JavaScript-based s1search implementation. See :ref:`s1search engine`.
+
+Works for all s1search sites that contain the ``__RAMPJS__`` JavaScript variable.
+"""
+
+import json
+import typing as t
+from urllib.parse import urlencode
+
+from searx.result_types import EngineResults
+from searx.utils import extr, html_to_text
+
+if t.TYPE_CHECKING:
+    from searx.search.processors import OnlineParams
+    from searx.extended_types import SXNG_Response
+
+about = {
+    "website": "https://s1search.co",
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+categories = ["general"]
+paging = True
+
+base_url = "https://search.answers.com"
+# other working base URLs:
+# - https://search.nation.online
+# - https://search.activebeat.com
+# - https://search.legalboulevard.com
+# - https://search.walletgenius.com
+# - https://search.legalboulevard.com
+
+
+def request(query: str, params: "OnlineParams"):
+    args = {"q": query, "page": params["pageno"]}
+    params["url"] = f"{base_url}/?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    res = EngineResults()
+
+    data_raw = extr(resp.text, "response: ", " };")
+    data = json.loads(data_raw)
+
+    mainline = [s for s in data["search"]["regions"] if s["name"] == "mainline"][0]
+    for group in mainline["groups"]:
+        for result in group["results"]:
+            if not ("url" in result or "clickUrl" in result):
+                continue
+
+            res.add(
+                res.types.MainResult(
+                    url=result.get("url") or result.get("clickUrl"),
+                    title=html_to_text(result["title"]),
+                    content=html_to_text(result["description"]),
+                )
+            )
+
+    return res

searx/engines/searchrockit.py

@@ -0,0 +1,88 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""SearchRockit is an American search engine. It allegedly has its own index,
+but the results seem to come from Google."""
+
+import typing as t
+from urllib.parse import urlencode
+from lxml import html
+from dateutil import parser
+
+from searx.result_types import EngineResults
+from searx.utils import (
+    eval_xpath_list,
+    extract_text,
+    eval_xpath,
+)
+
+if t.TYPE_CHECKING:
+    from searx.search.processors import OnlineParams
+    from searx.extended_types import SXNG_Response
+
+about = {
+    "website": "https://searchrockit.com",
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "HTML",
+}
+
+categories = ["general"]
+paging = True
+
+SearchrockitCateg = t.Literal["web", "images", "news"]
+searchrockit_categ: SearchrockitCateg = "web"
+
+base_url = "https://searchrockit.com"
+
+
+def setup(_):
+    if searchrockit_categ not in t.get_args(SearchrockitCateg):
+        raise ValueError("invalid search category: %s" % searchrockit_categ)
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    args = {"q": query, "p": params["pageno"]}
+    params["url"] = f"{base_url}/results/{searchrockit_categ}?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    doc = html.fromstring(resp.text)
+    res = EngineResults()
+
+    match searchrockit_categ:
+        case "web" | "news":
+            for result in eval_xpath_list(
+                doc, "//div[contains(@class, 'results-list')]/div[contains(@class, 'result-item')]"
+            ):
+                publishedDate = None
+                try:
+                    d = extract_text(eval_xpath(result, ".//span[contains(@class, 'result-item--publishedAt')]")) or ""
+                    publishedDate = parser.parse(d)
+                except parser.ParserError:
+                    pass
+                res.add(
+                    res.types.MainResult(
+                        url=extract_text(eval_xpath(result, ".//a[contains(@class, 'result-item--title')]/@href")),
+                        title=extract_text(eval_xpath(result, ".//a[contains(@class, 'result-item--title')]")) or "",
+                        content=extract_text(eval_xpath(result, ".//a[contains(@class, 'result-item--desc')]")) or "",
+                        thumbnail=extract_text(
+                            eval_xpath(result, ".//a[contains(@class, 'result-item--thumb')]/img/@src")
+                        )
+                        or "",
+                        publishedDate=publishedDate,
+                    )
+                )
+        case "images":
+            for result in eval_xpath_list(
+                doc, "//div[contains(@class, 'image-grid')]/a[contains(@class, 'image-card')]"
+            ):
+                res.add(
+                    res.types.Image(
+                        url=extract_text(eval_xpath(result, "./@href")),
+                        title=extract_text(eval_xpath(result, "./div[contains(@class, 'image-title')]")) or "",
+                        thumbnail_src=extract_text(eval_xpath(result, "./img/@src")) or "",
+                        img_src=extract_text(eval_xpath(result, "./@data-full-url")) or "",
+                    )
+                )
+
+    return res

searx/engines/searchzee.py

@@ -4,13 +4,11 @@ independent search infrastructure."""
 
 import typing as t
 from urllib.parse import urlencode
+import uuid
 
-from searx.exceptions import SearxEngineAPIException
 from searx.extended_types import SXNG_Response
-from searx.network import get
 from searx.result_types import EngineResults
-from searx.utils import extr, html_to_text
+from searx.utils import html_to_text
-from searx.enginelib import EngineCache
 
 if t.TYPE_CHECKING:
     from searx.search.processors import OnlineParams
@@ -34,43 +32,19 @@ SearchzeeCategType = t.Literal["web", "news"]
 searchzee_categ: SearchzeeCategType = None  # type: ignore[reportAssignmentType]
 
 
-CACHE: EngineCache
-"""Cache for storing the scraped API Token."""
-
 base_url = "https://searchzee.com"
 
 # only supports for news
 time_range_map = {"day": "pd", "week": "pw", "month": "pm", "year": "py"}
 
 
-def setup(engine_settings: dict[str, t.Any]) -> bool:
+def setup(_: dict[str, t.Any]):
     if searchzee_categ not in t.get_args(SearchzeeCategType):
         raise ValueError("invalid category: %s" % searchzee_categ)
 
-    global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])  # type: ignore[reportAny]
-    return True
-
-
-def _obtain_api_token() -> str:
-    token: str | None = CACHE.get("token")  # type: ignore[reportAny]
-    if token:
-        return token
-
-    token_resp = get(
-        f"{base_url}/app.js",
-    )
-    if not token_resp.ok:
-        raise SearxEngineAPIException("failed to obtain api key")
-
-    token = extr(token_resp.text, "const SEARCHZEE_API_TOKEN = \"", "\";")
-    CACHE.set("token", token, expire=3600)
-
-    return token
-
 
 def request(query: str, params: "OnlineParams"):
-    params["headers"]["X-SearchZee-Token"] = _obtain_api_token()
+    params["cookies"]["szs"] = str(uuid.uuid4())
 
     args = {"q": query, "type": searchzee_categ, "offset": params["pageno"] - 1}
     if params["time_range"]:

searx/engines/searx_engine.py

@@ -1,57 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""
-Searx (all)
-"""
-
-from json import loads
-from searx.engines import categories as searx_categories
-
-# about
-about = {
-    "website": 'https://github.com/searxng/searxng',
-    "wikidata_id": 'Q17639196',
-    "official_api_documentation": 'https://docs.searxng.org/dev/search_api.html',
-    "use_official_api": True,
-    "require_api_key": False,
-    "results": 'JSON',
-}
-
-categories = searx_categories.keys()
-
-# search-url
-instance_urls = []
-instance_index = 0
-
-
-# do search-request
-def request(query, params):
-    global instance_index  # pylint: disable=global-statement
-    params['url'] = instance_urls[instance_index % len(instance_urls)]
-    params['method'] = 'POST'
-
-    instance_index += 1
-
-    params['data'] = {
-        'q': query,
-        'pageno': params['pageno'],
-        'language': params['language'],
-        'time_range': params['time_range'],
-        'category': params['category'],
-        'format': 'json',
-    }
-
-    return params
-
-
-# get response from search-request
-def response(resp):
-
-    response_json = loads(resp.text)
-    results = response_json['results']
-
-    for i in ('answers', 'infoboxes'):
-        results.extend(response_json[i])
-
-    results.extend({'suggestion': s} for s in response_json['suggestions'])
-
-    return results

searx/engines/solr.py

@@ -34,7 +34,6 @@ 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

searx/engines/soundcloud.py

@@ -118,7 +118,7 @@ def response(resp):
 
 def setup(engine_settings: dict[str, t.Any]) -> bool:
     global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])  # type:ignore
+    CACHE = EngineCache(engine_settings["name"])  # type: ignore
     return True
 
 

searx/engines/sqlite.py

@@ -44,6 +44,7 @@ Implementations
 ===============
 
 """
+
 import typing as t
 import sqlite3
 import contextlib

searx/engines/startpage.py

@@ -1,5 +1,8 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""Startpage's language & region selectors are a mess ..
+"""Startpage requires solving an Anubis POW captcha (difficulty 4).
+Solving it requires a lot of CPU, so the engine is set inactive by default.
+
+Startpage's language & region selectors are a mess ..
 
 .. _startpage regions:
 
@@ -82,8 +85,10 @@ Startpage's category (for Web-search, News, Videos, ..) is set by
   Supported categories are ``web``, ``news`` and ``images``.
 
 """
+
 # pylint: disable=too-many-statements
 
+import hashlib
 import re
 import typing as t
 from collections import OrderedDict
@@ -99,7 +104,7 @@ from searx.enginelib import EngineCache
 from searx.enginelib.traits import EngineTraits
 from searx.exceptions import SearxEngineCaptchaException
 from searx.locales import region_tag
-from searx.network import get  # see https://github.com/searxng/searxng/issues/762
+from searx.network import get, post  # see https://github.com/searxng/searxng/issues/762
 from searx.utils import (
     eval_xpath,
     extr,
@@ -176,6 +181,45 @@ def setup(_: dict[str, t.Any]) -> bool | None:
 sc_code_cache_sec = 3600
 """Time in seconds the sc-code is cached in memory :py:obj:`get_sc_code`."""
 
+# startpage's anubis difficulty is set to 4
+max_difficulty = 4
+
+
+def _solve_anubis(resp) -> str:
+    """Anubis POW solver"""
+    payload = loads(extr(resp.text, '<script id="anubis_challenge" type="application/json">', "</script>"))
+    challenge = payload["challenge"]
+    difficulty = int(payload["rules"]["difficulty"])
+    if difficulty > max_difficulty:
+        raise SearxEngineCaptchaException(message="startpage: Anubis difficulty too high")
+    prefix = "0" * difficulty
+    blob = challenge["randomData"].encode()
+    for nonce in range(16**difficulty * 8):  # max search is 8x average search, e^-8 = 0.034% will fail
+        digest = hashlib.sha256(blob + str(nonce).encode()).hexdigest()
+        if digest.startswith(prefix):
+            break
+    else:
+        raise SearxEngineCaptchaException(message="startpage: Anubis failed")
+
+    pass_resp = get(
+        f"{base_url}/.within.website/x/cmd/anubis/api/pass-challenge",
+        params={
+            "id": challenge["id"],
+            "response": digest,
+            "nonce": nonce,
+            "redir": str(resp.url),
+            "elapsedTime": "1",
+        },
+        cookies=resp.cookies,
+        allow_redirects=False,
+    )
+    auth = pass_resp.cookies.get("spchal-auth")
+    if not auth:
+        raise SearxEngineCaptchaException(message="startpage: Anubis pass-challenge failed")
+    auth = str(auth)
+    CACHE.set("SPCHAL_AUTH", auth, expire=240)
+    return auth
+
 
 def get_sc_code(params):
     """Get an actual ``sc`` argument from Startpage's search form (HTML page).
@@ -201,6 +245,9 @@ def get_sc_code(params):
     logger.debug("get_sc_code: request headers: %s", headers)
     resp = get(get_sc_url, headers=headers)
 
+    if 'id="anubis_challenge"' in resp.text:
+        resp = get(get_sc_url, headers=headers, cookies={"spchal-auth": _solve_anubis(resp)})
+
     # ?? x = network.get('https://www.startpage.com/sp/cdn/images/filter-chevron.svg', headers=headers)
     # ?? https://www.startpage.com/sp/cdn/images/filter-chevron.svg
     # ?? ping-back URL: https://www.startpage.com/sp/pb?sc=TLsB0oITjZ8F21
@@ -239,8 +286,8 @@ def request(query, params):
     Additionally the arguments form Startpage's search form needs to be set in
     HTML POST data / compare ``<input>`` elements: :py:obj:`search_form_xpath`.
     """
-    engine_region = traits.get_region(params["searxng_locale"], "en-US")
+    engine_region = traits.get_region(params["searxng_locale"], "en_US")
-    engine_language = traits.get_language(params["searxng_locale"], "en")
+    engine_language = traits.get_language(params["searxng_locale"], "english")
 
     params["headers"]["Origin"] = base_url
     params["headers"]["Referer"] = base_url + "/"
@@ -262,9 +309,9 @@ def request(query, params):
         args["language"] = engine_language
         args["lui"] = engine_language
 
+    args["segment"] = "startpage.udog"
     if params["pageno"] > 1:
         args["page"] = params["pageno"]
-        args["segment"] = "startpage.udog"
 
     # Build cookie
     lang_homepage = "en"
@@ -289,6 +336,8 @@ def request(query, params):
         cookie["search_results_region"] = engine_region
 
     params["cookies"]["preferences"] = "N1N".join(["%sEEE%s" % x for x in cookie.items()])
+    if auth := CACHE.get("SPCHAL_AUTH"):
+        params["cookies"]["spchal-auth"] = auth
     logger.debug("cookie preferences: %s", params["cookies"]["preferences"])
 
     logger.debug("data: %s", args)
@@ -400,6 +449,18 @@ def _get_image_result(result) -> dict[str, t.Any] | None:
 
 
 def response(resp):
+    if 'id="anubis_challenge"' in resp.text:
+        params = resp.search_params
+        params["cookies"]["spchal-auth"] = _solve_anubis(resp)
+        resp = post(
+            params["url"] or search_url,
+            data=params["data"],
+            headers=params["headers"],
+            cookies=params["cookies"],
+        )
+        if 'id="anubis_challenge"' in resp.text:
+            raise SearxEngineCaptchaException()
+
     categ = startpage_categ.capitalize()
     results_raw = "{" + extr(resp.text, f"React.createElement(UIStartpage.AppSerp{categ}, {{", "}})") + "}}"
 

searx/engines/stocksnap.py

@@ -21,8 +21,6 @@ about = {
     "require_api_key": False,
     "results": "JSON",
 }
-# otherwise all requests get blocked, probably HTTP2 fingerprinting
-enable_http2 = False
 
 base_url = "https://stocksnap.io"
 cdn_url = "https://cdn.stocksnap.io"

searx/engines/tubearchivist.py

@@ -74,7 +74,6 @@ Implementations
 ===============
 """
 
-
 import typing as t
 from urllib.parse import urlencode
 from dateutil.parser import parse

searx/engines/tusksearch.py

@@ -13,7 +13,7 @@ from dateutil import parser
 
 from searx.exceptions import SearxEngineAPIException
 from searx.network import get
-from searx.utils import gen_useragent, html_to_text
+from searx.utils import html_to_text
 from searx.result_types import EngineResults
 
 if t.TYPE_CHECKING:
@@ -52,7 +52,7 @@ def _obtain_x_sid() -> tuple[str, str]:
     The header key is usually called `x-sid-{UUIDv4}`, and the value is
     usually a plain UUIDv4 (but a different one than in the header key).
     """
-    resp = get(f"{api_url}/revcontent/embed.js", headers={"User-Agent": gen_useragent()})
+    resp = get(f"{api_url}/revcontent/embed.js", headers={"Referer": "https://tusksearch.com/"})
     if not resp.ok:
         raise SearxEngineAPIException("failed to obtain request x-sid token")
 
@@ -95,6 +95,7 @@ def request(query: str, params: "OnlineParams") -> None:
             # required - we send a random longitude and latitude instead of the actual user location
             "x-lon": str(round(random.random() * 90, 4)),
             "x-lat": str(round(random.random() * 90, 4)),
+            "Referer": "https://tusksearch.com/",
         }
     )
 

searx/engines/uxwing.py

@@ -17,12 +17,10 @@ about = {
 categories = ['images', 'icons']
 
 base_url = "https://uxwing.com"
-enable_http2 = False
 
 
 def request(query, params):
     params['url'] = f"{base_url}/?s={quote_plus(query)}"
-    return params
 
 
 def response(resp):

searx/engines/vuhuv.py

@@ -12,7 +12,6 @@ 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

searx/engines/wikidata.py

@@ -3,6 +3,7 @@
 
 Some implementations are shared from :ref:`wikipedia engine`.
 """
+
 # pylint: disable=missing-class-docstring
 
 import typing as t

searx/engines/wolframalpha_noapi.py

@@ -53,7 +53,7 @@ seconds."""
 
 def setup(engine_settings: dict[str, t.Any]) -> bool | None:
     global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])  # type:ignore
+    CACHE = EngineCache(engine_settings["name"])  # type: ignore
 
 
 def obtain_token() -> str:

searx/engines/yacy.py

@@ -50,6 +50,7 @@ the engine).
 Implementations
 ===============
 """
+
 # pylint: disable=fixme
 
 import typing as t
@@ -58,7 +59,7 @@ from json import loads
 from urllib.parse import urlencode
 from dateutil import parser
 
-from httpx import DigestAuth
+from curl_cffi import CurlOpt
 
 from searx.utils import html_to_text
 
@@ -141,7 +142,10 @@ def request(query, params):
     params["url"] = f"{_base_url()}/yacysearch.json?{urlencode(args)}"
 
     if http_digest_auth_user and http_digest_auth_pass:
-        params['auth'] = DigestAuth(http_digest_auth_user, http_digest_auth_pass)
+        params['curl_options'] = {
+            CurlOpt.HTTPAUTH: 2,  # CURLAUTH_DIGEST
+            CurlOpt.USERPWD: f"{http_digest_auth_user}:{http_digest_auth_pass}",
+        }
 
     return params
 

searx/engines/yandex.py

@@ -8,7 +8,6 @@ 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/',
@@ -22,6 +21,7 @@ about = {
 # Engine configuration
 categories = []
 paging = True
+enable_http3 = True
 search_type = ""
 
 # Search URL

searx/engines/yandex_api.py

@@ -77,10 +77,10 @@ notifications, but only as a fallback -- a request whose own locale matches
 ``kk``, ``uk``, ``tr`` or ``en``."""
 
 region: str = ""
-"""Optional Yandex `region id`.
+"""Optional Yandex `region id`_.
 Only meaningful together with ``SEARCH_TYPE_RU``.
 
-__ https://aistudio.yandex.ru/docs/en/search-api/reference/regions.html
+.. _region id: https://aistudio.yandex.ru/docs/en/search-api/reference/regions.html
 """
 
 page_size: int = 10

searx/engines/yep.py

@@ -30,8 +30,6 @@ web_base_url = "https://yep.com"
 safesearch = True
 safesearch_map = {0: "off", 1: "moderate", 2: "strict"}
 
-enable_http2 = False
-
 results_per_page = 20
 
 _IMPORT_RE = re.compile(r"import\"(.*?)\";")
@@ -50,9 +48,6 @@ def request(query: str, params: "OnlineParams") -> None:
         {
             "Referer": f"{web_base_url}/",
             "Origin": web_base_url,
-            "Sec-Fetch-Dest": "empty",
-            "Sec-Fetch-Mode": "cors",
-            "Sec-Fetch-Site": "same-site",
         }
     )
 

searx/engines/youtube_api.py

@@ -22,6 +22,7 @@ about = {
 # engine dependent config
 categories = ['videos', 'music']
 paging = False
+enable_http3 = True
 api_key = None
 
 # search-url

searx/engines/youtube_noapi.py

@@ -20,6 +20,7 @@ about = {
 # engine dependent config
 categories = ['videos', 'music']
 paging = True
+enable_http3 = True
 language_support = False
 time_range_support = True
 

searx/extended_types.py

@@ -3,7 +3,7 @@
 
 - :py:obj:`flask.request` is replaced by :py:obj:`sxng_request`
 - :py:obj:`flask.Request` is replaced by :py:obj:`SXNG_Request`
-- :py:obj:`httpx.response` is replaced by :py:obj:`SXNG_Response`
+- :py:obj:`curl_cffi.requests.Response` is replaced by :py:obj:`SXNG_Response`
 
 ----
 
@@ -19,13 +19,16 @@
    :members:
 
 """
+
 # pylint: disable=invalid-name
 
 __all__ = ["SXNG_Request", "sxng_request", "SXNG_Response"]
 
 import typing
+from urllib.parse import urlsplit
+
 import flask
-import httpx
+from curl_cffi.requests import Response as CurlResponse
 
 if typing.TYPE_CHECKING:
     import searx.preferences
@@ -69,18 +72,37 @@ class SXNG_Request(flask.Request):
 sxng_request = typing.cast(SXNG_Request, flask.request)
 
 
-class SXNG_Response(httpx.Response):
+class SXNG_URL(str):
-    """SearXNG extends the class :py:obj:`httpx.Response` with properties from
+    """String URL"""
-    *this* class (type cast of :py:obj:`httpx.Response`).
+
+    @property
+    def host(self) -> str | None:
+        return urlsplit(self).hostname
+
+    @property
+    def path(self) -> str:
+        return urlsplit(self).path
+
+
+class SXNG_Response(CurlResponse):
+    """SearXNG extends :py:obj:`curl_cffi.requests.Response` with properties from
+    *this* class (type cast of the curl_cffi response).
 
     .. code:: python
 
-       response = httpx.get("https://example.org")
        response = typing.cast(SXNG_Response, response)
        if response.ok:
           ...
        query_was = search_params["query"]
     """
 
-    ok: bool
     search_params: "OnlineParamTypes | OnlineDictParams | OnlineCurrenciesParams"
+    _url: str = ""
+
+    @property
+    def url(self) -> SXNG_URL:  # type: ignore[override]
+        return SXNG_URL(self._url)
+
+    @url.setter
+    def url(self, value: str) -> None:
+        self._url = str(value or "")