[data] update searx.data - update_engine_traits.py

Bumps [docker/scout-action](https://github.com/docker/scout-action) from 1.21.0 to 1.22.0.
- [Release notes](https://github.com/docker/scout-action/releases)
- [Commits](cd72f264be...7520205ff6)

---
updated-dependencies:
- dependency-name: docker/scout-action
  dependency-version: 1.22.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.github/workflows/container.yml

@@ -73,18 +73,18 @@ jobs:
       # yamllint enable rule:line-length
 
       - name: Setup Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
           fetch-depth: "0"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -96,7 +96,7 @@ jobs:
         run: echo "date=$(date +'%Y%m%d')" >>$GITHUB_OUTPUT
 
       - name: Setup cache container
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "container-${{ matrix.arch }}-${{ steps.date.outputs.date }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -141,7 +141,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
 
@@ -175,7 +175,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
 

.github/workflows/data-update.yml

@@ -41,17 +41,17 @@ jobs:
 
     steps:
       - name: Setup Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |

.github/workflows/documentation.yml

@@ -32,18 +32,18 @@ jobs:
 
     steps:
       - name: Setup Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
           fetch-depth: "0"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |

.github/workflows/integration.yml

@@ -34,17 +34,17 @@ jobs:
 
     steps:
       - name: Setup Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: "${{ matrix.python-version }}"
 
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "python-${{ matrix.python-version }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -62,12 +62,12 @@ jobs:
     runs-on: ubuntu-24.04-arm
     steps:
       - name: Setup Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
 
@@ -77,13 +77,13 @@ jobs:
           node-version-file: "./.nvmrc"
 
       - name: Setup cache Node.js
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "nodejs-${{ runner.arch }}-${{ hashFiles('./.nvmrc', './package.json') }}"
           path: "./client/simple/node_modules/"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |

.github/workflows/l10n.yml

@@ -35,18 +35,18 @@ jobs:
 
     steps:
       - name: Setup Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           token: "${{ secrets.WEBLATE_GITHUB_TOKEN }}"
           fetch-depth: "0"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -83,18 +83,18 @@ jobs:
 
     steps:
       - name: Setup Python
-        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6.2.0
+        uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           token: "${{ secrets.WEBLATE_GITHUB_TOKEN }}"
           fetch-depth: "0"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8  # v6.0.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |

.github/workflows/security.yml

@@ -24,12 +24,12 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
 
       - name: Sync GHCS from Docker Scout
-        uses: docker/scout-action@cd72f264beff1cd72735de31148b9d3244a0234a  # v1.21.0
+        uses: docker/scout-action@7520205ff60037fdc436b40b6a1d1e55a839ec2d  # v1.22.0
         with:
           organization: "searxng"
           dockerhub-user: "${{ secrets.DOCKER_USER }}"

client/simple/package-lock.json

@@ -16,11 +16,11 @@
       },
       "devDependencies": {
         "@biomejs/biome": "2.5.0",
-        "@types/node": "^25.9.3",
+        "@types/node": "^26.0.0",
         "browserslist": "^4.28.2",
         "browserslist-to-esbuild": "^2.1.1",
         "edge.js": "^6.5.1",
-        "less": "^4.6.4",
+        "less": "^4.6.6",
         "mathjs": "^15.2.0",
         "sharp": "~0.35.1",
         "sort-package-json": "^4.0.0",
@@ -1570,13 +1570,13 @@
       }
     },
     "node_modules/@types/node": {
-      "version": "25.9.3",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-25.9.3.tgz",
-      "integrity": "sha512-603BddQMv3pUcr4U2dhujk83N2tTDVr/34wII2B6bJy6g+8WD6yUb11jszNs0gdi4PesVWl7ABt8nYMVpnLUcg==",
+      "version": "26.0.0",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-26.0.0.tgz",
+      "integrity": "sha512-vf2YFi1iY9lHGwNJMs01biZFbKJkrZR1T6/MlzjhJLPdntOHLhTrDSnSVcdtvjihi4VQNlrFRIxLsDBlQpAipA==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "undici-types": ">=7.24.0 <7.24.7"
+        "undici-types": "~8.3.0"
       }
     },
     "node_modules/@types/pluralize": {
@@ -2890,9 +2890,9 @@
       "license": "Apache-2.0"
     },
     "node_modules/less": {
-      "version": "4.6.4",
-      "resolved": "https://registry.npmjs.org/less/-/less-4.6.4.tgz",
-      "integrity": "sha512-OJmO5+HxZLLw0RLzkqaNHzcgEAQG7C0y3aMbwtCzIUFZsLMNNq/1IdAdHEycQ58CwUO3jPTHmoN+tE5I7FQxNg==",
+      "version": "4.6.6",
+      "resolved": "https://registry.npmjs.org/less/-/less-4.6.6.tgz",
+      "integrity": "sha512-ooPSwQGQ2sVe8Dh1jVsbKKsRR2gd8lFK72BDkeSzjnD1T5aIHL65hCMfO0GVmtriKgDKrQv6xp9UrihUsWuAzA==",
       "dev": true,
       "license": "Apache-2.0",
       "dependencies": {
@@ -2909,7 +2909,7 @@
         "errno": "^0.1.1",
         "graceful-fs": "^4.1.2",
         "image-size": "~0.5.0",
-        "make-dir": "^2.1.0",
+        "make-dir": "^5.1.0",
         "mime": "^1.4.1",
         "needle": "^3.1.0",
         "source-map": "~0.6.0"
@@ -3191,18 +3191,17 @@
       "license": "MIT"
     },
     "node_modules/make-dir": {
-      "version": "2.1.0",
-      "resolved": "https://registry.npmjs.org/make-dir/-/make-dir-2.1.0.tgz",
-      "integrity": "sha512-LS9X+dc8KLxXCb8dni79fLIIUA5VyZoyjSMCwTluaXA0o27cCK0bhXkpgw+sTXVpPy/lSO57ilRixqk0vDmtRA==",
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/make-dir/-/make-dir-5.1.0.tgz",
+      "integrity": "sha512-IfpFq6UM39dUNiphpA6uDezNx/AvWyhwfICWPR3t1VspkgkMZrL+Rk1RbN1bx+aeNYwOrqGJgEgV3yotk+ZUVw==",
       "dev": true,
       "license": "MIT",
       "optional": true,
-      "dependencies": {
-        "pify": "^4.0.1",
-        "semver": "^5.6.0"
-      },
       "engines": {
-        "node": ">=6"
+        "node": ">=18"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
       }
     },
     "node_modules/mathjs": {
@@ -3491,17 +3490,6 @@
         "url": "https://github.com/sponsors/jonschlinkert"
       }
     },
-    "node_modules/pify": {
-      "version": "4.0.1",
-      "resolved": "https://registry.npmjs.org/pify/-/pify-4.0.1.tgz",
-      "integrity": "sha512-uB80kBFb/tfd68bVleG9T5GGsGPjJrLAUpR5PZIrhBnIaRTQRjqdJSsIKkOP6OAIFbj7GOrcudc5pNjZ+geV2g==",
-      "dev": true,
-      "license": "MIT",
-      "optional": true,
-      "engines": {
-        "node": ">=6"
-      }
-    },
     "node_modules/pluralize": {
       "version": "8.0.0",
       "resolved": "https://registry.npmjs.org/pluralize/-/pluralize-8.0.0.tgz",
@@ -3861,17 +3849,6 @@
       "dev": true,
       "license": "MIT"
     },
-    "node_modules/semver": {
-      "version": "5.7.2",
-      "resolved": "https://registry.npmjs.org/semver/-/semver-5.7.2.tgz",
-      "integrity": "sha512-cBznnQ9KjJqU67B52RMC65CMarK2600WFnbkcaiwWq3xy/5haFJlshgnpjovMVJ+Hff49d8GEn0b87C5pDQ10g==",
-      "dev": true,
-      "license": "ISC",
-      "optional": true,
-      "bin": {
-        "semver": "bin/semver"
-      }
-    },
     "node_modules/sharp": {
       "version": "0.35.1",
       "resolved": "https://registry.npmjs.org/sharp/-/sharp-0.35.1.tgz",
@@ -4515,9 +4492,9 @@
       }
     },
     "node_modules/undici-types": {
-      "version": "7.24.6",
-      "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-7.24.6.tgz",
-      "integrity": "sha512-WRNW+sJgj5OBN4/0JpHFqtqzhpbnV0GuB+OozA9gCL7a993SmU+1JBZCzLNxYsbMfIeDL+lTsphD5jN5N+n0zg==",
+      "version": "8.3.0",
+      "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-8.3.0.tgz",
+      "integrity": "sha512-j375ScV60dom+YkPFIfTLcOiPxkN/buHz5GobjLhixFuANaNs3C9l4GmrWqejgXWJ7BbJcFYpTEUkS1Ge8bpZQ==",
       "dev": true,
       "license": "MIT"
     },

client/simple/package.json

@@ -30,11 +30,11 @@
   },
   "devDependencies": {
     "@biomejs/biome": "2.5.0",
-    "@types/node": "^25.9.3",
+    "@types/node": "^26.0.0",
     "browserslist": "^4.28.2",
     "browserslist-to-esbuild": "^2.1.1",
     "edge.js": "^6.5.1",
-    "less": "^4.6.4",
+    "less": "^4.6.6",
     "mathjs": "^15.2.0",
     "sharp": "~0.35.1",
     "sort-package-json": "^4.0.0",

docs/dev/engines/online/aol.rst

@@ -1,8 +0,0 @@
-.. _aol engine:
-
-===
-AOL
-===
-
-.. automodule:: searx.engines.aol
-   :members:

requirements-dev.txt

@@ -2,16 +2,16 @@ mock==5.2.0
 nose2[coverage_plugin]==0.16.0
 cov-core==1.15.0
 black==25.9.0
-pylint==4.0.5
+pylint==4.0.6
 splinter==0.21.0
-selenium==4.44.0
+selenium==4.45.0
 Sphinx==8.2.3;python_version <= "3.11"
 Sphinx==9.1.0; python_version > "3.11"
 sphinx-issues==6.0.0
 sphinx-jinja==2.0.2
 sphinx-tabs==3.5.0
 furo==2025.12.19
-sphinxcontrib-programoutput==0.19
+sphinxcontrib-programoutput==0.20
 sphinx-autobuild==2025.8.25
 sphinx-notfound-page==1.1.0
 myst-parser==5.0.0
@@ -24,5 +24,5 @@ docutils>=0.21.2;python_version <= "3.11"
 docutils>=0.22.4; python_version > "3.11"
 parameterized==0.9.0
 granian[reload]==2.7.6
-basedpyright==1.39.7
+basedpyright==1.39.8
 types-lxml==2026.2.16

requirements.txt

@@ -1,4 +1,4 @@
-certifi==2026.5.20
+certifi==2026.6.17
 babel==2.18.0
 flask-babel==4.0.0
 flask==3.1.3

searx/data/engine_traits.json

@@ -7165,6 +7165,7 @@
         "IR",
         "IS",
         "IT",
+        "JE",
         "JM",
         "JO",
         "JP",
@@ -7194,6 +7195,7 @@
         "MC",
         "MD",
         "ME",
+        "MF",
         "MG",
         "MH",
         "MK",
@@ -7260,6 +7262,7 @@
         "SS",
         "ST",
         "SV",
+        "SX",
         "SY",
         "SZ",
         "TC",
@@ -7407,6 +7410,7 @@
       "th": "thai",
       "ti": "tigrinya",
       "tk": "turkmen",
+      "to": "tonga",
       "tr": "turkish",
       "tt": "tatar",
       "uk": "ukrainian",
@@ -7687,460 +7691,22 @@
     "all_locale": null,
     "custom": {},
     "data_type": "traits_v1",
-    "languages": {
-      "af": "afrikaans",
-      "am": "amharic",
-      "ar": "arabic",
-      "az": "azerbaijani",
-      "be": "belarusian",
-      "bg": "bulgarian",
-      "bn": "bengali",
-      "bs": "bosnian",
-      "ca": "catalan",
-      "cs": "czech",
-      "cy": "welsh",
-      "da": "dansk",
-      "de": "deutsch",
-      "el": "greek",
-      "en": "english",
-      "eo": "esperanto",
-      "es": "espanol",
-      "et": "estonian",
-      "eu": "basque",
-      "fa": "persian",
-      "fi": "suomi",
-      "fo": "faroese",
-      "fr": "francais",
-      "fy": "frisian",
-      "ga": "irish",
-      "gd": "gaelic",
-      "gl": "galician",
-      "gu": "gujarati",
-      "he": "hebrew",
-      "hi": "hindi",
-      "hr": "croatian",
-      "hu": "hungarian",
-      "ia": "interlingua",
-      "id": "indonesian",
-      "is": "icelandic",
-      "it": "italiano",
-      "ja": "nihongo",
-      "jv": "javanese",
-      "ka": "georgian",
-      "kn": "kannada",
-      "ko": "hangul",
-      "la": "latin",
-      "lt": "lithuanian",
-      "lv": "latvian",
-      "mai": "bihari",
-      "mk": "macedonian",
-      "ml": "malayalam",
-      "mr": "marathi",
-      "ms": "malay",
-      "mt": "maltese",
-      "nb": "norsk",
-      "ne": "nepali",
-      "nl": "nederlands",
-      "oc": "occitan",
-      "pa": "punjabi",
-      "pl": "polski",
-      "pt": "portugues",
-      "pt_BR": "brazilian",
-      "ro": "romanian",
-      "ru": "russian",
-      "si": "sinhalese",
-      "sk": "slovak",
-      "sl": "slovenian",
-      "sq": "albanian",
-      "sr": "serbian",
-      "su": "sudanese",
-      "sv": "svenska",
-      "sw": "swahili",
-      "ta": "tamil",
-      "te": "telugu",
-      "th": "thai",
-      "ti": "tigrinya",
-      "tl": "tagalog",
-      "tr": "turkce",
-      "uk": "ukrainian",
-      "ur": "urdu",
-      "uz": "uzbek",
-      "vi": "vietnamese",
-      "xh": "xhosa",
-      "zh": "jiantizhongwen",
-      "zh_Hant": "fantizhengwen",
-      "zu": "zulu"
-    },
-    "regions": {
-      "ar-EG": "ar_EG",
-      "bg-BG": "bg_BG",
-      "ca-ES": "ca_ES",
-      "cs-CZ": "cs_CZ",
-      "da-DK": "da_DK",
-      "de-AT": "de_AT",
-      "de-CH": "de_CH",
-      "de-DE": "de_DE",
-      "el-GR": "el_GR",
-      "en-AU": "en_AU",
-      "en-CA": "en_CA",
-      "en-GB": "en-GB_GB",
-      "en-ID": "en_ID",
-      "en-IE": "en_IE",
-      "en-IN": "en_IN",
-      "en-MY": "en_MY",
-      "en-NZ": "en_NZ",
-      "en-PH": "en_PH",
-      "en-SG": "en_SG",
-      "en-US": "en_US",
-      "en-ZA": "en_ZA",
-      "es-AR": "es_AR",
-      "es-CL": "es_CL",
-      "es-CO": "es_CO",
-      "es-ES": "es_ES",
-      "es-MX": "es_MX",
-      "es-PE": "es_PE",
-      "es-US": "es_US",
-      "es-UY": "es_UY",
-      "es-VE": "es_VE",
-      "et-EE": "et_EE",
-      "fi-FI": "fi_FI",
-      "fil-PH": "fil_PH",
-      "fr-BE": "fr_BE",
-      "fr-CA": "fr_CA",
-      "fr-CH": "fr_CH",
-      "fr-FR": "fr_FR",
-      "hi-IN": "hi_IN",
-      "hu-HU": "hu_HU",
-      "id-ID": "id_ID",
-      "it-CH": "it_CH",
-      "it-IT": "it_IT",
-      "ja-JP": "ja_JP",
-      "ko-KR": "ko_KR",
-      "ms-MY": "ms_MY",
-      "ms-SG": "ms_SG",
-      "nb-NO": "no_NO",
-      "nl-BE": "nl_BE",
-      "nl-NL": "nl_NL",
-      "pl-PL": "pl_PL",
-      "pt-BR": "pt-BR_BR",
-      "pt-PT": "pt_PT",
-      "ro-RO": "ro_RO",
-      "ru-BY": "ru_BY",
-      "ru-RU": "ru_RU",
-      "sv-SE": "sv_SE",
-      "tr-TR": "tr_TR",
-      "uk-UA": "uk_UA",
-      "vi-VN": "vi_VN",
-      "zh-CN": "zh-CN_CN",
-      "zh-HK": "zh-TW_HK",
-      "zh-TW": "zh-TW_TW"
-    }
+    "languages": {},
+    "regions": {}
   },
   "startpage images": {
     "all_locale": null,
     "custom": {},
     "data_type": "traits_v1",
-    "languages": {
-      "af": "afrikaans",
-      "am": "amharic",
-      "ar": "arabic",
-      "az": "azerbaijani",
-      "be": "belarusian",
-      "bg": "bulgarian",
-      "bn": "bengali",
-      "bs": "bosnian",
-      "ca": "catalan",
-      "cs": "czech",
-      "cy": "welsh",
-      "da": "dansk",
-      "de": "deutsch",
-      "el": "greek",
-      "en": "english",
-      "eo": "esperanto",
-      "es": "espanol",
-      "et": "estonian",
-      "eu": "basque",
-      "fa": "persian",
-      "fi": "suomi",
-      "fo": "faroese",
-      "fr": "francais",
-      "fy": "frisian",
-      "ga": "irish",
-      "gd": "gaelic",
-      "gl": "galician",
-      "gu": "gujarati",
-      "he": "hebrew",
-      "hi": "hindi",
-      "hr": "croatian",
-      "hu": "hungarian",
-      "ia": "interlingua",
-      "id": "indonesian",
-      "is": "icelandic",
-      "it": "italiano",
-      "ja": "nihongo",
-      "jv": "javanese",
-      "ka": "georgian",
-      "kn": "kannada",
-      "ko": "hangul",
-      "la": "latin",
-      "lt": "lithuanian",
-      "lv": "latvian",
-      "mai": "bihari",
-      "mk": "macedonian",
-      "ml": "malayalam",
-      "mr": "marathi",
-      "ms": "malay",
-      "mt": "maltese",
-      "nb": "norsk",
-      "ne": "nepali",
-      "nl": "nederlands",
-      "oc": "occitan",
-      "pa": "punjabi",
-      "pl": "polski",
-      "pt": "portugues",
-      "pt_BR": "brazilian",
-      "ro": "romanian",
-      "ru": "russian",
-      "si": "sinhalese",
-      "sk": "slovak",
-      "sl": "slovenian",
-      "sq": "albanian",
-      "sr": "serbian",
-      "su": "sudanese",
-      "sv": "svenska",
-      "sw": "swahili",
-      "ta": "tamil",
-      "te": "telugu",
-      "th": "thai",
-      "ti": "tigrinya",
-      "tl": "tagalog",
-      "tr": "turkce",
-      "uk": "ukrainian",
-      "ur": "urdu",
-      "uz": "uzbek",
-      "vi": "vietnamese",
-      "xh": "xhosa",
-      "zh": "jiantizhongwen",
-      "zh_Hant": "fantizhengwen",
-      "zu": "zulu"
-    },
-    "regions": {
-      "ar-EG": "ar_EG",
-      "bg-BG": "bg_BG",
-      "ca-ES": "ca_ES",
-      "cs-CZ": "cs_CZ",
-      "da-DK": "da_DK",
-      "de-AT": "de_AT",
-      "de-CH": "de_CH",
-      "de-DE": "de_DE",
-      "el-GR": "el_GR",
-      "en-AU": "en_AU",
-      "en-CA": "en_CA",
-      "en-GB": "en-GB_GB",
-      "en-ID": "en_ID",
-      "en-IE": "en_IE",
-      "en-IN": "en_IN",
-      "en-MY": "en_MY",
-      "en-NZ": "en_NZ",
-      "en-PH": "en_PH",
-      "en-SG": "en_SG",
-      "en-US": "en_US",
-      "en-ZA": "en_ZA",
-      "es-AR": "es_AR",
-      "es-CL": "es_CL",
-      "es-CO": "es_CO",
-      "es-ES": "es_ES",
-      "es-MX": "es_MX",
-      "es-PE": "es_PE",
-      "es-US": "es_US",
-      "es-UY": "es_UY",
-      "es-VE": "es_VE",
-      "et-EE": "et_EE",
-      "fi-FI": "fi_FI",
-      "fil-PH": "fil_PH",
-      "fr-BE": "fr_BE",
-      "fr-CA": "fr_CA",
-      "fr-CH": "fr_CH",
-      "fr-FR": "fr_FR",
-      "hi-IN": "hi_IN",
-      "hu-HU": "hu_HU",
-      "id-ID": "id_ID",
-      "it-CH": "it_CH",
-      "it-IT": "it_IT",
-      "ja-JP": "ja_JP",
-      "ko-KR": "ko_KR",
-      "ms-MY": "ms_MY",
-      "ms-SG": "ms_SG",
-      "nb-NO": "no_NO",
-      "nl-BE": "nl_BE",
-      "nl-NL": "nl_NL",
-      "pl-PL": "pl_PL",
-      "pt-BR": "pt-BR_BR",
-      "pt-PT": "pt_PT",
-      "ro-RO": "ro_RO",
-      "ru-BY": "ru_BY",
-      "ru-RU": "ru_RU",
-      "sv-SE": "sv_SE",
-      "tr-TR": "tr_TR",
-      "uk-UA": "uk_UA",
-      "vi-VN": "vi_VN",
-      "zh-CN": "zh-CN_CN",
-      "zh-HK": "zh-TW_HK",
-      "zh-TW": "zh-TW_TW"
-    }
+    "languages": {},
+    "regions": {}
   },
   "startpage news": {
     "all_locale": null,
     "custom": {},
     "data_type": "traits_v1",
-    "languages": {
-      "af": "afrikaans",
-      "am": "amharic",
-      "ar": "arabic",
-      "az": "azerbaijani",
-      "be": "belarusian",
-      "bg": "bulgarian",
-      "bn": "bengali",
-      "bs": "bosnian",
-      "ca": "catalan",
-      "cs": "czech",
-      "cy": "welsh",
-      "da": "dansk",
-      "de": "deutsch",
-      "el": "greek",
-      "en": "english",
-      "eo": "esperanto",
-      "es": "espanol",
-      "et": "estonian",
-      "eu": "basque",
-      "fa": "persian",
-      "fi": "suomi",
-      "fo": "faroese",
-      "fr": "francais",
-      "fy": "frisian",
-      "ga": "irish",
-      "gd": "gaelic",
-      "gl": "galician",
-      "gu": "gujarati",
-      "he": "hebrew",
-      "hi": "hindi",
-      "hr": "croatian",
-      "hu": "hungarian",
-      "ia": "interlingua",
-      "id": "indonesian",
-      "is": "icelandic",
-      "it": "italiano",
-      "ja": "nihongo",
-      "jv": "javanese",
-      "ka": "georgian",
-      "kn": "kannada",
-      "ko": "hangul",
-      "la": "latin",
-      "lt": "lithuanian",
-      "lv": "latvian",
-      "mai": "bihari",
-      "mk": "macedonian",
-      "ml": "malayalam",
-      "mr": "marathi",
-      "ms": "malay",
-      "mt": "maltese",
-      "nb": "norsk",
-      "ne": "nepali",
-      "nl": "nederlands",
-      "oc": "occitan",
-      "pa": "punjabi",
-      "pl": "polski",
-      "pt": "portugues",
-      "pt_BR": "brazilian",
-      "ro": "romanian",
-      "ru": "russian",
-      "si": "sinhalese",
-      "sk": "slovak",
-      "sl": "slovenian",
-      "sq": "albanian",
-      "sr": "serbian",
-      "su": "sudanese",
-      "sv": "svenska",
-      "sw": "swahili",
-      "ta": "tamil",
-      "te": "telugu",
-      "th": "thai",
-      "ti": "tigrinya",
-      "tl": "tagalog",
-      "tr": "turkce",
-      "uk": "ukrainian",
-      "ur": "urdu",
-      "uz": "uzbek",
-      "vi": "vietnamese",
-      "xh": "xhosa",
-      "zh": "jiantizhongwen",
-      "zh_Hant": "fantizhengwen",
-      "zu": "zulu"
-    },
-    "regions": {
-      "ar-EG": "ar_EG",
-      "bg-BG": "bg_BG",
-      "ca-ES": "ca_ES",
-      "cs-CZ": "cs_CZ",
-      "da-DK": "da_DK",
-      "de-AT": "de_AT",
-      "de-CH": "de_CH",
-      "de-DE": "de_DE",
-      "el-GR": "el_GR",
-      "en-AU": "en_AU",
-      "en-CA": "en_CA",
-      "en-GB": "en-GB_GB",
-      "en-ID": "en_ID",
-      "en-IE": "en_IE",
-      "en-IN": "en_IN",
-      "en-MY": "en_MY",
-      "en-NZ": "en_NZ",
-      "en-PH": "en_PH",
-      "en-SG": "en_SG",
-      "en-US": "en_US",
-      "en-ZA": "en_ZA",
-      "es-AR": "es_AR",
-      "es-CL": "es_CL",
-      "es-CO": "es_CO",
-      "es-ES": "es_ES",
-      "es-MX": "es_MX",
-      "es-PE": "es_PE",
-      "es-US": "es_US",
-      "es-UY": "es_UY",
-      "es-VE": "es_VE",
-      "et-EE": "et_EE",
-      "fi-FI": "fi_FI",
-      "fil-PH": "fil_PH",
-      "fr-BE": "fr_BE",
-      "fr-CA": "fr_CA",
-      "fr-CH": "fr_CH",
-      "fr-FR": "fr_FR",
-      "hi-IN": "hi_IN",
-      "hu-HU": "hu_HU",
-      "id-ID": "id_ID",
-      "it-CH": "it_CH",
-      "it-IT": "it_IT",
-      "ja-JP": "ja_JP",
-      "ko-KR": "ko_KR",
-      "ms-MY": "ms_MY",
-      "ms-SG": "ms_SG",
-      "nb-NO": "no_NO",
-      "nl-BE": "nl_BE",
-      "nl-NL": "nl_NL",
-      "pl-PL": "pl_PL",
-      "pt-BR": "pt-BR_BR",
-      "pt-PT": "pt_PT",
-      "ro-RO": "ro_RO",
-      "ru-BY": "ru_BY",
-      "ru-RU": "ru_RU",
-      "sv-SE": "sv_SE",
-      "tr-TR": "tr_TR",
-      "uk-UA": "uk_UA",
-      "vi-VN": "vi_VN",
-      "zh-CN": "zh-CN_CN",
-      "zh-HK": "zh-TW_HK",
-      "zh-TW": "zh-TW_TW"
-    }
+    "languages": {},
+    "regions": {}
   },
   "wikidata": {
     "all_locale": null,
@@ -8394,6 +7960,7 @@
         "inh",
         "io",
         "is",
+        "isv",
         "it",
         "iu",
         "ja",
@@ -8442,6 +8009,7 @@
         "ltg",
         "lv",
         "mad",
+        "mag",
         "mai",
         "map-bms",
         "mdf",
@@ -9585,4 +9153,4 @@
     },
     "regions": {}
   }
-}
+}

searx/enginelib/__init__.py

@@ -207,6 +207,7 @@ class EngineAbout(msgspec.Struct, kw_only=True):
 
     use_official_api: bool = False
     """SearXNG engine makes use of the official API or not"""
+
     require_api_key: bool = False
     """API requires a key or not."""
 
@@ -217,8 +218,7 @@ class EngineAbout(msgspec.Struct, kw_only=True):
     """Brief description of the engine and where it gets its data from.
 
     This value should only be set as long as no description of the data source
-    is available via a :py:obj:`EngineAbout.wikidata_id`.
-    """
+    is available via a :py:obj:`EngineAbout.wikidata_id`."""
 
     language: str = ""
     """Deprecated! Migrate your setting from `engine.about.language` to

searx/engines/aol.py

@@ -1,210 +0,0 @@
-# SPDX-License-Identifier: AGPL-3.0-or-later
-"""AOL supports WEB, image, and video search.  Internally, it uses the Bing
-index.
-
-AOL doesn't seem to support setting the language via request parameters, instead
-the results are based on the URL.  For example, there is
-
-- `search.aol.com <https://search.aol.com>`_ for English results
-- `suche.aol.de <https://suche.aol.de>`_ for German results
-
-However, AOL offers its services only in a few regions:
-
-- en-US: search.aol.com
-- de-DE: suche.aol.de
-- fr-FR: recherche.aol.fr
-- en-GB: search.aol.co.uk
-- en-CA: search.aol.ca
-
-In order to still offer sufficient support for language and region, the `search
-keywords`_ known from Bing, ``language`` and ``loc`` (region), are added to the
-search term (AOL is basically just a proxy for Bing).
-
-.. _search keywords:
-    https://support.microsoft.com/en-us/topic/advanced-search-keywords-ea595928-5d63-4a0b-9c6b-0b769865e78a
-
-"""
-
-from urllib.parse import urlencode, unquote_plus
-import typing as t
-
-from lxml import html
-from dateutil import parser
-
-from searx.result_types import EngineResults
-from searx.utils import eval_xpath_list, eval_xpath, extract_text
-
-if t.TYPE_CHECKING:
-    from searx.extended_types import SXNG_Response
-    from searx.search.processors import OnlineParams
-
-about = {
-    "website": "https://www.aol.com",
-    "wikidata_id": "Q27585",
-    "official_api_documentation": None,
-    "use_official_api": False,
-    "require_api_key": False,
-    "results": "HTML",
-}
-
-categories = ["general"]
-search_type = "search"  # supported: search, image, video
-
-paging = True
-safesearch = True
-time_range_support = True
-results_per_page = 10
-
-
-base_url = "https://search.aol.com"
-time_range_map = {"day": "1d", "week": "1w", "month": "1m", "year": "1y"}
-safesearch_map = {0: "p", 1: "r", 2: "i"}
-
-enable_http2 = False
-
-
-def init(_):
-    if search_type not in ("search", "image", "video"):
-        raise ValueError(f"unsupported search type {search_type}")
-
-
-def request(query: str, params: "OnlineParams") -> None:
-
-    language, region = (params["searxng_locale"].split("-") + [None])[:2]
-    if language and language != "all":
-        query = f"{query} language:{language}"
-    if region:
-        query = f"{query} loc:{region}"
-
-    args: dict[str, str | int | None] = {
-        "q": query,
-        "b": params["pageno"] * results_per_page + 1,  # page is 1-indexed
-        "pz": results_per_page,
-    }
-
-    if params["time_range"]:
-        args["fr2"] = "time"
-        args["age"] = params["time_range"]
-    else:
-        args["fr2"] = "sb-top-search"
-
-    params["cookies"]["sB"] = f"vm={safesearch_map[params['safesearch']]}"
-    params["url"] = f"{base_url}/aol/{search_type}?{urlencode(args)}"
-    logger.debug(params)
-
-
-def _deobfuscate_url(obfuscated_url: str) -> str | None:
-    # URL looks like "https://search.aol.com/click/_ylt=AwjFSDjd;_ylu=JfsdjDFd/RV=2/RE=1774058166/RO=10/RU=https%3a%2f%2fen.wikipedia.org%2fwiki%2fTree/RK=0/RS=BP2CqeMLjscg4n8cTmuddlEQA2I-"  # pylint: disable=line-too-long
-    if not obfuscated_url:
-        return None
-
-    for part in obfuscated_url.split("/"):
-        if part.startswith("RU="):
-            return unquote_plus(part[3:])
-    # pattern for de-obfuscating URL not found, fall back to Yahoo's tracking link
-    return obfuscated_url
-
-
-def _general_results(doc: html.HtmlElement) -> EngineResults:
-    res = EngineResults()
-
-    for result in eval_xpath_list(doc, "//div[@id='web']//ol/li[not(contains(@class, 'first'))]"):
-        obfuscated_url = extract_text(eval_xpath(result, ".//h3/a/@href"))
-        if not obfuscated_url:
-            continue
-
-        url = _deobfuscate_url(obfuscated_url)
-        if not url:
-            continue
-
-        res.add(
-            res.types.MainResult(
-                url=url,
-                title=extract_text(eval_xpath(result, ".//h3/a")) or "",
-                content=extract_text(eval_xpath(result, ".//div[contains(@class, 'compText')]")) or "",
-                thumbnail=extract_text(eval_xpath(result, ".//a[contains(@class, 'thm')]/img/@data-src")) or "",
-            )
-        )
-    return res
-
-
-def _video_results(doc: html.HtmlElement) -> EngineResults:
-    res = EngineResults()
-
-    for result in eval_xpath_list(doc, "//div[contains(@class, 'results')]//ol/li"):
-        obfuscated_url = extract_text(eval_xpath(result, ".//a/@href"))
-        if not obfuscated_url:
-            continue
-
-        url = _deobfuscate_url(obfuscated_url)
-        if not url:
-            continue
-
-        published_date_raw = extract_text(eval_xpath(result, ".//div[contains(@class, 'v-age')]"))
-        try:
-            published_date = parser.parse(published_date_raw or "")
-        except parser.ParserError:
-            published_date = None
-
-        res.add(
-            res.types.LegacyResult(
-                {
-                    "template": "videos.html",
-                    "url": url,
-                    "title": extract_text(eval_xpath(result, ".//h3")),
-                    "content": extract_text(eval_xpath(result, ".//div[contains(@class, 'compText')]")),
-                    "thumbnail": extract_text(eval_xpath(result, ".//img[contains(@class, 'thm')]/@src")),
-                    "length": extract_text(eval_xpath(result, ".//span[contains(@class, 'v-time')]")),
-                    "publishedDate": published_date,
-                }
-            )
-        )
-
-    return res
-
-
-def _image_results(doc: html.HtmlElement) -> EngineResults:
-    res = EngineResults()
-
-    for result in eval_xpath_list(doc, "//section[@id='results']//ul/li"):
-        obfuscated_url = extract_text(eval_xpath(result, "./a/@href"))
-        if not obfuscated_url:
-            continue
-
-        url = _deobfuscate_url(obfuscated_url)
-        if not url:
-            continue
-
-        res.add(
-            res.types.LegacyResult(
-                {
-                    "template": "images.html",
-                    # results don't have an extra URL, only the image source
-                    "url": url,
-                    "title": extract_text(eval_xpath(result, ".//a/@aria-label")),
-                    "thumbnail_src": extract_text(eval_xpath(result, ".//img/@src")),
-                    "img_src": url,
-                }
-            )
-        )
-
-    return res
-
-
-def response(resp: "SXNG_Response") -> EngineResults:
-    doc = html.fromstring(resp.text)
-
-    match search_type:
-        case "search":
-            results = _general_results(doc)
-        case "image":
-            results = _image_results(doc)
-        case "video":
-            results = _video_results(doc)
-        case _:
-            raise ValueError("unsupported search type")
-
-    for suggestion in eval_xpath_list(doc, ".//ol[contains(@class, 'searchRightBottom')]//table//a"):
-        results.add(results.types.LegacyResult({"suggestion": extract_text(suggestion)}))
-
-    return results

searx/engines/chatnoir.py

@@ -14,7 +14,6 @@ from searx.extended_types import SXNG_Response
 from searx.network import get, post
 from searx.result_types import EngineResults
 from searx.utils import html_to_text
-from searx.enginelib import EngineCache
 
 if t.TYPE_CHECKING:
     from searx.search.processors import OnlineParams
@@ -42,21 +41,7 @@ search_index = "cw22"
 <https://www.chatnoir.eu/docs/api-general>`_ for a full list."""
 
 
-CACHE: EngineCache
-"""Cache to store session info (i.e. api key, csrf token, session id)."""
-
-
-def setup(engine_settings: dict[str, t.Any]) -> bool:
-    global CACHE  # pylint: disable=global-statement
-    CACHE = EngineCache(engine_settings["name"])
-    return True
-
-
 def _obtain_api_key() -> tuple[str, str, str]:
-    cached_session = CACHE.get("session")
-    if cached_session:
-        return tuple(cached_session.split("|"))
-
     home_resp = get(base_url)
     if not home_resp.ok:
         raise SearxEngineAPIException("failed to obtain api key")
@@ -76,10 +61,6 @@ def _obtain_api_key() -> tuple[str, str, str]:
     session_id = token_resp.cookies["sessionid"]
     scraped_api_key = token_resp.json()["token"]["token"]
 
-    # session keys seem to become rate-limited very fast, so only remembering
-    # for 1 minute here
-    CACHE.set("session", f"{csrf_token}|{session_id}|{scraped_api_key}", expire=60)
-
     return csrf_token, session_id, scraped_api_key
 
 

searx/engines/chinaso.py

@@ -19,11 +19,9 @@ Configuration
 
 The engine has the following additional settings:
 
-- :py:obj:`chinaso_category` (:py:obj:`ChinasoCategoryType`)
 - :py:obj:`chinaso_news_source` (:py:obj:`ChinasoNewsSourceType`)
 
-In the example below, all three ChinaSO engines are using the :ref:`network
-<engine network>` from the ``chinaso news`` engine.
+In the example below, ChinaSO is configured for news search.
 
 .. code:: yaml
 
@@ -31,23 +29,8 @@ In the example below, all three ChinaSO engines are using the :ref:`network
      engine: chinaso
      shortcut: chinaso
      categories: [news]
-     chinaso_category: news
      chinaso_news_source: all
 
-   - name: chinaso images
-     engine: chinaso
-     network: chinaso news
-     shortcut: chinasoi
-     categories: [images]
-     chinaso_category: images
-
-   - name: chinaso videos
-     engine: chinaso
-     network: chinaso news
-     shortcut: chinasov
-     categories: [videos]
-     chinaso_category: videos
-
 
 Implementations
 ===============
@@ -78,19 +61,6 @@ results_per_page = 10
 categories = []
 language = "zh"
 
-ChinasoCategoryType = t.Literal['news', 'videos', 'images']
-"""ChinaSo supports news, videos, images search.
-
-- ``news``: search for news
-- ``videos``: search for videos
-- ``images``: search for images
-
-In the category ``news`` you can additionally filter by option
-:py:obj:`chinaso_news_source`.
-"""
-chinaso_category = 'news'
-"""Configure ChinaSo category (:py:obj:`ChinasoCategoryType`)."""
-
 ChinasoNewsSourceType = t.Literal['CENTRAL', 'LOCAL', 'BUSINESS', 'EPAPER', 'all']
 """Filtering ChinaSo-News results by source:
 
@@ -109,39 +79,24 @@ base_url = "https://www.chinaso.com"
 
 
 def init(_):
-    if chinaso_category not in ('news', 'videos', 'images'):
-        raise ValueError(f"Unsupported category: {chinaso_category}")
-    if chinaso_category == 'news' and chinaso_news_source not in t.get_args(ChinasoNewsSourceType):
+    if chinaso_news_source not in t.get_args(ChinasoNewsSourceType):
         raise ValueError(f"Unsupported news source: {chinaso_news_source}")
 
 
 def request(query, params):
-    query_params = {"q": query}
+    query_params = {'q': query, 'pn': params["pageno"], 'ps': results_per_page}
 
     if time_range_dict.get(params['time_range']):
         query_params["stime"] = time_range_dict[params['time_range']]
         query_params["etime"] = 'now'
 
-    category_config = {
-        'news': {'endpoint': '/v5/general/v1/web/search', 'params': {'pn': params["pageno"], 'ps': results_per_page}},
-        'images': {
-            'endpoint': '/v5/general/v1/search/image',
-            'params': {'start_index': (params["pageno"] - 1) * results_per_page, 'rn': results_per_page},
-        },
-        'videos': {
-            'endpoint': '/v5/general/v1/search/video',
-            'params': {'start_index': (params["pageno"] - 1) * results_per_page, 'rn': results_per_page},
-        },
-    }
     if chinaso_news_source != 'all':
         if chinaso_news_source == 'EPAPER':
-            category_config['news']['params']["type"] = 'EPAPER'
+            query_params["type"] = 'EPAPER'
         else:
-            category_config['news']['params']["cate"] = chinaso_news_source
+            query_params["cate"] = chinaso_news_source
 
-    query_params.update(category_config[chinaso_category]['params'])
-
-    params["url"] = f"{base_url}{category_config[chinaso_category]['endpoint']}?{urlencode(query_params)}"
+    params["url"] = f"{base_url}/v5/general/v1/web/search?{urlencode(query_params)}"
     cookie = {
         "uid": base64.b64encode(secrets.token_bytes(16)).decode("utf-8"),
     }
@@ -163,12 +118,6 @@ def response(resp):
     if not data["data"]:
         return []
 
-    parsers = {'news': parse_news, 'images': parse_images, 'videos': parse_videos}
-
-    return parsers[chinaso_category](data)
-
-
-def parse_news(data):
     results = []
     if not data.get("data", {}).get("data"):
         raise SearxEngineAPIException("Invalid response")
@@ -190,47 +139,3 @@ def parse_news(data):
             }
         )
     return results
-
-
-def parse_images(data):
-    results = []
-    if not data.get("data", {}).get("arrRes"):
-        raise SearxEngineAPIException("Invalid response")
-
-    for entry in data["data"]["arrRes"]:
-        results.append(
-            {
-                'url': entry["web_url"],
-                'title': html_to_text(entry["title"]),
-                'content': html_to_text(entry.get("ImageInfo", "")),
-                'template': 'images.html',
-                'img_src': entry["url"].replace("http://", "https://"),
-                'thumbnail_src': entry["largeimage"].replace("http://", "https://"),
-            }
-        )
-    return results
-
-
-def parse_videos(data):
-    results = []
-    if not data.get("data", {}).get("arrRes"):
-        raise SearxEngineAPIException("Invalid response")
-
-    for entry in data["data"]["arrRes"]:
-        published_date = None
-        if entry.get("VideoPubDate"):
-            try:
-                published_date = datetime.fromtimestamp(int(entry["VideoPubDate"]))
-            except (ValueError, TypeError):
-                pass
-
-        results.append(
-            {
-                'url': entry["url"],
-                'title': html_to_text(entry["raw_title"]),
-                'template': 'videos.html',
-                'publishedDate': published_date,
-                'thumbnail': entry["image_src"].replace("http://", "https://"),
-            }
-        )
-    return results

searx/engines/findfiles.py

@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""FindFiles.net_ is a Germany-based file search engine.
+
+FindFiles.net_ is a specialized file search engine designed to help you search
+files online with precision. Unlike traditional search engines that mainly index
+web pages, FindFiles focuses on finding real files on the internet - including
+PDFs, documents, archives, videos, datasets, and more.
+
+.. _FindFiles.net: https://findfiles.net
+"""
+
+from os.path import basename
+from urllib.parse import urlencode
+import typing as t
+
+from lxml import html
+
+from searx.result_types import EngineResults
+from searx.utils import extract_text, eval_xpath, eval_xpath_list
+
+if t.TYPE_CHECKING:
+    from extended_types import SXNG_Response
+    from search.processors import OnlineParams
+
+about = {
+    "website": "https://findfiles.net",
+    "wikidata_id": None,
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "HTML",
+}
+
+base_url = "https://findfiles.net"
+categories = ["files"]
+paging = True
+safeserach = True
+
+safesearch_map = {
+    0: "contentguard.off",
+    1: "contentguard.moderate",
+    2: "contentguard.strict",
+}
+
+FindFilesCategory = t.Literal[
+    "all",
+    "document",
+    "text",
+    "image",
+    "audio",
+    "video",
+]
+FINDFILES_CATEGORIES = t.get_args(FindFilesCategory)
+
+findfiles_categ: FindFilesCategory = "all"
+"""Category to search in."""
+
+
+def setup(_: dict[str, t.Any]) -> bool:
+    if findfiles_categ not in FINDFILES_CATEGORIES:
+        raise ValueError("invalid category: %s" % findfiles_categ)
+    return True
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    args = {
+        "query": query,
+        "contentguard": safesearch_map[params["safesearch"]],
+        "page": params["pageno"],
+    }
+    # the language in the path doesn't change anything about the results, it
+    # only changes the UI
+    params["url"] = f"{base_url}/en/serp/{findfiles_categ}/?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    res = EngineResults()
+
+    dom = html.fromstring(resp.text)
+    if findfiles_categ == "image":
+        for result in eval_xpath_list(
+            dom, "//div[contains(@class, 'image-mosaic')]/div[contains(@class, 'image-item')]"
+        ):
+            res.add(
+                res.types.Image(
+                    url=extract_text(eval_xpath(result, ".//div[contains(@class, 'caption')]/a/@href")) or "",
+                    title=extract_text(eval_xpath(result, ".//div[contains(@class, 'caption')]/a")) or "",
+                    thumbnail_src=extract_text(eval_xpath(result, ".//img/@src")) or "",
+                )
+            )
+    elif findfiles_categ == "video":
+        for result in eval_xpath_list(
+            dom, "//div[contains(@class, 'video-mosaic')]/div[contains(@class, 'video-item')]"
+        ):
+            video_src = extract_text(eval_xpath(result, ".//video/@src")) or ""
+            res.add(
+                res.types.LegacyResult(
+                    template="videos.html",
+                    url=video_src,
+                    title=extract_text(eval_xpath(result, ".//div[contains(@class, 'caption')]/span")) or "",
+                    iframe_src=video_src or "",
+                )
+            )
+    else:
+        for result in eval_xpath_list(dom, "//ol/li[contains(@class, 'result-item')]/article"):
+            filename = basename(extract_text(eval_xpath(result, ".//h3")) or "")
+            res.add(
+                res.types.File(
+                    url=extract_text(eval_xpath(result, ".//h3/a/@href")) or "",
+                    title=filename,
+                    content=" ".join(extract_text(el) or "" for el in eval_xpath_list(result, "./div/span")),
+                    filename=filename,
+                    size=extract_text(eval_xpath(result, "(.//span[@id])[1]")) or "",
+                    embedded=extract_text(eval_xpath(result, ".//audio/@src")) or "",
+                )
+            )
+
+    return res

searx/engines/giphy.py

@@ -0,0 +1,127 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Giphy (images)"""
+
+import random
+from urllib.parse import urlencode
+import re
+
+import typing as t
+
+from lxml import html
+
+from searx.enginelib import EngineCache
+from searx.exceptions import SearxEngineAPIException
+from searx.network import get
+from searx.result_types import EngineResults
+from searx.result_types.image import ImageRef
+from searx.utils import eval_xpath_list, humanize_bytes
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
+
+
+about = {
+    "website": "https://giphy.com",
+    "wikidata_id": "Q17054335",
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+base_url = "https://giphy.com"
+api_url = "https://api.giphy.com"
+
+categories = ["images"]
+paging = True
+page_size = 15
+
+GiphyCategs = t.Literal["gifs", "stickers", "clips"]
+giphy_categ: GiphyCategs = "gifs"
+"""Giphy category to search in."""
+
+CACHE: EngineCache
+"""Cache for storing the extracted api key."""
+
+
+_GIPHY_API_KEY_RE = re.compile(r"[Aa]piKey\s*:\s*\"(\w+)\"")
+
+
+def setup(engine_settings: dict[str, str]) -> bool:
+    if giphy_categ not in t.get_args(GiphyCategs):
+        raise ValueError("invalid category: %s" % giphy_categ)
+
+    global CACHE  # pylint: disable=global-statement
+    CACHE = EngineCache(engine_settings["name"])
+
+    return True
+
+
+def _get_api_key() -> str:
+    """
+    Extract the Giphy API key from the JavaScript code. There are different API keys
+    (e.g. for mobile, desktop, ...), so we just pick a random one of these.
+    """
+    cached = CACHE.get("api_key")
+    if cached:
+        return cached
+
+    homepage_resp = get(base_url)
+    homepage_doc = html.fromstring(homepage_resp.text)
+
+    for script_src in eval_xpath_list(homepage_doc, "//script[contains(@src, 'layout')]/@src"):
+        script_resp = get(base_url + script_src)
+        api_keys = _GIPHY_API_KEY_RE.findall(script_resp.text)
+        if api_keys:
+            api_key = random.choice(api_keys)
+            CACHE.set("api_key", api_key, expire=60 * 60 * 6)  # 6 hours
+            return api_key
+
+    raise SearxEngineAPIException("failed to extract api keys")
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    args = {
+        "q": query,
+        "api_key": _get_api_key(),
+        "limit": page_size,
+        "offset": (params["pageno"] - 1) * page_size,
+        "type": giphy_categ,
+    }
+    params["url"] = f"{api_url}/v1/{giphy_categ}/search?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response"):
+    res = EngineResults()
+
+    result: dict[str, t.Any]
+    for result in resp.json()["data"]:
+        img = result['images']['original']
+        formats = [
+            ImageRef(url=img["mp4"], subtype="mp4"),  # type: ignore
+            ImageRef(url=img["webp"], subtype="webp"),  # type: ignore
+        ]
+        thumb = (
+            result["images"].get("downsized")
+            or result["images"].get("downsized_medium")
+            or result["images"].get("downsized_small")
+            or result["images"].get("downsized_large")
+        )
+        res.add(
+            res.types.Image(
+                title=result["title"],
+                content=", ".join(result.get("tags", [])),
+                url=result["url"],
+                thumbnail_src=thumb.get("url") or img["url"],
+                img_src=img["url"],
+                resolution=f"{img['width']}x{img['height']}",
+                img_format="GIF",
+                formats=formats,
+                author=result["username"],
+                filesize=humanize_bytes(int(img["size"])),
+                source=result.get("source_tld") or "",
+            )
+        )
+
+    return res

searx/engines/iseek.py

@@ -0,0 +1,88 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""iseek_ is a search engine by the AI company Vantage Labs LLC,
+that focuses on medical and educational applicances.
+Although it's an AI company, it doesn't include any AI stuff in its results.
+
+.. _iseek : https://www.iseek.ai/
+"""
+
+import base64
+from hashlib import sha256
+import typing as t
+from urllib.parse import urlencode
+
+from searx.result_types import EngineResults
+
+if t.TYPE_CHECKING:
+    from searx.search.processors import OnlineParams
+    from searx.extended_types import SXNG_Response
+
+
+about = {
+    "website": 'https://www.iseek.com',
+    "wikidata_id": None,
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+categories = ["general"]
+paging = True
+
+base_url = "https://api.iseek.com"
+page_size = 10
+
+
+def _get_new_token(query: str, pageno: int) -> str:
+    """Create a new ``qToken``. This reduced the time for fetching subsequent pages
+    from 4 seconds to 200ms when testing."""
+    # The website uses a random value as qToken for the first page. For our use case,
+    # it's easier if the qToken can be deterministically re-calculated based on the search query,
+    # so that we can the same result when calling _get_new_token for the second, third, ... page
+    #
+    # var qToken = Math.ceil(Math.random() * parseInt("ZZZZ", 36)).toString(36);
+    # while (qToken.length < 4) qToken = '0' + qToken;
+    # qToken = qToken + "_" + pageno
+    query_hash = sha256(query.encode()).digest()
+    hash_start = base64.b64encode(query_hash).decode()[0:4]
+    return f"{hash_start}_{pageno}"
+
+
+def request(query: str, params: "OnlineParams"):
+    offset = (params["pageno"] - 1) * page_size
+
+    # always seems to find 20 results max
+    if offset >= 20:
+        params["url"] = None
+        return
+
+    args = {
+        "q": query,
+        "key": "core-web",
+        "num": str(page_size),
+        "off": offset,
+        "rSort": "__metasearch_score_d:desc",
+        # it supports many more fields, but none of them are really relevant
+        "names": "title_t,content_txt,url_s",
+        "qNames": "title_t",
+        "qToken": _get_new_token(query, params["pageno"]),
+    }
+    params["url"] = f"{base_url}/search?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    res = EngineResults()
+
+    for group in resp.json()["data"]:
+        group: dict[str, t.Any]
+        for result in group["doclist"]["docs"]:
+            result: dict[str, str]
+            res.add(
+                res.types.MainResult(
+                    url=result["url_s"],
+                    title=result["title_t"],
+                    content="".join(result["content_txt"]),
+                )
+            )
+
+    return res

searx/engines/marginalia.py

@@ -44,7 +44,7 @@ about = {
 
 base_url = "https://api2.marginalia-search.com"
 safesearch = True
-categories = ["general"]
+categories = ["general", "blogs"]
 paging = True
 results_per_page = 20
 api_key = None

searx/engines/resulthunter.py

@@ -101,7 +101,7 @@ def _image_results(doc: "ElementBase") -> EngineResults:
                 res.types.Image(
                     url=extract_text(eval_xpath(result, "./@href")) or "",
                     title=extract_text(eval_xpath(result, "./img/@alt")) or "",
-                    thumbnail_src=extract_text(eval_xpath(result, "./img/@src")) or "",
+                    img_src=extract_text(eval_xpath(result, "./img/@src")) or "",
                 ),
             )
         )

searx/engines/startpagina.py

@@ -0,0 +1,107 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Startpagina is a Netherlands search engine by `Kompas`_. It takes all its
+results from Google.
+
+.. _Kompas: https://www.kompaspublishing.nl/
+"""
+
+import typing as t
+from urllib.parse import urlencode
+
+from dateutil import parser
+
+from searx.utils import format_duration
+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://startpagina.nl",
+    "wikidata_id": None,
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+language = "ne"
+paging = True
+safesearch = True
+
+categories = ["general"]
+startpagina_categ = "web"
+"""Category to search in. Can be either "web", "images", "videos" or "news"."""
+page_size = 10
+
+
+api_url = "https://search.kompas.services"
+
+
+def init(_):
+    if startpagina_categ not in ("web", "images", "videos", "news"):
+        raise ValueError("invalid search type: %s" % startpagina_categ)
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    args = {"q": query, "page_size": page_size, "page": params["pageno"]}
+    params["url"] = f"{api_url}/api/v2/search/{startpagina_categ}/?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response"):
+    res = EngineResults()
+
+    json_resp = resp.json()
+
+    for result in json_resp["results"]:
+        if startpagina_categ == "web":
+            res.add(
+                res.types.MainResult(
+                    url=result["original_url"],
+                    title=result["title"],
+                    content=result["description"],
+                )
+            )
+        elif startpagina_categ == "news":
+            publishedDate = None
+            try:
+                publishedDate = parser.parse(result["date"])
+            except parser.ParserError:
+                pass
+
+            res.add(
+                res.types.MainResult(
+                    url=result["original_url"],
+                    title=result["title"],
+                    content=result["description"],
+                    thumbnail=result["image"]["thumbnail_url"],
+                    publishedDate=publishedDate,
+                )
+            )
+        elif startpagina_categ == "videos":
+            res.add(
+                res.types.LegacyResult(
+                    template="videos.html",
+                    url=result["original_url"],
+                    title=result["title"],
+                    content=result["description"],
+                    thumbnail=result["video"]["thumbnail_url"],
+                    length=format_duration(result["video"]["duration"]),
+                )
+            )
+        elif startpagina_categ == "images":
+            res.add(
+                res.types.Image(
+                    url=result["original_url"],
+                    title=result["title"],
+                    content=result["description"],
+                    thumbnail_src=result["image"]["thumbnail_url"],
+                    resolution=f"{result['image']['width']}x{result['image']['height']}",
+                )
+            )
+
+    for related in json_resp["related_searches"]:
+        res.add(res.types.LegacyResult(suggestion=related["query"]))
+
+    return res

searx/engines/tiger.py

@@ -73,7 +73,7 @@ def _obtain_session_code() -> str:
     if cached_session:
         return cached_session
 
-    results_page = get(f"{base_url}/_internCode.aspx")
+    results_page = get(f"{base_url}/checkCode.aspx")
     doc = html.fromstring(results_page.text)
 
     extra_data: dict[str, str] = {}
@@ -107,7 +107,7 @@ def _obtain_session_code() -> str:
     }
 
     challenge_response = post(
-        f"{base_url}/_internCode.aspx",
+        f"{base_url}/checkCode.aspx",
         cookies=results_page.cookies,
         data=data,
     )
@@ -125,7 +125,9 @@ def request(query: str, params: "OnlineParams"):
     code = _obtain_session_code()
     args = {"w": query, "page": params["pageno"]}
     params["url"] = f"{base_url}/{tiger_category}?{urlencode(args)}"
-    params["cookies"]["Tiger.ch"] = f"Code={code}"
+    # Setting Checked=1 shows related search terms / suggestions
+    # Language and country could be set with Lng= and Land= in the future
+    params["cookies"]["Tiger.ch"] = f"Tiger.ch=&Code={code}&Checked=1"
 
 
 def response(resp: "SXNG_Response") -> EngineResults:
@@ -144,6 +146,9 @@ def response(resp: "SXNG_Response") -> EngineResults:
                     content=extract_text(eval_xpath(result, ".//*[contains(@class, 'webbodynopic')]")) or "",
                 )
             )
+
+        for suggestion in eval_xpath_list(doc, "//a[contains(@class, 'linkAnders')]"):
+            res.add(res.types.LegacyResult(suggestion=extract_text(suggestion)))
     elif tiger_category == "News":
         for result in eval_xpath_list(doc, "//div[@id='panNews']/div"):
             publishedDate = None

searx/engines/tusksearch.py

@@ -0,0 +1,162 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Tusksearch_ is an American search engine that claims to fight censorship.
+Its search results are (at least partially) from Brave.
+
+.. _Tusksearch: https://tusksearch.com/about
+"""
+
+from json import loads
+import random
+import typing as t
+from urllib.parse import urlencode
+from dateutil import parser
+
+from searx.exceptions import SearxEngineAPIException
+from searx.network import get
+from searx.utils import html_to_text
+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://tusksearch.com",
+    "wikidata_id": None,
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+paging = True
+
+categories = ["general"]
+tusk_categ = "web"
+"""Category to search in. Can be either "web", "images", "videos" or "news"."""
+
+
+api_url = "https://api.tusksearch.com"
+
+
+def init(_):
+    if tusk_categ not in ("web", "images", "videos", "news"):
+        raise ValueError("invalid search type: %s" % tusk_categ)
+
+
+def _obtain_x_sid() -> tuple[str, str]:
+    """
+    The session ID ("sid") is encoded as a byte array in ``embed.js``.
+    It is only valid for exactly one request, so we can't cache it.
+
+    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")
+    if not resp.ok:
+        raise SearxEngineAPIException("failed to obtain request x-sid token")
+
+    # data is prefixed by 'var x='
+    data_array = loads(resp.text[6:])
+
+    def _byte_array_to_ascii(text: list[int]) -> str:
+        """
+        Converts a byte array (e.g. [81, 101, 97, 114, 88, 78, 71]) to the ASCII
+        string representation (e.g. "SearXNG").
+        """
+        return "".join([chr(x) for x in text])
+
+    x_sid_header = _byte_array_to_ascii(data_array[3])
+    x_sid_value = _byte_array_to_ascii(data_array[4])
+    return x_sid_header, x_sid_value
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    # images don't support pagination, news and videos only support two pages
+    if tusk_categ == "images" and params["pageno"] > 1 or tusk_categ in ("news", "videos") and params["pageno"] > 2:
+        params["url"] = None
+        return
+
+    args = {
+        "q": query,
+        "p": params["pageno"],
+        "l": "center",  # political direction: "left", "center" or "right"
+    }
+    if tusk_categ == "images":
+        params["url"] = f"{api_url}/Search/Image?{urlencode(args)}"
+    else:
+        # web response also contains news and videos
+        params["url"] = f"{api_url}/Search/Web?{urlencode(args)}"
+
+    x_sid_header, x_sid_value = _obtain_x_sid()
+    params["headers"] = {
+        x_sid_header: x_sid_value,
+        # required - we send a random longitude and latitude instead of the actual user location
+        'x-lon': str(random.random() * 90),
+        'x-lat': str(random.random() * 90),
+    }
+
+
+def response(resp: "SXNG_Response"):
+    res = EngineResults()
+
+    json_resp = resp.json()["results"]
+
+    if tusk_categ == "web":
+        for result in (json_resp.get("web") or {}).get("results", []):
+            res.add(
+                res.types.MainResult(
+                    url=result["url"],
+                    title=html_to_text(result["title"]),
+                    content=html_to_text(result["description"]),
+                    thumbnail=(result["thumbnail"] or {}).get("src") or "",
+                )
+            )
+    elif tusk_categ == "news":
+        for result in (json_resp.get("news") or {}).get("results", []):
+            publishedDate = None
+            try:
+                publishedDate = parser.parse(result["age"])
+            except parser.ParserError:
+                pass
+
+            res.add(
+                res.types.MainResult(
+                    url=result["url"],
+                    title=html_to_text(result["title"]),
+                    content=html_to_text(result["description"]),
+                    thumbnail=result["thumbnail"]["src"],
+                    publishedDate=publishedDate,
+                )
+            )
+    elif tusk_categ == "videos":
+        for result in (json_resp.get("videos") or {}).get("results", []):
+            publishedDate = None
+            try:
+                publishedDate = parser.parse(result["age"])
+            except parser.ParserError:
+                pass
+
+            res.add(
+                res.types.LegacyResult(
+                    template="videos.html",
+                    url=result["url"],
+                    title=html_to_text(result["title"]),
+                    content=html_to_text(result["description"]),
+                    thumbnail=result["thumbnail"]["src"],
+                    publishedDate=publishedDate,
+                    length=result["video"].get("duration"),
+                )
+            )
+    elif tusk_categ == "images":
+        for result in json_resp:
+            res.add(
+                res.types.Image(
+                    url=result["url"],
+                    title=html_to_text(result["title"]),
+                    img_src=result["properties"]["url"],
+                    thumbnail_src=result["thumbnail"]["src"],
+                )
+            )
+
+    return res

searx/result_types/image.py

@@ -14,6 +14,7 @@ template.
 # pylint: disable=too-few-public-methods
 __all__ = ["Image", "ImageRef"]
 
+import mimetypes
 import types
 import typing as t
 from collections.abc import Callable
@@ -71,7 +72,7 @@ class Image(MainResult, kw_only=True):
     """The resolution of the image (e.g. ``1920 x 1080`` pixel)"""
 
     img_format: str = ""
-    """The format of the image (e.g. ``png``)."""
+    """The format of the image :py:obj:`.MainResult.img_src` (e.g. ``png``)."""
 
     source: str = ""
     """Source of the image."""
@@ -83,6 +84,19 @@ class Image(MainResult, kw_only=True):
     formats: list[ImageRef] = []
     """List of links to alternative image formats."""
 
+    def __post_init__(self):
+        super().__post_init__()
+
+        if not self.img_format:
+            # automatically guess the image format based on the path of the image
+            mimetype = mimetypes.guess_type(self.img_src)[0]
+            if mimetype:
+                subtype = mimetype.split("/")[-1]
+                if subtype in MIMESUB:
+                    self.img_format = MIMESUB[subtype]
+                else:
+                    self.img_format = subtype.upper()
+
     def filter_urls(self, filter_func: "Callable[[Result | LegacyResult, str, str], str | bool ]"):
 
         for _ref in self.formats[:]:

searx/settings.yml

@@ -443,27 +443,12 @@ engines:
     timeout: 6.0
     shortcut: conda
     disabled: true
-
-  - name: aol
-    engine: aol
-    search_type: search
-    categories: [general]
-    shortcut: aol
-    disabled: true
-
-  - name: aol images
-    engine: aol
-    search_type: image
-    categories: [images]
-    shortcut: aoli
-    disabled: true
-
-  - name: aol videos
-    engine: aol
-    search_type: video
-    categories: [videos]
-    shortcut: aolv
-    disabled: true
+    about:
+      website: https://anaconda.org/search
+      wikidata_id: Q18209310
+      official_api_documentation: https://api.anaconda.org/search
+      use_official_api: false
+      results: HTML
 
   - name: arch linux wiki
     engine: archlinux
@@ -665,28 +650,29 @@ engines:
     engine: chinaso
     shortcut: chinaso
     categories: [news]
-    chinaso_category: news
     chinaso_news_source: all
     disabled: true
     inactive: true
 
-  - name: chinaso images
-    engine: chinaso
-    network: chinaso news
-    shortcut: chinasoi
-    categories: [images]
-    chinaso_category: images
-    disabled: true
-    inactive: true
-
-  - name: chinaso videos
-    engine: chinaso
-    network: chinaso news
-    shortcut: chinasov
-    categories: [videos]
-    chinaso_category: videos
+  - name: cl0q
+    engine: json_engine
+    shortcut: cl
+    categories: general
+    paging: true
+    first_page_num: 0
+    page_size: 20
+    search_url: https://cl0q.com/search?q={query}&limit=20&offset={pageno}
+    results_query: results
+    url_query: domain
+    url_prefix: https://
+    title_query: title
+    content_query: description
     disabled: true
     inactive: true
+    about:
+      website: https://cl0q.com
+      description: "Open source network for searching domains"
+      results: JSON
 
   - name: cloudflareai
     engine: cloudflareai
@@ -978,6 +964,34 @@ engines:
     shortcut: fd
     disabled: true
 
+  - name: findfiles
+    engine: findfiles
+    findfiles_categ: all
+    categories: files
+    shortcut: fif
+    disabled: true
+
+  - name: findfiles images
+    engine: findfiles
+    findfiles_categ: image
+    categories: images
+    shortcut: fifi
+    disabled: true
+
+  - name: findfiles videos
+    engine: findfiles
+    findfiles_categ: video
+    categories: videos
+    shortcut: fifv
+    disabled: true
+
+  - name: findfiles music
+    engine: findfiles
+    findfiles_categ: audio
+    categories: music
+    shortcut: fifm
+    disabled: true
+
   - name: findthatmeme
     engine: findthatmeme
     shortcut: ftm
@@ -1114,6 +1128,11 @@ engines:
     search_type: text
     timeout: 10
 
+  - name: giphy
+    engine: giphy
+    shortcut: gif
+    disabled: true
+
   - name: gitlab
     engine: gitlab
     base_url: https://gitlab.com
@@ -1295,6 +1314,13 @@ engines:
       require_api_key: false
       results: JSON
 
+  - name: iseek
+    engine: iseek
+    shortcut: isk
+    timeout: 4
+    disabled: true
+    inactive: true
+
   - name: il post
     engine: il_post
     shortcut: pst
@@ -1383,6 +1409,21 @@ engines:
   #   api_key: ""  # required
   #   kagi_categ: videos
 
+  - name: kozmonavt
+    engine: xpath
+    search_url: https://kozmonavt.su/s?q={query}
+    shortcut: koz
+    disabled: true
+    inactive: true
+    results_xpath: //div[contains(@class, 'list')]/section
+    url_xpath: concat('https://', substring-after(.//a/@href, '?q='))
+    title_xpath: .//a
+    content_xpath: .//div[contains(@class, 'snip')]
+    about:
+      website: https://kozmonavt.su
+      description: "Web site directory with its own index"
+      results: HTML
+
   - name: jisho
     engine: jisho
     shortcut: js
@@ -1400,6 +1441,22 @@ engines:
     shortcut: kc
     timeout: 4.0
 
+  - name: kukei
+    engine: xpath
+    categories: [general, blogs]
+    search_url: https://kukei.eu/?q={query}
+    shortcut: kuk
+    disabled: true
+    inactive: true
+    results_xpath: //ul/li[contains(@class, "result-item-first-level")]
+    url_xpath: .//a/@href
+    title_xpath: .//h3
+    content_xpath: .//p
+    about:
+      website: https://kukei.eu
+      description: "Curated search for the small web"
+      results: HTML
+
   - name: lemmy communities
     engine: lemmy
     lemmy_type: Communities
@@ -2033,7 +2090,7 @@ engines:
   - name: rawweb
     engine: json_engine
     shortcut: rw
-    categories: general
+    categories: [general, blogs]
     paging: true
     search_url: 'https://api.rawweb.org/api/search?keyword={query}&page={pageno}&lang=*'
     results_query: data
@@ -2088,7 +2145,7 @@ engines:
   - name: searchmysite
     engine: xpath
     shortcut: sms
-    categories: general
+    categories: [general, blogs]
     paging: true
     search_url: https://searchmysite.net/search/?q={query}&page={pageno}
     results_xpath: //div[contains(@class,'search-result')]
@@ -2404,6 +2461,35 @@ engines:
       - 5000
     inactive: true
 
+  - name: tusksearch
+    engine: tusksearch
+    shortcut: tu
+    tusk_categ: web
+    categories: general
+    disabled: true
+
+  - name: tusksearch images
+    engine: tusksearch
+    shortcut: tui
+    paging: false
+    tusk_categ: images
+    categories: images
+    disabled: true
+
+  - name: tusksearch videos
+    engine: tusksearch
+    shortcut: tuv
+    tusk_categ: videos
+    categories: videos
+    disabled: true
+
+  - name: tusksearch news
+    engine: tusksearch
+    shortcut: tun
+    tusk_categ: news
+    categories: news
+    disabled: true
+
   # tmp suspended - too slow, too many errors
   #  - name: urbandictionary
   #    engine      : xpath
@@ -2417,6 +2503,24 @@ engines:
     engine: unsplash
     shortcut: us
 
+  - name: unobtanium
+    engine: xpath
+    shortcut: uno
+    categories: [general, blogs]
+    paging: true
+    first_page_num: 0
+    search_url: https://unobtanium.rocks/search?search={query}&page={pageno}
+    results_xpath: //ul[contains(@class, 'search-results')]/li
+    url_xpath: .//a/@href
+    title_xpath: .//a/b
+    content_xpath: .//p[2]
+    disabled: true
+    inactive: true
+    about:
+      website: https://unobtanium.rocks
+      description: "Personal websites focused search engine."
+      results: HTML
+
   - name: yandex
     engine: yandex
     categories: general
@@ -2476,7 +2580,7 @@ engines:
     url_query: URL
     title_query: Title
     content_query: Snippet
-    categories: [general, web]
+    categories: [general, blogs]
     shortcut: wib
     disabled: true
     about:
@@ -2901,6 +3005,38 @@ engines:
     disabled: true
     inactive: true
 
+  - name: startpagina
+    engine: startpagina
+    shortcut: spnl
+    startpagina_categ: web
+    categories: general
+    disabled: true
+    inactive: true
+
+  - name: startpagina images
+    engine: startpagina
+    shortcut: spnli
+    startpagina_categ: images
+    categories: images
+    disabled: true
+    inactive: true
+
+  - name: startpagina videos
+    engine: startpagina
+    shortcut: spnlv
+    startpagina_categ: videos
+    categories: videos
+    disabled: true
+    inactive: true
+
+  - name: startpagina news
+    engine: startpagina
+    shortcut: spnln
+    startpagina_categ: news
+    categories: news
+    disabled: true
+    inactive: true
+
   - name: swisscows
     engine: swisscows
     categories: general
@@ -3023,6 +3159,22 @@ engines:
     shortcut: wttr
     timeout: 9.0
 
+  - name: xonaly
+    engine: xpath
+    search_url: https://xonaly.com/?query={query}
+    categories: general
+    shortcut: xo
+    disabled: true
+    inactive: true
+    results_xpath: //div[contains(@class, 'results-block')]/ul/li
+    url_xpath: ./div[contains(@class, 'result-title')]/a/@href
+    title_xpath: ./div[contains(@class, 'result-title')]/a
+    content_xpath: ./p[contains(@class, 'excerpt')]
+    about:
+      website: https://xonaly.com
+      description: "Canadian search engine with its own index"
+      results: HTML
+
   - name: zapmeta
     engine: xpath
     shortcut: zpm

searx/sxng_locales.py

@@ -9,7 +9,6 @@
 '''
 
 sxng_locales = (
-    ('af', 'Afrikaans', '', 'Afrikaans', '\U0001f310'),
     ('ar', 'العربية', '', 'Arabic', '\U0001f310'),
     ('ar-SA', 'العربية', 'المملكة العربية السعودية', 'Arabic', '\U0001f1f8\U0001f1e6'),
     ('bg', 'Български', '', 'Bulgarian', '\U0001f310'),
@@ -46,7 +45,6 @@ sxng_locales = (
     ('es-ES', 'Español', 'España', 'Spanish', '\U0001f1ea\U0001f1f8'),
     ('es-MX', 'Español', 'México', 'Spanish', '\U0001f1f2\U0001f1fd'),
     ('es-PE', 'Español', 'Perú', 'Spanish', '\U0001f1f5\U0001f1ea'),
-    ('es-VE', 'Español', 'Venezuela', 'Spanish', '\U0001f1fb\U0001f1ea'),
     ('et', 'Eesti', '', 'Estonian', '\U0001f310'),
     ('et-EE', 'Eesti', 'Eesti', 'Estonian', '\U0001f1ea\U0001f1ea'),
     ('fi', 'Suomi', '', 'Finnish', '\U0001f310'),
@@ -58,7 +56,6 @@ sxng_locales = (
     ('fr-CA', 'Français', 'Canada', 'French', '\U0001f1e8\U0001f1e6'),
     ('fr-CH', 'Français', 'Suisse', 'French', '\U0001f1e8\U0001f1ed'),
     ('fr-FR', 'Français', 'France', 'French', '\U0001f1eb\U0001f1f7'),
-    ('gl', 'Galego', '', 'Galician', '\U0001f310'),
     ('hi', 'हिन्दी', '', 'Hindi', '\U0001f310'),
     ('hi-IN', 'हिन्दी', 'भारत', 'Hindi', '\U0001f1ee\U0001f1f3'),
     ('hr', 'Hrvatski', '', 'Croatian', '\U0001f310'),
@@ -74,6 +71,8 @@ sxng_locales = (
     ('ja-JP', '日本語', '日本', 'Japanese', '\U0001f1ef\U0001f1f5'),
     ('ko', '한국어', '', 'Korean', '\U0001f310'),
     ('ko-KR', '한국어', '대한민국', 'Korean', '\U0001f1f0\U0001f1f7'),
+    ('mi', 'Māori', '', 'Māori', '\U0001f310'),
+    ('mi-NZ', 'Māori', 'Aotearoa', 'Māori', '\U0001f1f3\U0001f1ff'),
     ('nb', 'Norsk Bokmål', '', 'Norwegian Bokmål', '\U0001f310'),
     ('nb-NO', 'Norsk Bokmål', 'Norge', 'Norwegian Bokmål', '\U0001f1f3\U0001f1f4'),
     ('nl', 'Nederlands', '', 'Dutch', '\U0001f310'),
@@ -90,8 +89,6 @@ sxng_locales = (
     ('ro-RO', 'Română', 'România', 'Romanian', '\U0001f1f7\U0001f1f4'),
     ('ru', 'Русский', '', 'Russian', '\U0001f310'),
     ('ru-RU', 'Русский', 'Россия', 'Russian', '\U0001f1f7\U0001f1fa'),
-    ('sk', 'Slovenčina', '', 'Slovak', '\U0001f310'),
-    ('sq', 'Shqip', '', 'Albanian', '\U0001f310'),
     ('sv', 'Svenska', '', 'Swedish', '\U0001f310'),
     ('sv-FI', 'Svenska', 'Finland', 'Swedish', '\U0001f1eb\U0001f1ee'),
     ('sv-SE', 'Svenska', 'Sverige', 'Swedish', '\U0001f1f8\U0001f1ea'),
@@ -99,7 +96,6 @@ sxng_locales = (
     ('th-TH', 'ไทย', 'ไทย', 'Thai', '\U0001f1f9\U0001f1ed'),
     ('tr', 'Türkçe', '', 'Turkish', '\U0001f310'),
     ('tr-TR', 'Türkçe', 'Türkiye', 'Turkish', '\U0001f1f9\U0001f1f7'),
-    ('uk', 'Українська', '', 'Ukrainian', '\U0001f310'),
     ('vi', 'Tiếng Việt', '', 'Vietnamese', '\U0001f310'),
     ('vi-VN', 'Tiếng Việt', 'Việt Nam', 'Vietnamese', '\U0001f1fb\U0001f1f3'),
     ('zh', '中文', '', 'Chinese', '\U0001f310'),

searx/translations/ru/LC_MESSAGES/messages.po

@@ -33,22 +33,24 @@
 # IcewindX <icewindx@noreply.codeberg.org>, 2025.
 # 0ko <0ko@noreply.codeberg.org>, 2025.
 # greatdng <greatdng@noreply.codeberg.org>, 2026.
+# code_gremlin <code_gremlin@noreply.codeberg.org>, 2026.
 msgid ""
 msgstr ""
-"Project-Id-Version:  searx\n"
+"Project-Id-Version: searx\n"
 "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
 "POT-Creation-Date: 2026-06-13 11:31+0000\n"
-"PO-Revision-Date: 2026-05-19 12:08+0000\n"
-"Last-Translator: return42 <return42@noreply.codeberg.org>\n"
+"PO-Revision-Date: 2026-06-24 10:07+0000\n"
+"Last-Translator: code_gremlin <code_gremlin@noreply.codeberg.org>\n"
+"Language-Team: Russian <https://translate.codeberg.org/projects/searxng/"
+"searxng/ru/>\n"
 "Language: ru\n"
-"Language-Team: Russian "
-"<https://translate.codeberg.org/projects/searxng/searxng/ru/>\n"
-"Plural-Forms: nplurals=4; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && "
-"n%10<=4 && (n%100<12 || n%100>14) ? 1 : n%10==0 || (n%10>=5 && n%10<=9) "
-"|| (n%100>=11 && n%100<=14)? 2 : 3);\n"
 "MIME-Version: 1.0\n"
 "Content-Type: text/plain; charset=utf-8\n"
 "Content-Transfer-Encoding: 8bit\n"
+"Plural-Forms: nplurals=4; plural=(n%10==1 && n%100!=11 ? 0 : n%10>=2 && "
+"n%10<=4 && (n%100<12 || n%100>14) ? 1 : n%10==0 || (n%10>=5 && n%10<=9) || "
+"(n%100>=11 && n%100<=14)? 2 : 3);\n"
+"X-Generator: Weblate 2026.6.1\n"
 "Generated-By: Babel 2.18.0\n"
 
 #. CONSTANT_NAMES['NO_SUBGROUPING']
@@ -1667,11 +1669,11 @@ msgstr "Разрешение"
 
 #: searx/templates/simple/result_templates/images.html:55
 msgid "Image formats"
-msgstr ""
+msgstr "Форматы изображений"
 
 #: searx/templates/simple/result_templates/images.html:56
 msgid "original format"
-msgstr ""
+msgstr "формат оригинала"
 
 #: searx/templates/simple/result_templates/images.html:63
 msgid "Engine"
@@ -2441,4 +2443,3 @@ msgstr "скрыть видео"
 
 #~ msgid "Format"
 #~ msgstr "Формат"
-

searxng_extra/update/update_engine_descriptions.py

@@ -15,25 +15,26 @@ from os.path import join
 
 from lxml.html import fromstring
 
+import searx.engines
 from searx.engines import wikidata, set_loggers
-from searx.utils import extract_text, searxng_useragent
+from searx.utils import extract_text
 from searx.locales import LOCALE_NAMES, locales_initialize, match_locale
 from searx import searx_dir
 from searx.utils import gen_useragent
 import searx.search
 import searx.network
-from searx.data import data_dir
+from searx.data import data_dir, ENGINE_DESCRIPTIONS
 
-DATA_FILE = data_dir / 'engine_descriptions.json'
+DATA_FILE = data_dir / "engine_descriptions.json"
 
-set_loggers(wikidata, 'wikidata')
+set_loggers(wikidata, "wikidata")
 locales_initialize()
 
 # you can run the query in https://query.wikidata.org
 # replace %IDS% by Wikidata entities separated by spaces with the prefix wd:
 # for example wd:Q182496 wd:Q1540899
 # replace %LANGUAGES_SPARQL% by languages
-SPARQL_WIKIPEDIA_ARTICLE = """
+SPARQL_WIKIPEDIA_ARTICLE: str = """
 SELECT DISTINCT ?item ?name ?article ?lang
 WHERE {
   hint:Query hint:optimizer "None".
@@ -48,7 +49,7 @@ WHERE {
 ORDER BY ?item ?lang
 """
 
-SPARQL_DESCRIPTION = """
+SPARQL_DESCRIPTION: str = """
 SELECT DISTINCT ?item ?itemDescription
 WHERE {
   VALUES ?item { %IDS% }
@@ -58,43 +59,43 @@ WHERE {
 ORDER BY ?itemLang
 """
 
-NOT_A_DESCRIPTION = [
-    'web site',
-    'site web',
-    'komputa serĉilo',
-    'interreta serĉilo',
-    'bilaketa motor',
-    'web search engine',
-    'wikimedia täpsustuslehekülg',
+NOT_A_DESCRIPTION: list[str] = [
+    "web site",
+    "site web",
+    "komputa serĉilo",
+    "interreta serĉilo",
+    "bilaketa motor",
+    "web search engine",
+    "wikimedia täpsustuslehekülg",
 ]
 
-SKIP_ENGINE_SOURCE = [
+SKIP_ENGINE_SOURCE: list[tuple[str, str]] = [
     # fmt: off
-    ('gitlab', 'wikidata')
+    ("gitlab", "wikidata")
     # descriptions are about wikipedia disambiguation pages
     # fmt: on
 ]
 
-WIKIPEDIA_LANGUAGES = {}
-LANGUAGES_SPARQL = ''
-IDS = None
-WIKIPEDIA_LANGUAGE_VARIANTS = {'zh_Hant': 'zh-tw'}
+WIKIPEDIA_LANGUAGES: dict[str, str] = {}
+LANGUAGES_SPARQL: str = ""
+IDS: str = ""
+WIKIPEDIA_LANGUAGE_VARIANTS: dict[str, str] = {"zh_Hant": "zh-tw"}
+
+# descriptions[engine][language] = [description, source]
+descriptions: dict[str, dict[str, list[str]]] = {}
+wd_to_engine_name: dict[str, set[str]] = {}
 
 
-descriptions = {}
-wd_to_engine_name = {}
-
-
-def normalize_description(description):
+def normalize_description(description: str):
     for c in [chr(c) for c in range(0, 31)]:
-        description = description.replace(c, ' ')
-    description = ' '.join(description.strip().split())
+        description = description.replace(c, " ")
+    description = " ".join(description.strip().split())
     return description
 
 
-def update_description(engine_name, lang, description, source, replace=True):
+def update_description(engine_name: str, lang: str, description: str, source: str, replace: bool = True) -> None:
     if not isinstance(description, str):
-        return
+        return  # pyright: ignore[reportUnreachable]
     description = normalize_description(description)
     if description.lower() == engine_name.lower():
         return
@@ -102,54 +103,71 @@ def update_description(engine_name, lang, description, source, replace=True):
         return
     if (engine_name, source) in SKIP_ENGINE_SOURCE:
         return
-    if ' ' not in description:
+    if " " not in description:
         # skip unique word description (like "website")
         return
     if replace or lang not in descriptions[engine_name]:
         descriptions[engine_name][lang] = [description, source]
 
 
-def get_wikipedia_summary(wikipedia_url, searxng_locale):
+def get_wikipedia_summary(wikipedia_url: str, searxng_locale: str):
     # get the REST API URL from the HTML URL
 
     # Headers
-    headers = {'User-Agent': searxng_useragent()}
+    headers = {
+        "User-Agent": gen_useragent(),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+        "Accept-Encoding": "gzip, deflate",
+        "DNT": "1",
+        "Upgrade-Insecure-Requests": "1",
+        "Sec-GPC": "1",
+        "Cache-Control": "max-age=0",
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "same-origin",
+        "Sec-Fetch-User": "?1",
+    }
 
     if searxng_locale in WIKIPEDIA_LANGUAGE_VARIANTS:
-        headers['Accept-Language'] = WIKIPEDIA_LANGUAGE_VARIANTS.get(searxng_locale)
+        headers["Accept-Language"] = WIKIPEDIA_LANGUAGE_VARIANTS[searxng_locale]
 
     # URL path : from HTML URL to REST API URL
     parsed_url = urlparse(wikipedia_url)
     # remove the /wiki/ prefix
-    article_name = parsed_url.path.split('/wiki/')[1]
+    article_name = parsed_url.path.split("/wiki/")[1]
     # article_name is already encoded but not the / which is required for the REST API call
-    encoded_article_name = article_name.replace('/', '%2F')
-    path = '/api/rest_v1/page/summary/' + encoded_article_name
+    encoded_article_name = article_name.replace("/", "%2F")
+    path = "/api/rest_v1/page/summary/" + encoded_article_name
     wikipedia_rest_url = parsed_url._replace(path=path).geturl()
     try:
         response = searx.network.get(wikipedia_rest_url, headers=headers, timeout=10)
         response.raise_for_status()
     except Exception as e:  # pylint: disable=broad-except
-        print("     ", wikipedia_url, e)
+        print("     get_wikipedia_summary: ", wikipedia_rest_url, e)
         return None
     api_result = json.loads(response.text)
-    return api_result.get('extract')
+    return api_result.get("extract")
 
 
-def get_website_description(url, lang1, lang2=None):
+def get_website_description(url: str, lang1: str | None, lang2: str | None = None):
     headers = {
-        'User-Agent': gen_useragent(),
-        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
-        'DNT': '1',
-        'Upgrade-Insecure-Requests': '1',
-        'Sec-GPC': '1',
-        'Cache-Control': 'max-age=0',
+        "User-Agent": gen_useragent(),
+        "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
+        "Accept-Encoding": "gzip, deflate",
+        "DNT": "1",
+        "Upgrade-Insecure-Requests": "1",
+        "Sec-GPC": "1",
+        "Cache-Control": "max-age=0",
+        "Sec-Fetch-Dest": "document",
+        "Sec-Fetch-Mode": "navigate",
+        "Sec-Fetch-Site": "same-origin",
+        "Sec-Fetch-User": "?1",
     }
     if lang1 is not None:
         lang_list = [lang1]
         if lang2 is not None:
             lang_list.append(lang2)
-        headers['Accept-Language'] = f'{",".join(lang_list)};q=0.8'
+        headers["Accept-Language"] = f'{",".join(lang_list)};q=0.8'
     try:
         response = searx.network.get(url, headers=headers, timeout=10)
         response.raise_for_status()
@@ -167,7 +185,7 @@ def get_website_description(url, lang1, lang2=None):
     if not description:
         description = extract_text(html.xpath('/html/head/title'))
     lang = extract_text(html.xpath('/html/@lang'))
-    if lang is None and len(lang1) > 0:
+    if lang is None and lang1 and len(lang1) > 0:
         lang = lang1
     lang = lang or 'en'
     lang = lang.split('_')[0]
@@ -178,15 +196,15 @@ def get_website_description(url, lang1, lang2=None):
 def initialize():
     global IDS, LANGUAGES_SPARQL
     searx.search.initialize()
-    wikipedia_engine = searx.engines.engines['wikipedia']
+    wikipedia_engine = searx.engines.engines["wikipedia"]
 
-    locale2lang = {'nl-BE': 'nl'}
+    locale2lang = {"nl-BE": "nl"}
     for sxng_ui_lang in LOCALE_NAMES:
 
         sxng_ui_alias = locale2lang.get(sxng_ui_lang, sxng_ui_lang)
         wiki_lang = None
 
-        if sxng_ui_alias in wikipedia_engine.traits.custom['WIKIPEDIA_LANGUAGES']:
+        if sxng_ui_alias in wikipedia_engine.traits.custom["WIKIPEDIA_LANGUAGES"]:
             wiki_lang = sxng_ui_alias
         if not wiki_lang:
             wiki_lang = wikipedia_engine.traits.get_language(sxng_ui_alias)
@@ -195,70 +213,84 @@ def initialize():
             continue
         WIKIPEDIA_LANGUAGES[sxng_ui_lang] = wiki_lang
 
-    LANGUAGES_SPARQL = ', '.join(f"'{l}'" for l in set(WIKIPEDIA_LANGUAGES.values()))
+    LANGUAGES_SPARQL = ", ".join(f"'{l}'" for l in set(WIKIPEDIA_LANGUAGES.values()))
     for engine_name, engine in searx.engines.engines.items():
         descriptions[engine_name] = {}
-        wikidata_id = getattr(engine, "about", {}).get('wikidata_id')
-        if wikidata_id is not None:
-            wd_to_engine_name.setdefault(wikidata_id, set()).add(engine_name)
+        if engine.about.wikidata_id:
+            wd_to_engine_name.setdefault(engine.about.wikidata_id, set()).add(engine_name)
 
-    IDS = ' '.join(list(map(lambda wd_id: 'wd:' + wd_id, wd_to_engine_name.keys())))
+    IDS = " ".join(list(map(lambda wd_id: "wd:" + wd_id, wd_to_engine_name.keys())))
 
 
 def fetch_wikidata_descriptions():
-    print('Fetching wikidata descriptions')
+    print("Fetching wikidata descriptions")
     searx.network.set_timeout_for_thread(60)
     result = wikidata.send_wikidata_query(
-        SPARQL_DESCRIPTION.replace('%IDS%', IDS).replace('%LANGUAGES_SPARQL%', LANGUAGES_SPARQL)
+        SPARQL_DESCRIPTION.replace("%IDS%", IDS).replace("%LANGUAGES_SPARQL%", LANGUAGES_SPARQL)
     )
-    if result is not None:
-        for binding in result['results']['bindings']:
-            wikidata_id = binding['item']['value'].replace('http://www.wikidata.org/entity/', '')
-            wikidata_lang = binding['itemDescription']['xml:lang']
-            desc = binding['itemDescription']['value']
-            for engine_name in wd_to_engine_name[wikidata_id]:
-                for searxng_locale in LOCALE_NAMES:
-                    if WIKIPEDIA_LANGUAGES[searxng_locale] != wikidata_lang:
-                        continue
-                    print(
-                        f"    engine: {engine_name:20} / wikidata_lang: {wikidata_lang:5}",
-                        f"/ len(wikidata_desc): {len(desc)}",
-                    )
-                    update_description(engine_name, searxng_locale, desc, 'wikidata')
+    if not result:
+        print("ERROR: fetching wikiDATA descriptions - SPARQL_DESCRIPTION query without results.")
+        return
+
+    for binding in result["results"]["bindings"]:
+        wikidata_id = binding["item"]["value"].replace("http://www.wikidata.org/entity/", "")
+        wikidata_lang = binding["itemDescription"]["xml:lang"]
+        desc = binding["itemDescription"]["value"]
+        for engine_name in wd_to_engine_name[wikidata_id]:
+            for searxng_locale in LOCALE_NAMES:
+                if WIKIPEDIA_LANGUAGES[searxng_locale] != wikidata_lang:
+                    continue
+                print(
+                    f"    engine: {engine_name:20} / wikidata_lang: {wikidata_lang:5}",
+                    f"/ len(wikidata_desc): {len(desc)}",
+                )
+                update_description(engine_name, searxng_locale, desc, "wikidata")
 
 
 def fetch_wikipedia_descriptions():
-    print('Fetching wikipedia descriptions')
+    print("Fetching wikipedia descriptions")
     result = wikidata.send_wikidata_query(
-        SPARQL_WIKIPEDIA_ARTICLE.replace('%IDS%', IDS).replace('%LANGUAGES_SPARQL%', LANGUAGES_SPARQL)
+        SPARQL_WIKIPEDIA_ARTICLE.replace("%IDS%", IDS).replace("%LANGUAGES_SPARQL%", LANGUAGES_SPARQL)
     )
-    if result is not None:
-        for binding in result['results']['bindings']:
-            wikidata_id = binding['item']['value'].replace('http://www.wikidata.org/entity/', '')
-            wikidata_lang = binding['name']['xml:lang']
-            wikipedia_url = binding['article']['value']  # for example the URL https://de.wikipedia.org/wiki/PubMed
-            for engine_name in wd_to_engine_name[wikidata_id]:
-                for searxng_locale in LOCALE_NAMES:
-                    if WIKIPEDIA_LANGUAGES[searxng_locale] != wikidata_lang:
-                        continue
-                    desc = get_wikipedia_summary(wikipedia_url, searxng_locale)
-                    if not desc:
-                        continue
-                    print(
-                        f"    engine: {engine_name:20} / wikidata_lang: {wikidata_lang:5}",
-                        f"/ len(wikipedia_desc): {len(desc)}",
-                    )
-                    update_description(engine_name, searxng_locale, desc, 'wikipedia')
+    if not result:
+        print("ERROR: fetching wikiPEDIA descriptions - SPARQL_WIKIPEDIA_ARTICLE query without results.")
+        return
+
+    # pylint: disable=too-many-nested-blocks
+    for binding in result["results"]["bindings"]:
+        wikidata_id = binding["item"]["value"].replace("http://www.wikidata.org/entity/", "")
+        wikidata_lang = binding["name"]["xml:lang"]
+        wikipedia_url = binding["article"]["value"]  # for example the URL https://de.wikipedia.org/wiki/PubMed
+        for engine_name in wd_to_engine_name[wikidata_id]:
+            for searxng_locale in LOCALE_NAMES:
+                if WIKIPEDIA_LANGUAGES[searxng_locale] != wikidata_lang:
+                    continue
+                desc = get_wikipedia_summary(wikipedia_url, searxng_locale)
+                if not desc:
+                    if descriptions.get(searxng_locale, {}).get(engine_name) is None:
+                        _descr = ENGINE_DESCRIPTIONS.get(searxng_locale, {}).get(engine_name)
+                        if _descr is not None:
+                            if len(_descr) == 2 and _descr[1] == 'ref':
+                                ref_engine, ref_lang = _descr[0].split(':')
+                                _descr = ENGINE_DESCRIPTIONS[ref_lang][ref_engine]
+                                update_description(engine_name, searxng_locale, _descr[0], _descr[1])
+
+                    continue
+                print(
+                    f"    engine: {engine_name:20} / wikidata_lang: {wikidata_lang:5}",
+                    f"/ len(wikipedia_desc): {len(desc)}",
+                )
+                update_description(engine_name, searxng_locale, desc, "wikipedia")
 
 
-def normalize_url(url):
-    url = url.replace('{language}', 'en')
-    url = urlparse(url)._replace(path='/', params='', query='', fragment='').geturl()
-    url = url.replace('https://api.', 'https://')
+def normalize_url(url: str):
+    url = url.replace("{language}", "en")
+    url = urlparse(url)._replace(path="/", params="", query="", fragment="").geturl()
+    url = url.replace("https://api.", "https://")
     return url
 
 
-def fetch_website_description(engine_name, website):
+def fetch_website_description(engine_name: str, website: str):
     print(f"- fetch website descr: {engine_name} / {website}")
     default_lang, default_description = get_website_description(website, None, None)
 
@@ -268,11 +300,11 @@ def fetch_website_description(engine_name, website):
 
     # to specify an order in where the most common languages are in front of the
     # language list ..
-    languages = ['en', 'es', 'pt', 'ru', 'tr', 'fr']
+    languages = ["en", "es", "pt", "ru", "tr", "fr"]
     languages = languages + [l for l in LOCALE_NAMES if l not in languages]
 
-    previous_matched_lang = None
-    previous_count = 0
+    previous_matched_lang: str | None = None
+    previous_count: int = 0
 
     for lang in languages:
 
@@ -307,19 +339,15 @@ def fetch_website_description(engine_name, website):
             f" / fetched lang: {fetched_lang:7} / len(desc): {len(desc)}"
         )
 
-        matched_lang = match_locale(fetched_lang, LOCALE_NAMES.keys(), fallback=lang)
+        matched_lang = match_locale(fetched_lang, list(LOCALE_NAMES.keys())) or lang
         update_description(engine_name, matched_lang, desc, website, replace=False)
 
 
 def fetch_website_descriptions():
-    print('Fetching website descriptions')
+    print("Fetching website descriptions")
     for engine_name, engine in searx.engines.engines.items():
-        website = getattr(engine, "about", {}).get('website')
-        if website is None and hasattr(engine, "search_url"):
-            website = normalize_url(getattr(engine, "search_url"))
-        if website is None and hasattr(engine, "base_url"):
-            website = normalize_url(getattr(engine, "base_url"))
-        if website is not None:
+        website = engine.about.website or getattr(engine, "search_url", "") or getattr(engine, "base_url", "")
+        if website:
             fetch_website_description(engine_name, website)
 
 
@@ -328,30 +356,32 @@ def get_engine_descriptions_filename():
 
 
 def get_output():
+    """Summary of the results, once known descriptions are not duplicated,
+    instead a reference is provided.
+
+    - from: ``descriptions[engine][language] = [description, source]``
+    - to: ``output[language][engine] = description_and_source``
+
+    ``description_and_source`` can be:
+
+    - ``[description, source]``
+    - ``description`` (if source = "wikipedia")
+    - ``[f"engine:lang", "ref"]`` reference to another existing description
+
     """
-    From descriptions[engine][language] = [description, source]
-    To
+    output: dict[str, dict[str, list[str] | str]] = {locale: {} for locale in LOCALE_NAMES}
+    seen_descriptions: dict[str, tuple[str, str]] = {}
 
-    * output[language][engine] = description_and_source
-    * description_and_source can be:
-       * [description, source]
-       * description (if source = "wikipedia")
-       * [f"engine:lang", "ref"] (reference to another existing description)
-    """
-    output = {locale: {} for locale in LOCALE_NAMES}
-
-    seen_descriptions = {}
-
-    for engine_name, lang_descriptions in descriptions.items():
-        for language, description in lang_descriptions.items():
-            if description[0] in seen_descriptions:
-                ref = seen_descriptions[description[0]]
-                description = [f'{ref[0]}:{ref[1]}', 'ref']
+    for engine_name, lang_descriptions in sorted(descriptions.items()):
+        for language, descr in sorted(lang_descriptions.items()):
+            if descr[0] in seen_descriptions:
+                ref = seen_descriptions[descr[0]]
+                descr = [f"{ref[0]}:{ref[1]}", "ref"]
             else:
-                seen_descriptions[description[0]] = (engine_name, language)
-                if description[1] == 'wikipedia':
-                    description = description[0]
-            output.setdefault(language, {}).setdefault(engine_name, description)
+                seen_descriptions[descr[0]] = (engine_name, language)
+                if descr[1] == "wikipedia":
+                    descr = descr[0]
+            output.setdefault(language, {}).setdefault(engine_name, descr)
 
     return output
 
@@ -363,8 +393,8 @@ def main():
     fetch_website_descriptions()
 
     output = get_output()
-    with DATA_FILE.open('w', encoding='utf8') as f:
-        f.write(json.dumps(output, indent=1, separators=(',', ':'), sort_keys=True, ensure_ascii=False))
+    with DATA_FILE.open("w", encoding="utf8") as f:
+        f.write(json.dumps(output, indent=1, separators=(",", ":"), sort_keys=True, ensure_ascii=False))
 
 
 if __name__ == "__main__":