[fix] container: ignore invalid SEARXNG_PORT values (#6439)

* [fix] container: ignore invalid SEARXNG_PORT values

* add note

---------

Co-authored-by: Ivan Gabaldon <igabaldon@inetol.net>

.dockerignore

@@ -1,5 +1,6 @@
 *
 
+!container/*.template.*
 !container/entrypoint.sh
 !searx/**
 !requirements*.txt

.github/workflows/container.yml

@@ -25,25 +25,21 @@ env:
 
 jobs:
   build:
-    if: github.repository_owner == 'searxng' || github.event_name == 'workflow_dispatch'
+    if: |
+      github.event_name == 'workflow_dispatch'
+      || (github.repository_owner == 'searxng' && github.event.workflow_run.conclusion == 'success')
     name: Build (${{ matrix.arch }})
-    runs-on: ${{ matrix.os }}
+    runs-on: ${{ matrix.runner }}
     strategy:
       fail-fast: false
       matrix:
         include:
-          - arch: amd64
+          - runner: ubuntu-26.04
-            march: amd64
+            arch: amd64
-            os: ubuntu-24.04
+          - runner: ubuntu-26.04-arm
-            emulation: false
+            arch: arm64
-          - arch: arm64
+          - runner: ubuntu-26.04-arm
-            march: arm64
+            arch: armv7
-            os: ubuntu-24.04-arm
-            emulation: false
-          - arch: armv7
-            march: arm64
-            os: ubuntu-24.04-arm
-            emulation: true
 
     permissions:
       packages: write
@@ -53,109 +49,82 @@ jobs:
       git_url: ${{ steps.build.outputs.git_url }}
 
     steps:
-      # yamllint disable rule:line-length
+      - name: Login to GHCR
-      - name: Setup podman
+        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0  # v4.4.0
-        env:
+        with:
-          PODMAN_VERSION: "v5.7.1"
+          registry: "ghcr.io"
-        run: |
+          username: "${{ github.repository_owner }}"
-          sudo apt-get purge -y podman runc crun conmon
+          password: "${{ secrets.GITHUB_TOKEN }}"
-
-          curl -fsSLO "https://github.com/mgoltzsche/podman-static/releases/download/${{ env.PODMAN_VERSION }}/podman-linux-${{ matrix.march }}.tar.gz"
-          curl -fsSLO "https://github.com/mgoltzsche/podman-static/releases/download/${{ env.PODMAN_VERSION }}/podman-linux-${{ matrix.march }}.tar.gz.asc"
-          gpg --keyserver hkps://keyserver.ubuntu.com --recv-keys 0CCF102C4F95D89E583FF1D4F8B5AF50344BB503
-          gpg --batch --verify "podman-linux-${{ matrix.march }}.tar.gz.asc" "podman-linux-${{ matrix.march }}.tar.gz"
-
-          tar -xzf "podman-linux-${{ matrix.march }}.tar.gz"
-          sudo cp -rfv ./podman-linux-${{ matrix.march }}/etc/. /etc/
-          sudo cp -rfv ./podman-linux-${{ matrix.march }}/usr/. /usr/
-
-          sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0
-      # 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: Setup QEMU
+        uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8  # v4.2.0
+
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
+          ref: "${{ github.event.workflow_run.head_sha || github.sha }}"
           persist-credentials: "false"
           fetch-depth: "0"
 
       - name: Setup cache Python
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
             python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-
           path: "./local/"
 
-      - name: Get date
-        id: date
-        run: echo "date=$(date +'%Y%m%d')" >>$GITHUB_OUTPUT
-
       - name: Setup cache container
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
-          key: "container-${{ matrix.arch }}-${{ steps.date.outputs.date }}-${{ hashFiles('./requirements*.txt') }}"
+          key: "container-${{ matrix.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
-            container-${{ matrix.arch }}-${{ steps.date.outputs.date }}-
             container-${{ matrix.arch }}-
           path: "/var/tmp/buildah-cache-*/*"
 
-      - if: ${{ matrix.emulation }}
-        name: Setup QEMU
-        uses: docker/setup-qemu-action@06116385d9baf250c9f4dcb4858b16962ea869c3  # v4.1.0
-
-      - name: Login to GHCR
-        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee  # v4.2.0
-        with:
-          registry: "ghcr.io"
-          username: "${{ github.repository_owner }}"
-          password: "${{ secrets.GITHUB_TOKEN }}"
-
       - name: Build
         id: build
         env:
           OVERRIDE_ARCH: "${{ matrix.arch }}"
-        run: make podman.build
+        run: make container.build
 
   test:
     name: Test (${{ matrix.arch }})
-    runs-on: ${{ matrix.os }}
+    runs-on: ${{ matrix.runner }}
     needs: build
     strategy:
       fail-fast: false
       matrix:
         include:
-          - arch: amd64
+          - runner: ubuntu-26.04
-            os: ubuntu-24.04
+            arch: amd64
-            emulation: false
+          - runner: ubuntu-26.04-arm
-          - arch: arm64
+            arch: arm64
-            os: ubuntu-24.04-arm
+          - runner: ubuntu-26.04-arm
-            emulation: false
+            arch: armv7
-          - arch: armv7
-            os: ubuntu-24.04-arm
-            emulation: true
 
     steps:
-      - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
-        with:
-          persist-credentials: "false"
-
-      - if: ${{ matrix.emulation }}
-        name: Setup QEMU
-        uses: docker/setup-qemu-action@06116385d9baf250c9f4dcb4858b16962ea869c3  # v4.1.0
-
       - name: Login to GHCR
-        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee  # v4.2.0
+        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0  # v4.4.0
         with:
           registry: "ghcr.io"
           username: "${{ github.repository_owner }}"
           password: "${{ secrets.GITHUB_TOKEN }}"
 
+      - name: Setup QEMU
+        uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8  # v4.2.0
+
+      - name: Checkout
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+        with:
+          ref: "${{ github.event.workflow_run.head_sha || github.sha }}"
+          persist-credentials: "false"
+
       - name: Test
         env:
           OVERRIDE_ARCH: "${{ matrix.arch }}"
@@ -165,7 +134,7 @@ jobs:
   release:
     if: github.repository_owner == 'searxng' && github.ref_name == 'master'
     name: Release
-    runs-on: ubuntu-24.04-arm
+    runs-on: ubuntu-26.04-arm
     needs:
       - build
       - test
@@ -174,24 +143,25 @@ jobs:
       packages: write
 
     steps:
-      - name: Checkout
+      - name: Login to Docker Hub
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0  # v4.4.0
         with:
-          persist-credentials: "false"
+          registry: "docker.io"
+          username: "${{ secrets.DOCKER_USER }}"
+          password: "${{ secrets.DOCKER_TOKEN }}"
 
       - name: Login to GHCR
-        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee  # v4.2.0
+        uses: docker/login-action@af1e73f918a031802d376d3c8bbc3fe56130a9b0  # v4.4.0
         with:
           registry: "ghcr.io"
           username: "${{ github.repository_owner }}"
           password: "${{ secrets.GITHUB_TOKEN }}"
 
-      - name: Login to Docker Hub
+      - name: Checkout
-        uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee  # v4.2.0
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
-          registry: "docker.io"
+          ref: "${{ github.event.workflow_run.head_sha || github.sha }}"
-          username: "${{ secrets.DOCKER_USER }}"
+          persist-credentials: "false"
-          password: "${{ secrets.DOCKER_TOKEN }}"
 
       - name: Release
         env:

.github/workflows/data-update.yml

@@ -21,7 +21,7 @@ jobs:
   data:
     if: github.repository_owner == 'searxng'
     name: ${{ matrix.fetch }}
-    runs-on: ubuntu-24.04-arm
+    runs-on: ubuntu-26.04-arm
     strategy:
       fail-fast: false
       matrix:
@@ -33,7 +33,6 @@ jobs:
           - update_engine_traits.py
           - update_wikidata_units.py
           - update_engine_descriptions.py
-          - update_gsa_useragents.py
 
     permissions:
       contents: write
@@ -41,17 +40,17 @@ 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@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -65,23 +64,17 @@ jobs:
         run: V=1 ./manage pyenv.cmd python "./searxng_extra/update/${{ matrix.fetch }}"
 
       - name: Create PR
-        id: cpr
         uses: peter-evans/create-pull-request@5f6978faf089d4d20b00c7766989d076bb2fc7f1  # v8.1.1
         with:
           author: "searxng-bot <searxng-bot@users.noreply.github.com>"
           committer: "searxng-bot <searxng-bot@users.noreply.github.com>"
-          title: "[data] update searx.data - ${{ matrix.fetch }}"
+          title: "[mod] data: update searx.data - ${{ matrix.fetch }}"
-          commit-message: "[data] update searx.data - ${{ matrix.fetch }}"
+          commit-message: "[mod] data: update searx.data - ${{ matrix.fetch }}"
-          branch: "update_data_${{ matrix.fetch }}"
+          branch: "ci-data-${{ matrix.fetch }}"
           delete-branch: "true"
           draft: "false"
           signoff: "false"
           body: |
-            [data] update searx.data - ${{ matrix.fetch }}
+            Update searx.data - ${{ matrix.fetch }}
           labels: |
             data
-
-      - name: Display information
-        run: |
-          echo "Pull Request Number - ${{ steps.cpr.outputs.pull-request-number }}"
-          echo "Pull Request URL - ${{ steps.cpr.outputs.pull-request-url }}"

.github/workflows/documentation.yml

@@ -25,25 +25,25 @@ jobs:
   release:
     if: github.repository_owner == 'searxng' || github.event_name == 'workflow_dispatch'
     name: Release
-    runs-on: ubuntu-24.04-arm
+    runs-on: ubuntu-26.04-arm
     permissions:
       # for JamesIves/github-pages-deploy-action to push
       contents: write
 
     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@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -65,7 +65,7 @@ jobs:
         with:
           folder: "dist/docs"
           branch: "gh-pages"
-          commit-message: "[doc] build from commit ${{ github.sha }}"
+          commit-message: "[mod] docs: build from commit ${{ github.sha }}"
           # Automatically remove deleted files from the deploy branch
           clean: "true"
           single-commit: "true"

.github/workflows/integration.yml

@@ -23,7 +23,7 @@ env:
 jobs:
   test:
     name: Python ${{ matrix.python-version }}
-    runs-on: ubuntu-24.04
+    runs-on: ubuntu-26.04
     strategy:
       matrix:
         python-version:
@@ -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@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
           key: "python-${{ matrix.python-version }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -59,37 +59,40 @@ jobs:
 
   theme:
     name: Theme
-    runs-on: ubuntu-24.04-arm
+    runs-on: ubuntu-26.04-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: Setup Node.js
+        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020  # v7.0.0
+        with:
+          node-version: "26"
+          check-latest: "true"
+
       - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
         with:
           persist-credentials: "false"
 
-      - name: Setup Node.js
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e  # v6.4.0
-        with:
-          node-version-file: "./.nvmrc"
-
-      - name: Setup cache Node.js
-        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
-        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@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
             python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-
           path: "./local/"
 
+      - name: Setup cache Node.js
+        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
+        with:
+          key: "nodejs-${{ runner.arch }}-${{ hashFiles('**/package-lock.json') }}"
+          restore-keys: |
+            nodejs-${{ runner.arch }}-
+          path: "./client/simple/node_modules/"
+
       - name: Setup venv
         run: make V=1 install
 

.github/workflows/l10n.yml

@@ -26,27 +26,27 @@ env:
 
 jobs:
   update:
-    if: github.repository_owner == 'searxng' && github.event.workflow_run.conclusion == 'success'
+    if: github.event.workflow_run.conclusion == 'success' && github.repository_owner == 'searxng'
     name: Update
-    runs-on: ubuntu-24.04-arm
+    runs-on: ubuntu-26.04-arm
     permissions:
       # For "make V=1 weblate.push.translations"
       contents: write
 
     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@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -59,7 +59,7 @@ jobs:
       - name: Setup Weblate
         run: |
           mkdir -p ~/.config
-          echo "${{ secrets.WEBLATE_CONFIG }}" > ~/.config/weblate
+          echo "${{ secrets.WEBLATE_CONFIG }}" >~/.config/weblate
 
       - name: Setup Git
         run: |
@@ -74,7 +74,7 @@ jobs:
       github.repository_owner == 'searxng'
       && (github.event_name == 'workflow_dispatch' || github.event_name == 'schedule')
     name: Pull Request
-    runs-on: ubuntu-24.04-arm
+    runs-on: ubuntu-26.04-arm
     permissions:
       # For "make V=1 weblate.translations.commit"
       contents: write
@@ -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@55cc8345863c7cc4c66a329aec7e433d2d1c52a9  # v6.1.0
         with:
           key: "python-${{ env.PYTHON_VERSION }}-${{ runner.arch }}-${{ hashFiles('./requirements*.txt') }}"
           restore-keys: |
@@ -107,7 +107,7 @@ jobs:
       - name: Setup Weblate
         run: |
           mkdir -p ~/.config
-          echo "${{ secrets.WEBLATE_CONFIG }}" > ~/.config/weblate
+          echo "${{ secrets.WEBLATE_CONFIG }}" >~/.config/weblate
 
       - name: Setup Git
         run: |
@@ -118,23 +118,17 @@ jobs:
         run: make V=1 weblate.translations.commit
 
       - name: Create PR
-        id: cpr
         uses: peter-evans/create-pull-request@5f6978faf089d4d20b00c7766989d076bb2fc7f1  # v8.1.1
         with:
           author: "searxng-bot <searxng-bot@users.noreply.github.com>"
           committer: "searxng-bot <searxng-bot@users.noreply.github.com>"
-          title: "[l10n] update translations from Weblate"
+          title: "[mod] i18n: update translations from Weblate"
-          commit-message: "[l10n] update translations from Weblate"
+          commit-message: "[mod] i18n: update translations from Weblate"
           branch: "translations_update"
           delete-branch: "true"
           draft: "false"
           signoff: "false"
           body: |
-            [l10n] update translations from Weblate
+            Update translations from Weblate
           labels: |
             area:i18n
-
-      - name: Display information
-        run: |
-          echo "Pull Request Number - ${{ steps.cpr.outputs.pull-request-number }}"
-          echo "Pull Request URL - ${{ steps.cpr.outputs.pull-request-url }}"

.github/workflows/security.yml

@@ -1,46 +0,0 @@
----
-name: Security
-
-# yamllint disable-line rule:truthy
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "42 05 * * *"
-
-concurrency:
-  group: ${{ github.workflow }}
-  cancel-in-progress: false
-
-permissions:
-  contents: read
-
-jobs:
-  container:
-    if: github.repository_owner == 'searxng'
-    name: Container
-    runs-on: ubuntu-24.04-arm
-    permissions:
-      security-events: write
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10  # v6.0.3
-        with:
-          persist-credentials: "false"
-
-      - name: Sync GHCS from Docker Scout
-        uses: docker/scout-action@cd72f264beff1cd72735de31148b9d3244a0234a  # v1.21.0
-        with:
-          organization: "searxng"
-          dockerhub-user: "${{ secrets.DOCKER_USER }}"
-          dockerhub-password: "${{ secrets.DOCKER_TOKEN }}"
-          image: "registry://ghcr.io/searxng/searxng:latest"
-          command: "cves"
-          sarif-file: "./scout.sarif"
-          exit-code: "false"
-          write-comment: "false"
-
-      - name: Upload SARIFs
-        uses: github/codeql-action/upload-sarif@8aad20d150bbac5944a9f9d289da16a4b0d87c1e  # v4.36.2
-        with:
-          sarif_file: "./scout.sarif"

Makefile

@@ -63,7 +63,7 @@ format: format.python format.shell
 # wrap ./manage script
 
 MANAGE += weblate.translations.commit weblate.push.translations
-MANAGE += data.all data.traits data.useragents data.gsa_useragents data.locales data.currencies
+MANAGE += data.all data.traits data.useragents data.locales data.currencies
 MANAGE += docs.html docs.live docs.gh-pages docs.prebuild docs.clean
 MANAGE += podman.build
 MANAGE += docker.build docker.buildx

client/simple/package.json

@@ -29,21 +29,21 @@
     "swiped-events": "1.2.0"
   },
   "devDependencies": {
-    "@biomejs/biome": "2.5.0",
+    "@biomejs/biome": "2.5.3",
-    "@types/node": "^25.9.3",
+    "@types/node": "^26.1.1",
-    "browserslist": "^4.28.2",
+    "browserslist": "^4.28.6",
     "browserslist-to-esbuild": "^2.1.1",
     "edge.js": "^6.5.1",
-    "less": "^4.6.4",
+    "less": "^4.6.7",
     "mathjs": "^15.2.0",
-    "sharp": "~0.35.1",
+    "sharp": "~0.35.3",
     "sort-package-json": "^4.0.0",
-    "stylelint": "^17.13.0",
+    "stylelint": "^17.14.0",
     "stylelint-config-standard-less": "^4.1.0",
     "stylelint-prettier": "^5.0.3",
-    "svgo": "^4.0.1",
+    "svgo": "^4.0.2",
-    "typescript": "~6.0.3",
+    "typescript": "~7.0.2",
-    "vite": "^8.0.16",
+    "vite": "^8.1.4",
     "vite-bundle-analyzer": "^1.3.8"
   }
 }

client/simple/src/js/main/results.ts

@@ -35,8 +35,9 @@ const imageLoader = (resultElement: HTMLElement): void => {
   }, 1000) as unknown as number;
 };
 
-const imageThumbnails: NodeListOf<HTMLImageElement> =
+const imageThumbnails: NodeListOf<HTMLImageElement> = document.querySelectorAll<HTMLImageElement>(
-  document.querySelectorAll<HTMLImageElement>("#urls img.image_thumbnail");
+  "#urls img.image_thumbnail, img.thumbnail"
+);
 for (const thumbnail of imageThumbnails) {
   if (thumbnail.complete && thumbnail.naturalWidth === 0) {
     thumbnail.src = `${settings.theme_static_path}/img/img_load_error.svg`;

client/simple/src/js/plugin/Calculator.ts

@@ -77,9 +77,9 @@ export default class Calculator extends Plugin {
 
   protected async run(): Promise<string | undefined> {
     const searchInput = getElement<HTMLInputElement>("q");
-    const node = Calculator.math.parse(searchInput.value);
 
     try {
+      const node = Calculator.math.parse(searchInput.value);
       return `${node.toString()} = ${node.evaluate()}`;
     } catch {
       // not a compatible math expression

container/builder.dockerfile

@@ -1,4 +1,4 @@
-FROM ghcr.io/searxng/base:searxng-builder AS builder
+FROM docker.io/searxng/base:searxng-builder AS builder
 
 COPY ./requirements.txt ./requirements-server.txt ./
 
@@ -21,8 +21,6 @@ RUN --mount=type=cache,id=uv,target=/root/.cache/uv set -eux -o pipefail; \
 
 COPY --exclude=./searx/version_frozen.py ./searx/ ./searx/
 
-ARG TIMESTAMP_SETTINGS="0"
-
 RUN set -eux -o pipefail; \
     python -m compileall -q -f -j 0 --invalidation-mode=unchecked-hash ./searx/; \
     find ./searx/static/ -type f \
@@ -30,5 +28,4 @@ RUN set -eux -o pipefail; \
     -exec gzip -9 -k {} + \
     -exec brotli -9 -k {} + \
     -exec gzip --test {}.gz + \
-    -exec brotli --test {}.br +; \
+    -exec brotli --test {}.br +
-    touch -c --date="@$TIMESTAMP_SETTINGS" ./searx/settings.yml

container/dist.dockerfile

@@ -2,7 +2,7 @@ ARG CONTAINER_IMAGE_ORGANIZATION="searxng"
 ARG CONTAINER_IMAGE_NAME="searxng"
 
 FROM localhost/$CONTAINER_IMAGE_ORGANIZATION/$CONTAINER_IMAGE_NAME:builder AS builder
-FROM ghcr.io/searxng/base:searxng AS dist
+FROM docker.io/searxng/base:searxng AS dist
 
 COPY --chown=977:977 --from=builder /usr/local/searxng/.venv/ ./.venv/
 COPY --chown=977:977 --from=builder /usr/local/searxng/searx/ ./searx/

container/entrypoint.sh

@@ -77,43 +77,23 @@ volume_handler() {
     setup_ownership "$target" "directory"
 }
 
-# Handle configuration file updates
+setup() {
-config_handler() {
+    local template_settings="/usr/local/searxng/settings.template.yml"
-    local target="$1"
+    local target_settings="$__SEARXNG_CONFIG_PATH/settings.yml"
-    local template="$2"
-    local new_template_target="$target.new"
 
-    # Create/Update the configuration file
+    if [ ! -f "$target_settings" ]; then
-    if [ -f "$target" ]; then
-        setup_ownership "$target" "file"
-
-        if [ "$template" -nt "$target" ]; then
-            cp -pfT "$template" "$new_template_target"
-
-            cat <<EOF
-...
-... INFORMATION
-... Update available for "$target"
-... It is recommended to update the configuration file to ensure proper functionality
-...
-... New version placed at "$new_template_target"
-... Please review and merge changes
-...
-EOF
-        fi
-    else
         cat <<EOF
 ...
 ... INFORMATION
-... "$target" does not exist, creating from template...
+... "$target_settings" does not exist, creating from template...
 ...
 EOF
-        cp -pfT "$template" "$target"
+        cp -pfT "$template_settings" "$target_settings"
 
-        sed -i "s/ultrasecretkey/$(head -c 24 /dev/urandom | base64 | tr -dc 'a-zA-Z0-9')/g" "$target"
+        sed -i "s/ultrasecretkey/$(head -c 24 /dev/urandom | base64 | tr -dc 'a-zA-Z0-9')/g" "$target_settings"
     fi
 
-    check_file "$target"
+    check_file "$target_settings"
 }
 
 cat <<EOF
@@ -124,8 +104,7 @@ EOF
 volume_handler "$__SEARXNG_CONFIG_PATH"
 volume_handler "$__SEARXNG_DATA_PATH"
 
-# Check for files
+setup
-config_handler "$__SEARXNG_SETTINGS_PATH" "/usr/local/searxng/searx/settings.yml"
 
 # root only features
 if [ "$(id -u)" -eq 0 ]; then
@@ -133,6 +112,15 @@ if [ "$(id -u)" -eq 0 ]; then
 fi
 
 # ENVs aliases
-export GRANIAN_PORT="${SEARXNG_PORT:-$GRANIAN_PORT}"
+# https://github.com/searxng/searxng/issues/5934
+case "${SEARXNG_PORT:-}" in
+    '') ;;
+    *[!0-9]*)
+        unset SEARXNG_PORT
+        ;;
+    *)
+        export GRANIAN_PORT="$SEARXNG_PORT"
+        ;;
+esac
 
 exec /usr/local/searxng/.venv/bin/granian searx.webapp:app

container/settings.template.yml

@@ -0,0 +1,8 @@
+# Read the documentation before extending the defaults:
+# https://docs.searxng.org/admin/settings/
+
+use_default_settings: true
+
+server:
+  secret_key: "ultrasecretkey"
+  image_proxy: true

docs/admin/installation-docker.rst

@@ -283,12 +283,12 @@ container images are not officially supported):
    $ make container
 
    $ docker images
-   REPOSITORY                 TAG                 IMAGE ID  CREATED             SIZE
+   REPOSITORY                 TAG                  IMAGE ID  SIZE
-   localhost/searxng/searxng  2025.8.1-3d96414    ...       About a minute ago  183 MB
+   localhost/searxng/searxng  2026.6.19-93f66bfb4  ...       265 MB
-   localhost/searxng/searxng  latest              ...       About a minute ago  183 MB
+   localhost/searxng/searxng  latest               ...       265 MB
-   localhost/searxng/searxng  builder             ...       About a minute ago  524 MB
+   localhost/searxng/searxng  builder              ...       687 MB
-   ghcr.io/searxng/base       searxng-builder     ...       2 days ago          378 MB
+   docker.io/searxng/base     searxng-builder      ...       565 MB
-   ghcr.io/searxng/base       searxng             ...       2 days ago          42.2 MB
+   docker.io/searxng/base     searxng              ...       143 MB
 
 Migrate from ``searxng-docker``
 ===============================

docs/dev/engines/online/aol.rst

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

docs/dev/search_api.rst

@@ -4,31 +4,32 @@
 Search API
 ==========
 
-SearXNG supports querying via a simple HTTP API.
+SearXNG supports querying via a simple HTTP API.  Two endpoints, ``/`` and
-Two endpoints, ``/`` and ``/search``, are supported for both GET and POST methods.
+``/search``, are supported for both GET and POST methods.  The ``GET`` method
-The GET method expects parameters as URL query parameters, while the POST method expects parameters as form data.
+expects parameters as URL query parameters, while the POST method expects
+parameters as form data (``application/x-www-form-urlencoded``).
 
 If you want to consume the results as JSON, CSV, or RSS, you need to set the
-``format`` parameter accordingly. Supported formats are defined in ``settings.yml``, under the ``search`` section.
+``format`` parameter accordingly.  Supported formats are defined in
-Requesting an unset format will return a 403 Forbidden error. Be aware that many public instances have these formats disabled.
+``settings.yml``, under the :ref:`settings search` section.  Requesting an
-
+unset format will return a 403 Forbidden error.  Be aware that many public
+instances have these formats disabled.
 
 Endpoints:
 
-``GET /``
+.. code::
-``GET /search``
 
-``POST /``
+   GET /
-``POST /search``
+   GET /search
+   POST /
+   POST /search
 
 example cURL calls:
 
-.. code-block:: bash
+.. code:: bash
 
    curl 'https://searx.example.org/search?q=searxng&format=json'
-
    curl -X POST 'https://searx.example.org/search' -d 'q=searxng&format=csv'
-
    curl -L -X POST -d 'q=searxng&format=json' 'https://searx.example.org/'
 
 Parameters
@@ -53,90 +54,27 @@ Parameters
   Comma separated list, specifies the active search categories (see
   :ref:`configured engines`)
 
-``engines`` : optional
-  Comma separated list, specifies the active search engines (see
-  :ref:`configured engines`).
-
 ``language`` : default from :ref:`settings search`
   Code of the language.
 
 ``pageno`` : default ``1``
   Search page number.
 
-``time_range`` : optional
+``time_range`` : optional : [ ``day``, ``month``, ``year`` ]
-  [ ``day``, ``month``, ``year`` ]
-
   Time range of search for engines which support it.  See if an engine supports
   time range search in the preferences page of an instance.
 
-``format`` : optional
+``format`` : optional :  [ ``json``, ``csv``, ``rss`` ]
-  [ ``json``, ``csv``, ``rss`` ]
-
   Output format of results.  Format needs to be activated in :ref:`settings
   search`.
 
-``results_on_new_tab`` : default ``0``
+``safesearch`` :  default from :ref:`settings search` : [ ``0``, ``1``, ``2`` ]
-  [ ``0``, ``1`` ]
-
-  Open search results on new tab.
-
-``image_proxy`` : default from :ref:`settings server`
-  [  ``True``, ``False`` ]
-
-  Proxy image results through SearXNG.
-
-``autocomplete`` : default from :ref:`settings search`
-  [ ``google``, ``dbpedia``, ``duckduckgo``, ``mwmbl``, ``startpage``,
-  ``privacywall``, ``wikipedia``, ``swisscows``, ``qwant`` ]
-
-  Service which completes words as you type.
-
-``safesearch`` :  default from :ref:`settings search`
-  [ ``0``, ``1``, ``2`` ]
-
   Filter search results of engines which support safe search.  See if an engine
   supports safe search in the preferences page of an instance.
 
-``theme`` : default ``simple``
+``theme`` : default ``simple`` : [ ``simple`` ]
-  [ ``simple`` ]
-
   Theme of instance.
 
   Please note, available themes depend on an instance.  It is possible that an
   instance administrator deleted, created or renamed themes on their instance.
   See the available options in the preferences page of the instance.
-
-``enabled_plugins`` : optional
-  List of enabled plugins.
-
-  :default:
-     ``Hash_plugin``, ``Self_Information``,
-     ``Tracker_URL_remover``, ``Ahmia_blacklist``
-
-  :values:
-     .. enabled by default
-
-     ``Hash_plugin``, ``Self_Information``,
-     ``Tracker_URL_remover``, ``Ahmia_blacklist``,
-
-     .. disabled by default
-
-     ``Hostnames_plugin``, ``Open_Access_DOI_rewrite``,
-     ``Vim-like_hotkeys``, ``Tor_check_plugin``
-
-``disabled_plugins``: optional
-  List of disabled plugins.
-
-  :default:
-     ``Hostnames_plugin``, ``Open_Access_DOI_rewrite``,
-     ``Vim-like_hotkeys``, ``Tor_check_plugin``
-
-  :values:
-     see values from ``enabled_plugins``
-
-``enabled_engines`` : optional : *all* :origin:`engines <searx/engines>`
-  List of enabled engines.
-
-``disabled_engines`` : optional : *all* :origin:`engines <searx/engines>`
-  List of disabled engines.
-

docs/user/configured_engines.rst

@@ -58,8 +58,8 @@ Configured Engines
       {% for mod in engines %}
 
       * - `{{mod.name}} <{{mod.about and mod.about.website}}>`_
-          {%- if mod.about and  mod.about.language %}
+          {%- if mod.language %}
-          ({{mod.about.language | upper}})
+          ({{mod.language | upper}})
           {%- endif %}
         - ``!{{mod.shortcut}}``
         - {%- if 'searx.engines.' + mod.__name__ in documented_modules %}

manage

@@ -48,7 +48,7 @@ PATH="${PY_ENV}/bin:${REPO_ROOT}/node_modules/.bin:${GOROOT}/bin:${GOPATH}/bin:$
 
 PYOBJECTS="searx"
 PY_SETUP_EXTRAS='[test]'
-GECKODRIVER_VERSION="v0.36.0"
+GECKODRIVER_VERSION="v0.37.0"
 # SPHINXOPTS=
 BLACK_OPTIONS=("--target-version" "py311" "--line-length" "120" "--skip-string-normalization")
 BLACK_TARGETS=("--exclude" "(searx/static|searx/languages.py)" "--include" 'searxng.msg|\.pyi?$' "searx" "searxng_extra" "tests")

requirements-dev.txt

@@ -2,27 +2,27 @@ 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==4.46.0
 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
 linuxdoc==20260504
 aiounittest==1.5.0
 yamllint==1.38.0
-wlc==2.0.0
+wlc==2.1.0
 coloredlogs==15.0.1
 docutils>=0.21.2;python_version <= "3.11"
 docutils>=0.22.4; python_version > "3.11"
 parameterized==0.9.0
-granian[reload]==2.7.6
+granian[reload]==2.7.9
-basedpyright==1.39.7
+basedpyright==1.39.9
 types-lxml==2026.2.16

requirements-server.txt

@@ -1,2 +1,2 @@
-granian==2.7.6
+granian==2.7.9
-granian[pname]==2.7.6
+granian[pname]==2.7.9

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
@@ -13,7 +13,7 @@ sniffio==1.3.1
 valkey==6.1.1
 markdown-it-py==4.2.0
 msgspec==0.21.1
-typer==0.26.7
+typer==0.27.0
 isodate==0.7.2
 whitenoise==6.12.0
-typing-extensions==4.15.0
+typing-extensions==4.16.0

searx/autocomplete.py

@@ -21,6 +21,8 @@ from searx.engines import (
 from searx.network import get as http_get, post as http_post
 from searx.exceptions import SearxEngineResponseException
 from searx.utils import extr, gen_useragent
+from searx.data import ENGINE_TRAITS
+from searx.enginelib.traits import EngineTraits
 
 if t.TYPE_CHECKING:
     from searx.extended_types import SXNG_Response
@@ -133,7 +135,9 @@ def google_complete(query: str, sxng_locale: str) -> list[str]:
 
     """
 
-    google_info: dict[str, t.Any] = google.get_google_info({'searxng_locale': sxng_locale}, engines['google'].traits)
+    data = ENGINE_TRAITS.get("google") or {}
+    traits = EngineTraits(**data)
+    google_info: dict[str, t.Any] = google.get_google_info({'searxng_locale': sxng_locale}, traits)
     url = 'https://{subdomain}/complete/search?{args}'
     args = urlencode(
         {

searx/cache.py

@@ -48,7 +48,7 @@ class ExpireCacheCfg(msgspec.Struct):  # pylint: disable=too-few-public-methods
     MAXHOLD_TIME: int = 60 * 60 * 24 * 7  # 7 days
     """Hold time (default in sec.), after which a value is removed from the cache."""
 
-    MAINTENANCE_PERIOD: int = 60 * 60  # 2h
+    MAINTENANCE_PERIOD: int = 60 * 60  # 1h
     """Maintenance period in seconds / when :py:obj:`MAINTENANCE_MODE` is set to
     ``auto``."""
 
@@ -458,12 +458,22 @@ class ExpireCacheSQLite(sqlitedb.SQLiteAppl, ExpireCache):
         # Before values are taken from the table, a maintenance interval may
         # need to be carried out.
         self.maintenance()
-        sql = f"SELECT value FROM {table} WHERE key = ?"
+        sql = f"SELECT value, expire FROM {table} WHERE key = ?"
         row = self.DB.execute(sql, (key,)).fetchone()
         if row is None:
             return default
 
-        return self.deserialize(row[0])
+        # Check if value is expired. It's possible that it's expired but has not
+        # yet been automatically deleted by the periodic maintenance
+        (value, expire) = row
+        now = time.time()
+        if expire < now:
+            # The record is deleted during the maintenance interval. Deleting
+            # the record at this point offers no advantage, as a SELECT
+            # statement must be executed for every cache.get request anyways.
+            return default
+
+        return self.deserialize(value)
 
     def pairs(self, ctx: str) -> Iterator[tuple[str, typing.Any]]:
         """Iterate over key/value pairs from table given by argument ``ctx``.

searx/data/__init__.py

@@ -6,7 +6,7 @@ make data.all
 """
 # pylint: disable=invalid-name
 
-__all__ = ["ahmia_blacklist_loader", "gsa_useragents_loader", "data_dir", "get_cache"]
+__all__ = ["ahmia_blacklist_loader", "data_dir", "get_cache"]
 
 import json
 import typing as t
@@ -63,7 +63,6 @@ lazy_globals = {
     "ENGINE_TRAITS": None,
     "LOCALES": None,
     "TRACKER_PATTERNS": TrackerPatternsDB(),
-    "GSA_USER_AGENTS": None,
 }
 
 data_json_files = {
@@ -106,24 +105,3 @@ def ahmia_blacklist_loader() -> list[str]:
     """
     with open(data_dir / 'ahmia_blacklist.txt', encoding='utf-8') as f:
         return f.read().split()
-
-
-def gsa_useragents_loader() -> list[str]:
-    """Load data from `gsa_useragents.txt` and return a list of user agents
-    suitable for Google.  The user agents are fetched by::
-
-      searxng_extra/update/update_gsa_useragents.py
-
-    This function is used by :py:mod:`searx.engines.google`.
-
-    """
-    data = lazy_globals["GSA_USER_AGENTS"]
-    if data is not None:
-        return data
-
-    log.debug("init searx.data.%s", "GSA_USER_AGENTS")
-
-    with open(data_dir / 'gsa_useragents.txt', encoding='utf-8') as f:
-        lazy_globals["GSA_USER_AGENTS"] = f.read().splitlines()
-
-    return lazy_globals["GSA_USER_AGENTS"]

searx/data/currencies.json

@@ -773,7 +773,7 @@
             "nl": "Boliviaanse boliviano",
             "oc": "Boliviano",
             "pa": "ਬੋਲੀਵੀਆਨੋ",
-            "pl": "boliviano",
+            "pl": "boliwiano",
             "pt": "Boliviano",
             "ro": "boliviano",
             "ru": "боливиано",
@@ -1107,7 +1107,7 @@
             "fi": "Kongon frangi",
             "fr": "franc congolais",
             "ga": "franc an Chongó",
-            "gl": "Franco congolés",
+            "gl": "franco congolés",
             "he": "פרנק קונגולזי",
             "hr": "Kongoanski franak",
             "hu": "kongói frank",
@@ -1636,7 +1636,7 @@
             "fi": "Algerian dinaari",
             "fr": "dinar algérien",
             "ga": "dinar na hAilgéire",
-            "gl": "Dinar alxeriano",
+            "gl": "dinar alxeriano",
             "he": "דינר אלג'ירי",
             "hr": "Alžirski dinar",
             "hu": "algériai dinár",
@@ -1651,7 +1651,7 @@
             "pap": "dinar argelino",
             "pl": "dinar algierski",
             "pt": "dinar argelino",
-            "ro": "Dinar algerian",
+            "ro": "dinar algerian",
             "ru": "алжирский динар",
             "sk": "Alžírský dinár",
             "sl": "alžirski dinar",
@@ -1786,7 +1786,7 @@
             "cy": "Ewro",
             "da": "Euro",
             "de": "Euro",
-            "en": "Euro",
+            "en": "euro",
             "eo": "eŭro",
             "es": "Euro",
             "et": "Euro",
@@ -1803,7 +1803,7 @@
             "it": "Euro",
             "ja": "ユーロ",
             "ko": "유로",
-            "lt": "Euras",
+            "lt": "euras",
             "lv": "eiro",
             "ml": "യൂറോ",
             "ms": "Euro",
@@ -2759,7 +2759,7 @@
             "pa": "ਜਪਾਨੀ ਯੈੱਨ",
             "pl": "jen",
             "pt": "iene",
-            "ro": "yeni",
+            "ro": "yen",
             "ru": "японская иена",
             "sk": "jen",
             "sl": "japonski jen",
@@ -3337,6 +3337,7 @@
             "fi": "Libyan dinaari",
             "fr": "dinar libyen",
             "ga": "dinar na Libia",
+            "gl": "dinar libio",
             "he": "דינר לובי ",
             "hr": "Libijski dinar",
             "hu": "líbiai dinár",
@@ -3539,6 +3540,7 @@
             "ja": "チャット",
             "ko": "미얀마 짯",
             "lt": "Kijatas",
+            "lv": "Kjats",
             "ml": "ബർമ്മീസ് ക്യാറ്റ്",
             "nl": "Myanmarese kyat",
             "oc": "Kyat",
@@ -4310,7 +4312,7 @@
             "ar": "بيسو فلبيني",
             "bg": "Филипинско песо",
             "ca": "peso filipí",
-            "cs": "Filipínské peso",
+            "cs": "filipínské peso",
             "de": "philippinischer Peso",
             "en": "Philippine peso",
             "eo": "filipina peso",
@@ -4614,7 +4616,7 @@
             "fi": "Serbian dinaari",
             "fr": "dinar serbe",
             "ga": "Dinar na Seirbia",
-            "gl": "Dinar serbio",
+            "gl": "dinar serbio",
             "he": "דינר סרבי",
             "hr": "srpski dinar",
             "hu": "szerb dinár",
@@ -5331,7 +5333,7 @@
             "pa": "ਤਾਜਿਕਿਸਤਾਨੀ ਸੋਮੋਨੀ",
             "pl": "Somoni",
             "pt": "Somoni",
-            "ro": "Somoni tadjic",
+            "ro": "somoni tadjic",
             "ru": "таджикский сомони",
             "sk": "tadžický som",
             "sl": "tadžikistanski somoni",
@@ -5394,6 +5396,7 @@
             "fi": "Tunisian dinaari",
             "fr": "dinar tunisien",
             "ga": "dinar na Túinéise",
+            "gl": "dinar tunisiano",
             "he": "דינר תוניסאי",
             "hr": "tuniski dinar",
             "hu": "tunéziai dinár",
@@ -5766,7 +5769,7 @@
             "fi": "Uruguayn peso",
             "fr": "peso uruguayen",
             "ga": "peso Uragua",
-            "gl": "Peso uruguaio",
+            "gl": "peso uruguaio",
             "he": "פסו של אורוגוואי",
             "hr": "Urugvajski pezo",
             "hu": "uruguayi peso",
@@ -6147,7 +6150,7 @@
             "oc": "Drechs de tiratge Especials",
             "pl": "specjalne prawa ciągnienia",
             "pt": "direitos especiais de saque",
-            "ro": "Drepturi speciale de tragere",
+            "ro": "drepturi speciale de tragere",
             "ru": "специальные права заимствования",
             "sk": "Zvláštne práva čerpania",
             "sl": "posebne pravice črpanja",
@@ -6225,6 +6228,7 @@
             "ja": "CFPフラン",
             "ko": "CFP 프랑",
             "lt": "CFP frankas",
+            "lv": "Klusā okeāna franks",
             "ms": "Franc CFP",
             "nl": "CFP-frank",
             "oc": "Franc CFP",
@@ -7055,6 +7059,7 @@
         "bolivjano": "BOB",
         "bolivya bolivianosu": "BOB",
         "bolivya bolivyanosu": "BOB",
+        "boliwiano": "BOB",
         "bolívar digital": "VED",
         "bolívar soberano": "VES",
         "bolívar sobirà": "VES",
@@ -8425,6 +8430,7 @@
         "drame arménio": "AMD",
         "dramm": "AMD",
         "drechs de tiratge especials": "XDR",
+        "drept special de tragere": "XDR",
         "drepturi speciale de tragere": "XDR",
         "drets especials de gir": "XDR",
         "droits de tirage speciaux": "XDR",
@@ -9518,6 +9524,8 @@
         "kíp lào": "LAK",
         "kīp": "LAK",
         "kjat": "MMK",
+        "kjats": "MMK",
+        "klusā okeāna franks": "XPF",
         "km": "BAM",
         "kmf": "KMF",
         "koeweitse dinar": "KWD",
@@ -10023,6 +10031,7 @@
         "lire sterline": "GBP",
         "lire turque": "TRY",
         "lisente": "LSL",
+        "list of syrian coins": "SYP",
         "liura de gibartar": "GIP",
         "liura egipciana": "EGP",
         "liura esterlina": "GBP",
@@ -11313,7 +11322,6 @@
         "riel camboxano": "KHR",
         "riel camboyano": "KHR",
         "riel campuchia": "KHR",
-        "riel kambodżański": "KHR",
         "riel kamboja": "KHR",
         "riel na cambóide": "KHR",
         "rietumāfrikas franks": "XOF",
@@ -12257,6 +12265,7 @@
         "thaise baht": "THB",
         "thajský baht": "THB",
         "thb": "THB",
+        "the australian dollar": "AUD",
         "thebe": "BWP",
         "third belarusian ruble": "BYN",
         "tical": "THB",
@@ -12740,6 +12749,7 @@
         "yen": "JPY",
         "yen giapponese": "JPY",
         "yen japones": "JPY",
+        "yen japonez": "JPY",
         "yen japonés": "JPY",
         "yeni": "JPY",
         "yeni i̇srail şekeli": "ILS",
@@ -12806,7 +12816,6 @@
         "zimbabwe zig": "ZWG",
         "zimbabwean dollar": "ZWL",
         "zimbabwean gold": "ZWG",
-        "zimbabwean zig": "ZWG",
         "zimbabwen kulta": "ZWG",
         "zimbabwiansky zlatý": "ZWG",
         "zimbabwský dolar": "ZWL",
@@ -12965,6 +12974,7 @@
             "FKP",
             "EGP"
         ],
+        "£S": "SYP",
         "£e": "EGP",
         "£s": "SYP",
         "¥": [
@@ -14959,6 +14969,8 @@
         "فورنت مجري": "HUF",
         "فورينت مجري": "HUF",
         "فِرَنْكٌ رُوَنْدِيٌّ": "RWF",
+        "قائمة النقود المعدنية السورية": "SYP",
+        "قائمة عملات سوريا المعدنية": "SYP",
         "ك": "KWD",
         "كتزال غواتيمالي": "GTQ",
         "كرونة آيسلندية": "ISK",

searx/data/useragents.json

@@ -5,7 +5,7 @@
     ],
     "ua": "Mozilla/5.0 ({os}; rv:{version}) Gecko/20100101 Firefox/{version}",
     "versions": [
-        "151.0",
+        "152.0",
-        "150.0"
+        "151.0"
     ]
 }

searx/data/wikidata_units.json

@@ -3272,7 +3272,7 @@
     "Q128822": {
         "si_name": "Q182429",
         "symbol": "kn",
-        "to_si_factor": 0.5144444444444445
+        "to_si_factor": 0.514
     },
     "Q12912288": {
         "si_name": null,

searx/enginelib/__init__.py

@@ -41,13 +41,13 @@ if t.TYPE_CHECKING:
     from searx.enginelib.traits import EngineTraits
     from searx.extended_types import SXNG_Response
     from searx.result_types import EngineResults
-    from searx.search.processors import OfflineParamTypes, OnlineParamTypes
+    from searx.search.processors import OfflineParamTypes, OnlineParamTypes, ProcessorType
 
 ENGINES_CACHE: ExpireCacheSQLite = ExpireCacheSQLite.build_cache(
     ExpireCacheCfg(
         name="ENGINES_CACHE",
         MAXHOLD_TIME=60 * 60 * 24 * 7,  # 7 days
-        MAINTENANCE_PERIOD=60 * 60,  # 2h
+        MAINTENANCE_PERIOD=60 * 60,  # 1h
         MAX_VALUE_LEN=1024 * 1024 * 1024,  # 1MB
     )
 )
@@ -180,7 +180,7 @@ class EngineCache:
         return ENGINES_CACHE.secret_hash(name=name)
 
 
-class EngineAbout(msgspec.Struct):
+class EngineAbout(msgspec.Struct, kw_only=True):
     """Additional fields describing the engine.
 
     .. code:: yaml
@@ -207,19 +207,22 @@ class EngineAbout(msgspec.Struct):
 
     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."""
 
     results: str = ""
     """Data format of the source (online-engines: of the response)."""
 
-    language: str = ""
+    description: str = ""
-    """If the engine supports only one language, this language is specified
+    """Brief description of the engine and where it gets its data from.
-    here (``en``, ``de``, ``"no"`` or ..); otherwise, the value remains empty.
 
-    For the YAML configuration: think of the `YAML-Norway problem
+    This value should only be set as long as no description of the data source
-    <https://ruuda.nl/2023/the-yaml-document-from-hell#the-norway-problem>`_
+    is available via a :py:obj:`EngineAbout.wikidata_id`."""
-    """
+
+    language: str = ""
+    """Deprecated! Migrate your setting from `engine.about.language` to
+    `engine.language`"""
 
 
 class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
@@ -227,6 +230,8 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
 
     Further documentation see :ref:`general engine configuration`.
 
+    The defaults are taken from :py:obj:`searx.engines.ENGINE_DEFAULT_ARGS`.
+
     .. hint::
 
        This class is currently never initialized and only used for type hinting.
@@ -234,49 +239,27 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
 
     logger: logging.Logger
 
-    # Common options in the engine module
+    # Common options of the engine module
 
-    engine_type: str
+    engine_type: "ProcessorType" = "online"
     """Type of the engine (:ref:`searx.search.processors`)"""
 
-    paging: bool
+    paging: bool = False
     """Engine supports multiple pages."""
 
     max_page: int = 0
     """If the engine supports paging, then this is the value for the last page
     that is still supported. ``0`` means unlimited numbers of pages."""
 
-    time_range_support: bool
+    time_range_support: bool = False
     """Engine supports search time range."""
 
-    safesearch: bool
+    safesearch: bool = False
     """Engine supports SafeSearch"""
 
-    language_support: bool
+    language_support: bool = False
     """Engine supports languages (locales) search."""
 
-    language: str
-    """For an engine, when there is ``language: ...`` in the YAML settings the engine
-    does support only this one language:
-
-    .. code:: yaml
-
-      - name: google french
-        engine: google
-        language: fr
-    """
-
-    region: str
-    """For an engine, when there is ``region: ...`` in the YAML settings the engine
-    does support only this one region::
-
-    .. code:: yaml
-
-      - name: google belgium
-        engine: google
-        region: fr-BE
-    """
-
     fetch_traits: "Callable[[EngineTraits, bool], None]"
     """Function to to fetch engine's traits from origin."""
 
@@ -285,9 +268,6 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
 
     # settings.yml
 
-    categories: list[str]
-    """Specifies to which :ref:`engine categories` the engine should be added."""
-
     name: str
     """Name that will be used across SearXNG to define this engine.  In settings, on
     the result page .."""
@@ -297,6 +277,43 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
     this search engine (file name from :origin:`searx/engines` without
     ``.py``)."""
 
+    categories: list[str] = ["general"]
+    """Specifies to which :ref:`engine categories` the engine should be added."""
+
+    language: str = ""
+    """If the engine supports only one language, this language is specified here
+    (``en``, ``de``, ``"no"`` or ..); otherwise, the value remains empty. For
+    the YAML configuration: think of the `YAML-Norway problem
+    <https://ruuda.nl/2023/the-yaml-document-from-hell#the-norway-problem>`_
+
+    .. code:: yaml
+
+      - name: google norway
+        engine: google
+        language: "no"
+
+    Depending on ``language_support``, this value has similar but also slightly
+    different meanings.
+
+    - When ``language_support`` is **true**, the map of
+      :py:obj:`traits.EngineTraits.languages` is reduced to the selected
+      language
+
+    - When ``language_support`` is **false**, then the implementation of the
+      engine only supports this one ``language``
+    """
+
+    region: str = ""
+    """For an engine, when there is ``region: ...`` in the YAML settings the engine
+    does support only this one region::
+
+    .. code:: yaml
+
+      - name: google belgium
+        engine: google
+        region: fr-BE
+    """
+
     enable_http: bool
     """Enable HTTP (by default only HTTPS is enabled)."""
 
@@ -309,6 +326,31 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
     display_error_messages: bool
     """Display error messages on the web UI."""
 
+    disabled: bool = False
+    """To disable by default the engine, but not deleting it.  It will allow the
+    user to manually activate it in the settings."""
+
+    inactive: bool = False
+    """Remove the engine from the settings (*disabled & removed*)."""
+
+    about: EngineAbout = EngineAbout()
+    """Additional fields describing the engine."""
+
+    using_tor_proxy: bool = False
+    """Using tor proxy (``true``) or not (``false``) for this engine."""
+
+    send_accept_language_header: bool = True
+    """When this option is activated (default), the language (locale) that is
+    selected by the user is used to build and send a ``Accept-Language`` header
+    in the request to the origin search engine."""
+
+    tokens: list[str] = []
+    """A list of secret tokens to make this engine *private*, more details see
+    :ref:`private engines`."""
+
+    weight: float = 1.0
+    """Weighting of the results of this engine (:ref:`weight <settings engines>`)."""
+
     proxies: dict[str, dict[str, str]]
     """Set proxies for a specific engine (YAML):
 
@@ -319,62 +361,43 @@ class Engine(abc.ABC):  # pylint: disable=too-few-public-methods
          https: socks5://proxy:port
     """
 
-    disabled: bool
+    def setup(self, engine_settings: dict[str, t.Any]) -> bool | None:  # pylint: disable=unused-argument
-    """To disable by default the engine, but not deleting it.  It will allow the
-    user to manually activate it in the settings."""
-
-    inactive: bool
-    """Remove the engine from the settings (*disabled & removed*)."""
-
-    about: EngineAbout
-    """Additional fields describing the engine."""
-
-    using_tor_proxy: bool
-    """Using tor proxy (``true``) or not (``false``) for this engine."""
-
-    send_accept_language_header: bool
-    """When this option is activated (default), the language (locale) that is
-    selected by the user is used to build and send a ``Accept-Language`` header
-    in the request to the origin search engine."""
-
-    tokens: list[str]
-    """A list of secret tokens to make this engine *private*, more details see
-    :ref:`private engines`."""
-
-    weight: int
-    """Weighting of the results of this engine (:ref:`weight <settings engines>`)."""
-
-    def setup(self, engine_settings: dict[str, t.Any]) -> bool:  # pylint: disable=unused-argument
         """Dynamic setup of the engine settings.
 
         With this method, the engine's setup is carried out.  For example, to
         check or dynamically adapt the values handed over in the parameter
-        ``engine_settings``.  The return value (True/False) indicates whether
+        ``engine_settings``.
-        the setup was successful and the engine can be built or rejected.
 
-        The method is optional and is called synchronously as part of the
+        Whether the initialization was successful can be indicated by the return
+        value ``True`` or even ``False``.
+
+        - If no return value (``None`` ) is given from this method , this is
+          equivalent to ``True``.
+
+        - If an exception is thrown as part of the initialization, this is
+          equivalent to ``False``.
+
+        The method is optional and is called **synchronously** as part of the
         initialization of the service and is therefore only suitable for simple
-        (local) exams/changes at the engine setting.  The :py:obj:`Engine.init`
+        (local) exams/changes at the engine setting.
-        method must be used for longer tasks in which values of a remote must be
+
-        determined, for example.
+        The :py:obj:`Engine.init` method must be used for longer tasks in which
+        values of a remote must be determined, for example.
         """
         return True
 
     def init(self, engine_settings: dict[str, t.Any]) -> bool | None:  # pylint: disable=unused-argument
         """Initialization of the engine.
 
-        The method is optional and asynchronous (in a thread).  It is suitable,
+        The method is optional and called **asynchronous** (in a thread).  The
-        for example, for setting up a cache (for the engine) or for querying
+        method is comparable to :py:obj:`Engine.setup`, it is suitable, for
-        values (required by the engine) from a remote.
+        caching data that first needs to be requested from a remote.
 
-        Whether the initialization was successful can be indicated by the return
+        The method is optional and runs **asynchronously** (in a thread), it is
-        value ``True`` or even ``False``.
+        comparable to :py:obj:`Engine.setup`. For instance, it is suitable for
+        caching data that first needs to be requested from a remote source.
 
-        - If no return value is given from this init method (``None``), this is
+        The evaluation of the return value is analogous to :py:obj:`Engine.setup`.
-          equivalent to ``True``.
-
-        - If an exception is thrown as part of the initialization, this is
-          equivalent to ``False``.
         """
         return True
 

searx/enginelib/traits.py

@@ -142,11 +142,11 @@ class EngineTraits:
         """
 
         if self.data_type == "traits_v1":
-            self._set_traits_v1(engine)
+            self._set_traits_v1(engine)  # pyright: ignore[reportArgumentType]
         else:
             raise TypeError("engine traits of type %s is unknown" % self.data_type)
 
-    def _set_traits_v1(self, engine: "Engine | types.ModuleType") -> None:
+    def _set_traits_v1(self, engine: "Engine") -> None:
         # For an engine, when there is `language: ...` in the YAML settings the engine
         # does support only this one language (region)::
         #
@@ -159,22 +159,25 @@ class EngineTraits:
 
         _msg = "settings.yml - engine: '%s' / %s: '%s' not supported"
 
-        languages = traits.languages
+        if engine.language:
-        if hasattr(engine, "language"):
+            if engine.language_support:
-            if engine.language not in languages:
+                if not len(traits.languages) > 1:
-                raise ValueError(_msg % (engine.name, "language", engine.language))
+                    raise ValueError(
-            traits.languages = {engine.language: languages[engine.language]}
+                        f"engine {engine.name}: activated language_support with just one or less languages"
+                    )
+                if engine.language not in traits.languages:
+                    raise ValueError(_msg % (engine.name, "language", engine.language))
+                traits.languages = {engine.language: traits.languages[engine.language]}
 
-        regions = traits.regions
+        if engine.region:
-        if hasattr(engine, "region"):
+            if engine.region not in traits.regions:
-            if engine.region not in regions:
                 raise ValueError(_msg % (engine.name, "region", engine.region))
-            traits.regions = {engine.region: regions[engine.region]}
+            traits.regions = {engine.region: traits.regions[engine.region]}
 
         engine.language_support = bool(traits.languages or traits.regions)
 
         # set the copied & modified traits in engine's namespace
-        engine.traits = traits  # pyright: ignore[reportAttributeAccessIssue]
+        engine.traits = traits
 
 
 class EngineTraitsMap(dict[str, EngineTraits]):

searx/engines/360search.py

@@ -22,8 +22,8 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": "HTML",
-    "language": "zh",
 }
+language = "zh"
 
 # Engine Configuration
 categories = ["general"]

searx/engines/__builtins__.pyi

@@ -5,19 +5,19 @@ intended monkey patching of the engine modules.
 .. attention::
 
    Monkey-patching modules is a practice from the past that shouldn't be
-   expanded upon.  In the long run, there should be an engine class that can be
+   expanded upon.  In the long run, engines should be instances of
-   inherited.  However, as long as this class doesn't exist, and as long as all
+   :py:obj:`searx.enginelib.Engine`. However, as long as long as all engine
-   engine modules aren't converted to an engine class, these builtin types will
+   modules aren't converted to this class, these builtin types will still be
-   still be needed.
+   needed.
 """
 
 import logging
 from searx.enginelib import traits as _traits
 
 logger: logging.Logger
-supported_languages: str
-language_aliases: str
 language_support: bool
+language: str
+region: str
 traits: _traits.EngineTraits
 
 # from searx.engines.ENGINE_DEFAULT_ARGS

searx/engines/__init__.py

@@ -14,40 +14,48 @@ import sys
 import copy
 import os
 from os.path import realpath, dirname
+import warnings
 
 import types
 import inspect
+import msgspec
 
 from searx import logger, settings
 from searx.utils import load_module
-
+from searx.data import ENGINE_TRAITS
-if t.TYPE_CHECKING:
+from searx.enginelib import Engine, EngineAbout
-    from searx.enginelib import Engine
 
 logger = logger.getChild('engines')
 ENGINE_DIR = dirname(realpath(__file__))
 
 # Defaults for the namespace of an engine module, see load_engine()
-ENGINE_DEFAULT_ARGS: dict[str, int | str | list[t.Any] | dict[str, t.Any] | bool] = {
+ENGINE_DEFAULT_ARGS: dict[str, t.Any] = {
     # Common options in the engine module
     "engine_type": "online",
     "paging": False,
+    "max_page": 0,
     "time_range_support": False,
     "safesearch": False,
+    "language_support": False,
     # settings.yml
     "categories": ["general"],
+    "language": "",
+    "region": "",
     "enable_http": False,
     "shortcut": "-",
     "timeout": settings["outgoing"]["request_timeout"],
     "display_error_messages": True,
     "disabled": False,
     "inactive": False,
-    "about": {},
+    "about": EngineAbout(),
     "using_tor_proxy": False,
     "send_accept_language_header": True,
     "tokens": [],
-    "max_page": 0,
+    "weight": 1.0,
 }
+"""Default values that are set in an engine of type *module*, please compare
+with the class :py:obj:`searx.enginelib.Engine`."""
+
 # set automatically when an engine does not have any tab category
 DEFAULT_CATEGORY = 'other'
 
@@ -177,14 +185,41 @@ def set_loggers(engine: "Engine|types.ModuleType", engine_name: str):
 
 
 def update_engine_attributes(engine: "Engine | types.ModuleType", engine_data: dict[str, t.Any]):
+    # pylint: disable=too-many-branches
+
     # set engine attributes from engine_data
+    kvargs: dict[str, t.Any]
+    if isinstance(engine.about, EngineAbout):
+        kvargs = {**msgspec.to_builtins(engine.about), **engine_data.get("about", {})}
+    else:
+        kvargs = {**engine.about, **engine_data.get("about", {})}
+
+    try:
+        engine.about = EngineAbout(**kvargs)
+    except TypeError as exc:
+        raise TypeError(
+            f"engine '{engine_data['name']}' ({engine_data['engine']}) - in the about section --> {exc}"
+        ) from exc
+
+    # warn about deprecated engine settings
+
+    if engine.about.language:
+        if hasattr(engine, "language") and not engine.language:
+            engine.language = engine.about.language
+        warnings.warn(
+            f"engine '{engine_data['name']}' ({engine_data['engine']})"
+            f" - migrate engine.about.language to engine.language!",
+            DeprecationWarning,
+            2,
+        )
+
     for param_name, param_value in engine_data.items():
+        if param_name == "about":
+            continue
         if param_name == 'categories':
             if isinstance(param_value, str):
                 param_value = list(map(str.strip, param_value.split(',')))
             engine.categories = param_value  # type: ignore
-        elif hasattr(engine, 'about') and param_name == 'about':
-            engine.about = {**engine.about, **engine_data['about']}  # type: ignore
         else:
             setattr(engine, param_name, param_value)
 
@@ -193,6 +228,9 @@ def update_engine_attributes(engine: "Engine | types.ModuleType", engine_data: d
         if not hasattr(engine, arg_name):
             setattr(engine, arg_name, copy.deepcopy(arg_value))
 
+    if ENGINE_TRAITS.get(engine.name, {}).get("languages") and not engine.language_support:
+        raise ValueError(f"engine '{engine.name}' ({engine_data['engine']}) language_support should be set to True")
+
 
 def update_attributes_for_tor(engine: "Engine | types.ModuleType"):
     if using_tor_proxy(engine) and hasattr(engine, 'onion_url'):
@@ -231,21 +269,27 @@ def is_engine_active(engine: "Engine | types.ModuleType"):
 
 
 def call_engine_setup(engine: "Engine | types.ModuleType", engine_data: dict[str, t.Any]) -> bool:
-    setup_ok = False
+
+    setup_ok: bool | None = False
     setup_func = getattr(engine, "setup", None)
 
     if setup_func is None:
         setup_ok = True
     elif not callable(setup_func):
-        logger.error("engine's setup method isn't a callable (is of type: %s)", type(setup_func))
+        logger.error(f"engine's setup method isn't a callable (is of type: {type(setup_func)})")
     else:
         try:
             setup_ok = engine.setup(engine_data)
         except Exception as e:  # pylint: disable=broad-except
-            logger.exception('exception : {0}'.format(e))
+            logger.exception(f"(PID {os.getpid()}) {engine.name}: engine SETUP failed, exception: {e}")
+            setup_ok = False
+
+    # The evaluation of the return value is analogous to Engine.init
+    if setup_ok is None:
+        setup_ok = True
 
     if not setup_ok:
-        logger.error("%s: Engine setup was not successful, engine is set to inactive.", engine.name)
+        logger.error(f"(PID {os.getpid()}) {engine.name}: engine setup was not successful")
     return setup_ok
 
 
@@ -273,14 +317,16 @@ def load_engines(engine_list: list[dict[str, t.Any]]):
     for engine_data in engine_list:
         if engine_data.get("inactive") is True:
             continue
+
         engine = load_engine(engine_data)
+
         if engine:
             register_engine(engine)
         else:
             # if an engine can't be loaded (if for example the engine is missing
             # tor or some other requirements) its set to inactive!
             logger.error(
-                f"(PID {os.getpid()}) loading engine %s failed: set engine to inactive!", engine_data.get("name", "???")
+                f"(PID {os.getpid()}) {engine_data.get('name', '???')}: can't register engine (loading engine failed)"
             )
             engine_data["inactive"] = True
     return engines

searx/engines/acfun.py

@@ -16,12 +16,12 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": "HTML",
-    "language": "zh",
 }
 
 # Engine Configuration
 categories = ["videos"]
 paging = True
+language = "zh"
 
 # Base URL
 base_url = "https://www.acfun.cn"
@@ -83,7 +83,7 @@ def extract_video_data(video_block):
         published_date = None
         if create_time:
             try:
-                published_date = datetime.strptime(create_time.strip(), "%Y-%m-%d")
+                published_date = datetime.fromisoformat(create_time.strip())
             except (ValueError, TypeError):
                 pass
 

searx/engines/annas_archive.py

@@ -64,6 +64,7 @@ about: dict[str, t.Any] = {
 # engine dependent config
 categories = ["files", "books"]
 paging: bool = True
+language_support = True
 
 # search-url
 base_url: list[str] | str = []

searx/engines/ansa.py

@@ -42,8 +42,8 @@ about = {
     'use_official_api': False,
     'require_api_key': False,
     'results': 'HTML',
-    'language': 'it',
 }
+language = "it"
 
 
 def request(query, params):

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/archlinux.py

@@ -35,6 +35,7 @@ about = {
 categories = ["it", "software wikis"]
 paging = True
 main_wiki = "wiki.archlinux.org"
+language_support = True
 
 
 def request(query, params):

searx/engines/arxiv.py

@@ -109,7 +109,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
         comments_elements = eval_xpath_getindex(entry, xpath_comment, 0, default=None)
         comments: str = "" if comments_elements is None else comments_elements.text
 
-        publishedDate = datetime.strptime(eval_xpath_getindex(entry, xpath_published, 0).text, "%Y-%m-%dT%H:%M:%SZ")
+        publishedDate = datetime.fromisoformat(eval_xpath_getindex(entry, xpath_published, 0).text.rstrip("Z"))
 
         res.add(
             res.types.Paper(

searx/engines/azure.py

@@ -54,8 +54,8 @@ about = {
     "use_official_api": True,
     "require_api_key": True,
     "results": "JSON",
-    "language": "en",
 }
+language = "en"
 
 CACHE: EngineCache
 """Persistent (SQLite) key/value cache that deletes its values after ``expire``

searx/engines/baidu.py

@@ -7,13 +7,17 @@
 # There exits a https://github.com/ohblue/baidu-serp-api/
 # but we don't use it here (may we can learn from).
 
+import typing as t
+
 from urllib.parse import urlencode
 from datetime import datetime
 from html import unescape
 import time
 import json
 
-from searx.exceptions import SearxEngineAPIException, SearxEngineCaptchaException
+from searx.exceptions import SearxEngineAPIException, SearxEngineCaptchaException, SearxEngineAccessDeniedException
+from searx.enginelib import EngineCache
+from searx.network import get as http_get
 from searx.utils import html_to_text
 
 about = {
@@ -23,8 +27,8 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": "JSON",
-    "language": "zh",
 }
+language = "zh"
 
 paging = True
 categories = []
@@ -35,6 +39,31 @@ baidu_category = 'general'
 time_range_support = True
 time_range_dict = {"day": 86400, "week": 604800, "month": 2592000, "year": 31536000}
 
+image_base_url = "https://image.baidu.com/"
+
+COOKIE_CACHE_KEY = "cookie"
+COOKIE_CACHE_EXPIRATION_SECONDS = 3600
+
+CACHE: EngineCache
+"""Stores cookies from Baidu image search warmup."""
+
+
+def setup(engine_settings: dict[str, t.Any]) -> bool:
+    global CACHE  # pylint: disable=global-statement
+    CACHE = EngineCache(engine_settings["name"])
+    return True
+
+
+def get_image_cookies(headers: dict[str, str]) -> dict[str, str]:
+    cookies: dict[str, str] | None = CACHE.get(COOKIE_CACHE_KEY)
+    if cookies:
+        return cookies
+
+    warmup = http_get(image_base_url, headers=headers, timeout=10)
+    cookies = dict(warmup.cookies.items())
+    CACHE.set(key=COOKIE_CACHE_KEY, value=cookies, expire=COOKIE_CACHE_EXPIRATION_SECONDS)
+    return cookies
+
 
 def init(_):
     if baidu_category not in ('general', 'images', 'it'):
@@ -88,6 +117,9 @@ def request(query, params):
         if baidu_category == 'it':
             query_params["paramList"] += f",timestamp_range={past}-{now}"
 
+    if baidu_category == 'images':
+        params["cookies"] = get_image_cookies(params["headers"])
+
     params["url"] = f"{query_url}?{urlencode(query_params)}"
     params["allow_redirects"] = False
     return params
@@ -103,6 +135,8 @@ def response(resp):
         # baidu's JSON encoder wrongly quotes / and ' characters by \\ and \'
         text = text.replace(r"\/", "/").replace(r"\'", "'")
     data = json.loads(text, strict=False)
+    if data.get("antiFlag") == 1:
+        raise SearxEngineAccessDeniedException(data.get("message", "Forbid spider access"))
     parsers = {'general': parse_general, 'images': parse_images, 'it': parse_it}
 
     return parsers[baidu_category](data)
@@ -152,7 +186,7 @@ def parse_images(data):
             img_date = item.get("bdImgnewsDate")
             publishedDate = None
             if img_date:
-                publishedDate = datetime.strptime(img_date, "%Y-%m-%d %H:%M")
+                publishedDate = datetime.fromisoformat(img_date)
             results.append(
                 {
                     "template": "images.html",

searx/engines/bilibili.py

@@ -8,6 +8,7 @@ import random
 import string
 from urllib.parse import urlencode
 from datetime import datetime, timedelta
+from zoneinfo import ZoneInfo
 
 from searx import utils
 
@@ -39,6 +40,32 @@ cookie = {
     "home_feed_column": "4",
 }
 
+_CN_TZ = ZoneInfo("Asia/Shanghai")
+
+# Calendar-day time filter (Asia/Shanghai); dict values are days to subtract from today.
+time_range_support = True
+time_range_dict = {"day": 0, "week": 6, "month": 29, "year": 364}
+
+
+def _pubtime_range(time_range: str) -> tuple[int, int]:
+    """Return ``(pubtime_begin_s, pubtime_end_s)`` for Bilibili's search API.
+
+    Time ranges follow Bilibili's website semantics: they are counted in
+    **calendar days** in China Standard Time (``Asia/Shanghai``), not as
+    sliding 24-hour windows.  For example, ``day`` means from 00:00:00 to
+    23:59:59 of the current local day; ``week`` spans from 00:00:00 on the
+    calendar day six days ago through the end of today, and so on.
+
+    The returned Unix timestamps (seconds) map to Bilibili's
+    ``pubtime_begin_s`` and ``pubtime_end_s`` query parameters.
+    """
+    now = datetime.now(_CN_TZ)
+    pubtime_end_s = int(now.replace(hour=23, minute=59, second=59, microsecond=0).timestamp())
+    begin_day = now - timedelta(days=time_range_dict[time_range])
+    pubtime_begin_s = int(begin_day.replace(hour=0, minute=0, second=0, microsecond=0).timestamp())
+
+    return pubtime_begin_s, pubtime_end_s
+
 
 def request(query, params):
     query_params = {
@@ -50,6 +77,11 @@ def request(query, params):
         "search_type": "video",
     }
 
+    if params.get("time_range") in time_range_dict:
+        pubtime_begin_s, pubtime_end_s = _pubtime_range(params["time_range"])
+        query_params["pubtime_begin_s"] = pubtime_begin_s
+        query_params["pubtime_end_s"] = pubtime_end_s
+
     params["url"] = f"{base_url}?{urlencode(query_params)}"
     params["headers"]["Referer"] = "https://www.bilibili.com/"
     params["headers"]["Accept"] = "application/json, text/javascript, */*; q=0.01"

searx/engines/bitchute.py

@@ -44,7 +44,7 @@ def response(resp):
                 "url": 'https://www.bitchute.com/video/' + item['video_id'],
                 "content": html_to_text(item['description']),
                 "author": item['channel']['channel_name'],
-                "publishedDate": datetime.strptime(item["date_published"], "%Y-%m-%dT%H:%M:%S.%fZ"),
+                "publishedDate": datetime.fromisoformat(item["date_published"].rstrip("Z")),
                 "length": item['duration'],
                 "views": item['view_count'],
                 "thumbnail": item['thumbnail_url'],

searx/engines/boardreader.py

@@ -34,6 +34,7 @@ about = {
 categories = ["general", "social media"]
 paging = True
 time_range_support = True
+language_support = True
 
 base_url = "https://boardreader.com"
 time_range_map = {"day": "1", "week": "7", "month": "30", "year": "365"}
@@ -103,7 +104,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
                 title=_remove_keyword_marker(result["Subject"]),
                 content=_remove_keyword_marker(result["Text"]),
                 url=result["Url"],
-                publishedDate=datetime.strptime(result["Published"], "%Y-%m-%d %H:%M:%S"),
+                publishedDate=datetime.fromisoformat(result["Published"]),
                 metadata=gettext.gettext("Posted by {author}").format(author=result["Author"]),
             )
         )

searx/engines/bpb.py

@@ -13,8 +13,8 @@ about = {
     'use_official_api': False,
     'require_api_key': False,
     'results': 'JSON',
-    'language': 'de',
 }
+language = "de"
 
 paging = True
 categories = ['general']

searx/engines/braveapi.py

@@ -31,6 +31,7 @@ from dateutil import parser
 
 from searx.exceptions import SearxEngineAPIException
 from searx.result_types import EngineResults
+from searx.utils import html_to_text
 
 if t.TYPE_CHECKING:
     from searx.extended_types import SXNG_Response
@@ -75,6 +76,7 @@ def request(query: str, params: "OnlineParams") -> None:
         "q": query,
         "count": results_per_page,
         "offset": (params["pageno"] - 1) * results_per_page,
+        "text_decorations": False,
     }
 
     # Apply time filter if specified
@@ -112,14 +114,19 @@ def response(resp: "SXNG_Response") -> EngineResults:
     res = EngineResults()
     data = resp.json()
 
-    for result in data.get("web", {}).get("results", []):
+    for result in (data.get("web") or {}).get("results", []):
+        thumbnail_obj = result.get("thumbnail")
+        thumbnail = ""
+        if thumbnail_obj and not thumbnail_obj.get("logo", False):
+            thumbnail = thumbnail_obj.get("src") or ""
+
         res.add(
             res.types.MainResult(
                 url=result["url"],
-                title=result["title"],
+                title=html_to_text(result["title"]),
-                content=result.get("description", ""),
+                content=html_to_text(result.get("description", "")),
                 publishedDate=_extract_published_date(result.get("age")),
-                thumbnail=result.get("thumbnail", {}).get("src"),
+                thumbnail=thumbnail,
             ),
         )
 

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/chefkoch.py

@@ -10,8 +10,8 @@ about = {
     'use_official_api': False,
     'require_api_key': False,
     'results': 'JSON',
-    'language': 'de',
 }
+language = "de"
 
 paging = True
 categories = []
@@ -43,7 +43,7 @@ def response(resp):
 
         publishedDate = None
         if recipe['submissionDate']:
-            publishedDate = datetime.strptime(result['recipe']['submissionDate'][:19], "%Y-%m-%dT%H:%M:%S")
+            publishedDate = datetime.fromisoformat(result['recipe']['submissionDate'][:19])
 
         content = [
             f"Schwierigkeitsstufe (1-3): {recipe['difficulty']}",

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
+In the example below, ChinaSO is configured for news search.
-<engine network>` from the ``chinaso news`` engine.
 
 .. 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
 ===============
@@ -70,26 +53,13 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": "JSON",
-    "language": "zh",
 }
 
 paging = True
 time_range_support = True
 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'):
+    if chinaso_news_source not in t.get_args(ChinasoNewsSourceType):
-        raise ValueError(f"Unsupported category: {chinaso_category}")
-    if chinaso_category == 'news' and 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}/v5/general/v1/web/search?{urlencode(query_params)}"
-
-    params["url"] = f"{base_url}{category_config[chinaso_category]['endpoint']}?{urlencode(query_params)}"
     cookie = {
         "uid": base64.b64encode(secrets.token_bytes(16)).decode("utf-8"),
     }
@@ -156,12 +111,13 @@ def response(resp):
     except Exception as e:
         raise SearxEngineAPIException(f"Invalid response: {e}") from e
 
-    parsers = {'news': parse_news, 'images': parse_images, 'videos': parse_videos}
+    # Upstream returns {'status': 0, 'msg': 'empty result', 'data': {}} when there
+    # are no results; this is a valid empty result rather than an API error.
+    if not isinstance(data, dict) or "data" not in data:
+        raise SearxEngineAPIException("Invalid response")
+    if not data["data"]:
+        return []
 
-    return parsers[chinaso_category](data)
-
-
-def parse_news(data):
     results = []
     if not data.get("data", {}).get("data"):
         raise SearxEngineAPIException("Invalid response")
@@ -183,47 +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/dailymotion.py

@@ -40,6 +40,7 @@ categories = ["videos"]
 paging = True
 page_size = 10
 
+language_support = True
 time_range_support = True
 time_delta_dict = {
     "day": timedelta(days=1),

searx/engines/demo_offline.py

@@ -24,7 +24,7 @@ import typing as t
 import json
 
 from searx.result_types import EngineResults
-from searx.enginelib import EngineCache
+from searx.enginelib import EngineCache, EngineAbout
 
 if t.TYPE_CHECKING:
     from searx.search.processors import RequestParams
@@ -35,13 +35,11 @@ categories = ["general"]
 disabled = True
 timeout = 2.0
 
-about = {
+language = "en"
-    "wikidata_id": None,
+about = EngineAbout(
-    "official_api_documentation": None,
+    results="JSON",
-    "use_official_api": False,
+    description="Demo offline engine Engine with results in the English language.",
-    "require_api_key": False,
+)
-    "results": "JSON",
-}
 
 # if there is a need for globals, use a leading underline
 _my_offline_engine: str = ""

searx/engines/demo_online.py

@@ -25,6 +25,7 @@ import typing as t
 
 from urllib.parse import urlencode
 from searx.result_types import EngineResults
+from searx.enginelib import EngineAbout
 
 if t.TYPE_CHECKING:
     from searx.extended_types import SXNG_Response
@@ -43,14 +44,14 @@ page_size = 20
 search_api = "https://api.artic.edu/api/v1/artworks/search"
 image_api = "https://www.artic.edu/iiif/2/"
 
-about = {
+about = EngineAbout(
-    "website": "https://www.artic.edu",
+    website="https://www.artic.edu",
-    "wikidata_id": "Q239303",
+    wikidata_id="Q239303",
-    "official_api_documentation": "http://api.artic.edu/docs/",
+    official_api_documentation="http://api.artic.edu/docs/",
-    "use_official_api": True,
+    use_official_api=True,
-    "require_api_key": False,
+    require_api_key=False,
-    "results": "JSON",
+    results="JSON",
-}
+)
 
 
 # if there is a need for globals, use a leading underline

searx/engines/destatis.py

@@ -11,8 +11,8 @@ about = {
     'use_official_api': False,
     'require_api_key': False,
     'results': 'HTML',
-    'language': 'de',
 }
+language = "de"
 
 categories = []
 paging = True

searx/engines/duckduckgo.py

@@ -203,6 +203,7 @@ about: dict[str, str | bool] = {
 categories: list[str] = ["general", "web"]
 paging: bool = True
 time_range_support: bool = True
+language_support = True
 safesearch: bool = True
 """DDG-lite: user can't select but the results are filtered."""
 

searx/engines/duckduckgo_extra.py

@@ -28,6 +28,7 @@ about = {
     "require_api_key": False,
     "results": "JSON (site requires js to get images)",
 }
+language_support = True
 
 # engine dependent config
 categories = []

searx/engines/duckduckgo_weather.py

@@ -26,6 +26,7 @@ about = {
     "require_api_key": False,
     "results": "JSON",
 }
+language_support = True
 
 # engine dependent config
 categories = ["weather"]

searx/engines/duden.py

@@ -14,8 +14,8 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": 'HTML',
-    "language": 'de',
 }
+language = "de"
 
 categories = ['dictionaries']
 paging = True

searx/engines/elasticsearch.py

@@ -55,7 +55,7 @@ about = {
     'official_api_documentation': 'https://www.elastic.co/guide/en/elasticsearch/reference/current/search-search.html',
     'use_official_api': True,
     'require_api_key': False,
-    'format': 'JSON',
+    "results": "JSON",
 }
 
 base_url = 'http://localhost:9200'

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/findthatmeme.py

@@ -37,7 +37,7 @@ def response(resp):
     for item in search_res:
         img = 'https://s3.thehackerblog.com/findthatmeme/' + item['image_path']
         thumb = 'https://s3.thehackerblog.com/findthatmeme/thumb/' + item.get('thumbnail', '')
-        date = datetime.strptime(item["updated_at"].split("T")[0], "%Y-%m-%d")
+        date = datetime.fromisoformat(item["updated_at"].split("T")[0])
         formatted_date = datetime.fromtimestamp(date.timestamp())
 
         results.append(

searx/engines/fyyd.py

@@ -47,7 +47,7 @@ def response(resp: "SXNG_Response"):
                 title=result["title"],
                 content=result["description"],
                 thumbnail=result["smallImageURL"],
-                publishedDate=datetime.strptime(result["status_since"], "%Y-%m-%d %H:%M:%S"),
+                publishedDate=datetime.fromisoformat(result["status_since"]),
                 metadata=f"Rank: {result['rank']} || {result['episode_count']} episodes",
             )
         )

searx/engines/geizhals.py

@@ -27,8 +27,8 @@ about = {
     'official_api_documentation': None,
     'require_api_key': False,
     'results': 'HTML',
-    'language': 'de',
 }
+language = "de"
 paging = True
 categories = ['shopping']
 

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/google.py

@@ -32,7 +32,6 @@ from searx.utils import (
     eval_xpath_getindex,
     eval_xpath_list,
     extract_text,
-    gen_gsa_useragent,
 )
 
 if t.TYPE_CHECKING:
@@ -57,6 +56,7 @@ max_page = 50
 .. _Google max 50 pages: https://github.com/searxng/searxng/issues/2982
 """
 time_range_support = True
+language_support = True
 safesearch = True
 
 time_range_dict = {"day": "d", "week": "w", "month": "m", "year": "y"}
@@ -196,7 +196,7 @@ def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[st
     #   https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages
 
     # https://github.com/searxng/searxng/issues/2515#issuecomment-1607150817
-    ret_val["params"]["hl"] = f"{lang_code}-{country}"
+    ret_val["params"]["hl"] = f"{lang_code}"
 
     # lr parameter:
     #   The lr (language restrict) parameter restricts search results to
@@ -267,7 +267,6 @@ def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[st
     # HTTP headers
 
     ret_val["headers"]["Accept"] = "*/*"
-    ret_val["headers"]["User-Agent"] = gen_gsa_useragent()
 
     # Cookies
 

searx/engines/google_cse.py

@@ -0,0 +1,190 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Google Custom Search Engine"""
+
+import datetime
+import typing as t
+from json import loads
+from urllib.parse import urlencode
+
+from searx.enginelib import EngineCache
+from searx.exceptions import SearxEngineAPIException, SearxEngineTooManyRequestsException
+from searx.network import get
+from searx.result_types import EngineResults, Result, MainResult, Image
+
+from searx.engines.google import fetch_traits  # pylint: disable=unused-import
+from searx.engines.google import filter_mapping, get_google_info
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
+
+about = {
+    "website": "https://www.google.com",
+    "wikidata_id": "Q2233943",
+    "official_api_documentation": "https://developers.google.com/custom-search/docs/element",
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSONP",
+    "description": "Platform for creating custom search engines based on Google Search.",
+}
+
+categories = ["general", "web"]
+paging = True
+max_page = 5
+page_size = 20
+time_range_support = True
+language_support = True
+safesearch = True
+
+GoogleCategType = t.Literal["", "image"]
+google_categ: GoogleCategType = ""
+"""Google CSE category. Set to ``""`` for web search."""
+
+CX = "partner-pub-8993703457585266:4862972284"  # blackle.com
+
+CACHE: EngineCache
+
+
+def setup(engine_settings: dict[str, t.Any]) -> bool:
+    global CACHE  # pylint: disable=global-statement
+
+    if google_categ not in t.get_args(GoogleCategType):
+        raise ValueError("invalid google cse category: %s" % google_categ)
+
+    CACHE = EngineCache(engine_settings["name"])
+    return True
+
+
+def _cse_token() -> dict[str, str]:
+    token: dict[str, str] = CACHE.get(CX)
+    if token:
+        return token
+
+    resp = get(f"https://www.google.com/cse/cse.js?cx={CX}", timeout=10)
+    if not resp.ok:
+        raise SearxEngineAPIException("failed to obtain cse token")
+
+    end = resp.text.rfind("});")
+    start = resp.text.rfind("({")
+    opts: dict[str, str] = loads(resp.text[start + 1 : end + 1])
+
+    cse_tok = opts.get("cse_token")
+    if not cse_tok:
+        raise SearxEngineAPIException("failed to obtain cse token")
+
+    exp = opts.get("exp")
+    token = {
+        "cse_tok": cse_tok,
+        "cselibv": opts.get("cselibVersion", ""),
+        "exp": ",".join(exp) if exp else "",
+    }
+    CACHE.set(CX, token, expire=3600)
+    return token
+
+
+def _get_start_and_end_date_str(time_range: str) -> tuple[str, str]:
+    time_range_map = {"day": 1, "week": 7, "month": 30, "year": 365}
+
+    end_date = datetime.datetime.now()
+    start_date = end_date - datetime.timedelta(days=time_range_map[time_range])
+
+    return start_date.strftime("%Y%m%d"), end_date.strftime("%Y%m%d")
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    token = _cse_token()
+
+    google_info = get_google_info(params, traits)
+    info: dict[str, str] = google_info["params"]
+
+    args = {
+        "rsz": "filtered_cse",
+        "num": str(page_size),
+        "hl": info["hl"],
+        "cselibv": token["cselibv"],
+        "cx": CX,
+        "q": query,
+        "safe": filter_mapping[params["safesearch"]],
+        "cse_tok": token["cse_tok"],
+        "callback": "_",
+        "rurl": "",
+        "searchtype": google_categ,
+    }
+    if params["time_range"]:
+        start_date, end_date = _get_start_and_end_date_str(params["time_range"])
+        args["sort"] = f"date:r:{start_date}:{end_date}"
+
+    if info.get("lr"):
+        args["lr"] = info["lr"]
+    if info.get("cr"):
+        args["cr"] = info["cr"]
+    if google_info["country"] not in (None, "ZZ"):
+        args["gl"] = google_info["country"]
+    if token["exp"]:
+        args["exp"] = token["exp"]
+
+    start = (params["pageno"] - 1) * page_size
+    if start:
+        args["start"] = str(start)
+
+    params["url"] = "https://cse.google.com/cse/element/v1?" + urlencode(args)
+    params["cookies"] = google_info["cookies"]
+    params["headers"].update(google_info["headers"])
+    params["headers"]["Referer"] = "https://cse.google.com/"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    json_resp = resp.text[resp.text.find("{") : resp.text.rfind("}") + 1]
+    data = loads(json_resp)
+
+    # not the real types, but a sufficient approximation
+    item: dict[str, str]
+    error: dict[str, str | int]
+
+    if error := data.get("error"):
+        message = error.get("message", "unknown error")
+        if error.get("code") == 429:
+            raise SearxEngineTooManyRequestsException(message=f"google cse: {message}")
+        raise SearxEngineAPIException(f"google cse: {message}")
+
+    results = EngineResults()
+
+    for item in data.get("results", []):
+
+        res: Result | None
+        if google_categ == "":
+            res = web_item(item)
+        elif google_categ == "image":
+            res = img_item(item)
+
+        if res is not None:
+            results.add(res)
+
+    return results
+
+
+def web_item(item: dict[str, str]) -> MainResult | None:
+    url = item.get("unescapedUrl")
+    if not url:
+        return None
+    return MainResult(
+        url=url,
+        title=item.get("titleNoFormatting", ""),
+        content=item.get("contentNoFormatting", ""),
+        thumbnail=item.get("richSnippet", {}).get("cseThumbnail", {}).get("src", ""),  # type: ignore
+    )
+
+
+def img_item(item: dict[str, str]) -> Image | None:
+    resolution = ""
+    if item.get("height") and item.get("width"):
+        resolution = f"{item['width']}x{item['height']}"
+    return Image(
+        url=item["originalContextUrl"],
+        title=item.get("titleNoFormatting", ""),
+        content=item.get("contentNoFormatting", ""),
+        img_src=item["unescapedUrl"],
+        thumbnail_src=item["tbUrl"],
+        resolution=resolution,
+        img_format=item["fileFormat"].split("/")[-1],
+    )

searx/engines/google_images.py

@@ -43,6 +43,7 @@ max_page = 50
 """
 
 time_range_support = True
+language_support = True
 safesearch = True
 
 filter_mapping = {0: 'images', 1: 'active', 2: 'active'}

searx/engines/google_news.py

@@ -66,6 +66,7 @@ about = {
 categories = ["news"]
 paging = False
 time_range_support = False
+language_support = True
 
 # Google-News results are always *SafeSearch*. Option 'safesearch' is set to
 # False here.

searx/engines/heexy.py

@@ -14,8 +14,11 @@ from urllib.parse import urlencode
 
 import typing as t
 
-from searx.exceptions import SearxEngineAccessDeniedException
+from searx.enginelib import EngineCache
+from searx.network import get
+from searx.exceptions import SearxEngineAPIException, SearxEngineAccessDeniedException
 from searx.result_types import EngineResults
+from searx.utils import gen_useragent
 
 if t.TYPE_CHECKING:
     from searx.extended_types import SXNG_Response
@@ -38,14 +41,46 @@ heexy_categ = "web"
 """Category to search in. Can be either "web" or "image"."""
 
 
-base_url = "https://seapi.heexy.org"
+base_url = "https://heexy.org"
+api_url = "https://seapi.heexy.org"
 safe_search_map = {0: "off", 1: "on", 2: "on"}
 
+CACHE: EngineCache
+"""Cache for storing the ``X-Data-Cacheft`` token (acts like an API key)."""
+
+
+def setup(engine_settings: dict[str, t.Any]) -> bool:
+    global CACHE  # pylint: disable=global-statement
 
-def init(_):
     if heexy_categ not in ("web", "image"):
         raise ValueError("invalid search category: %s" % heexy_categ)
 
+    CACHE = EngineCache(engine_settings["name"])
+    return True
+
+
+def _get_api_token(query: str) -> str:
+    """The API token is independent of the search query. We just need any query
+    to obtain it initially, and don't hardcode it here to decrease chances of
+    getting blocked. The token must be passed as ``X-Data-Cacheft`` header."""
+
+    cached_token: str = CACHE.get("token")
+    if cached_token:
+        return cached_token
+
+    resp = get(
+        f"{base_url}/search?q={query}", headers={"User-Agent": gen_useragent(), "Accept-Language": "en-US,en:q=0.9"}
+    )
+    if not resp.ok:
+        raise SearxEngineAPIException("failed to obtain request token: invalid response code")
+
+    token = resp.cookies["cacheft"]
+    if not token:
+        raise SearxEngineAPIException("failed to obtain request token: no token found")
+
+    CACHE.set("token", token, expire=3 * 60)
+    return token
+
 
 def request(query: str, params: "OnlineParams") -> None:
     args = {
@@ -56,8 +91,10 @@ def request(query: str, params: "OnlineParams") -> None:
     if params["searxng_locale"] != "all":
         args["lang"] = params["searxng_locale"].split("-")[0]
 
-    params["url"] = f"{base_url}/search/{heexy_categ}?{urlencode(args)}"
+    params["url"] = f"{api_url}/search/{heexy_categ}?{urlencode(args)}"
-    params["headers"]["Origin"] = base_url
+
+    params["headers"]["Origin"] = api_url
+    params["cookies"]["cacheft"] = _get_api_token(query)
 
 
 def response(resp: "SXNG_Response"):

searx/engines/huggingface.py

@@ -91,7 +91,7 @@ def response(resp) -> EngineResults:
 
         published_date = None
         try:
-            published_date = datetime.strptime(entry["createdAt"], "%Y-%m-%dT%H:%M:%S.%fZ")
+            published_date = datetime.fromisoformat(entry["createdAt"].rstrip("Z"))
         except (ValueError, TypeError):
             pass
 

searx/engines/il_post.py

@@ -34,8 +34,8 @@ about = {
     "use_official_api": True,
     "require_api_key": False,
     "results": "JSON",
-    "language": "it",
 }
+language = "it"
 
 
 def request(query, params):

searx/engines/ina.py

@@ -16,8 +16,8 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": 'HTML',
-    "language": 'fr',
 }
+language = "fr"
 
 # engine dependent config
 categories = ['videos']

searx/engines/iqiyi.py

@@ -14,9 +14,9 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": "JSON",
-    "language": "zh",
 }
 
+language = "zh"
 paging = True
 time_range_support = True
 categories = ["videos"]
@@ -43,7 +43,7 @@ def _result(video: dict[str, typing.Any], album_info: dict[str, typing.Any]):
     release_time = album_info.get("releaseTime", {}).get("value")
     if release_time:
         try:
-            published_date = datetime.strptime(release_time, "%Y-%m-%d")
+            published_date = datetime.fromisoformat(release_time)
         except (ValueError, TypeError):
             pass
 

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/jisho.py

@@ -13,8 +13,8 @@ about = {
     "use_official_api": True,
     "require_api_key": False,
     "results": 'JSON',
-    "language": 'ja',
 }
+language = "ja"
 
 categories = ['dictionaries']
 paging = False
@@ -110,8 +110,8 @@ def get_infobox(alt_forms, result_url, definitions):
     # definitions
     infobox_content.append(
         '''
-        <small><a href="https://www.edrdg.org/wiki/index.php/JMdict-EDICT_Dictionary_Project">JMdict</a> 
+        <small><a href="https://www.edrdg.org/wiki/index.php/JMdict-EDICT_Dictionary_Project">JMdict</a>
-        and <a href="https://www.edrdg.org/enamdict/enamdict_doc.html">JMnedict</a> 
+        and <a href="https://www.edrdg.org/enamdict/enamdict_doc.html">JMnedict</a>
         by <a href="https://www.edrdg.org/edrdg/licence.html">EDRDG</a>, CC BY-SA 3.0.</small>
         <ul>
     '''

searx/engines/json_engine.py

@@ -79,6 +79,9 @@ from json import loads
 from urllib.parse import urlencode
 from searx.utils import to_string, html_to_text
 from searx.network import raise_for_httperror
+from searx.enginelib import EngineAbout
+
+about = EngineAbout()
 
 search_url = None
 """

searx/engines/kagi.py

@@ -42,15 +42,14 @@ To enable Kagi, add the following to the ``engines`` seciton of
 .. _Api Portal: https://help.kagi.com/kagi/api/overview.html
 """
 
-
 from datetime import datetime, timedelta
 
 import typing as t
-import html
+
 
 from searx.extended_types import SXNG_Response
 from searx.result_types import EngineResults
-from searx.utils import parse_duration_string
+from searx.utils import html_to_text, parse_duration_string
 
 if t.TYPE_CHECKING:
     from searx.search.processors import OnlineParams
@@ -77,7 +76,12 @@ kagi_categ: t.Literal["search", "images", "news", "videos"] = "search"
 base_url = "https://kagi.com"
 
 safe_search_map = {0: False, 1: True, 2: True}
-time_range_to_days_map: dict[TimeRangeType, int] = {"day": 1, "week": 7, "month": 30, "year": 365}
+time_range_to_days_map: dict[TimeRangeType, int] = {
+    "day": 1,
+    "week": 7,
+    "month": 30,
+    "year": 365,
+}
 
 api_key = ""
 """Kagi API key. Required for using this engine."""
@@ -135,9 +139,13 @@ def response(resp: "SXNG_Response") -> EngineResults:
 
     if kagi_categ in ("images", "videos"):
         # the JSON key is "image" for "images" and "video" for "videos"
-        json_results = json_data["data"][kagi_categ[:-1]]
+        json_results = json_data["data"].get(kagi_categ[:-1])
     else:
-        json_results = json_data["data"][kagi_categ]
+        json_results = json_data["data"].get(kagi_categ)
+
+    # if no results were found, the response doesn't contain the results field
+    if not json_results:
+        return res
 
     for result in json_results:
         published_date: datetime | None = None
@@ -148,8 +156,8 @@ def response(resp: "SXNG_Response") -> EngineResults:
             res.add(
                 res.types.MainResult(
                     url=result["url"],
-                    title=html.unescape(result["title"]),
+                    title=html_to_text(result.get("title", "no title available")),
-                    content=html.unescape(result["snippet"]),
+                    content=html_to_text(result.get("snippet", "")),
                     thumbnail=result.get("image", {}).get("url") or "",
                     publishedDate=published_date,
                 )
@@ -158,15 +166,15 @@ def response(resp: "SXNG_Response") -> EngineResults:
             res.add(
                 res.types.Image(
                     url=result["url"],
-                    title=html.unescape(result.get("title")),
+                    title=html_to_text(result.get("title", "no title available")),
                     img_src=result.get("image", {}).get("url"),
-                    resolution=f"{result['image']['width']}x{result['image']['height']}",
+                    resolution=f"{result.get('image', {}).get('width')}x{result.get('image', {}).get('height')}",
                     thumbnail_src=result.get("props", {}).get("thumbnail", {}).get("url"),
                 )
             )
         elif kagi_categ == "videos":
             length: timedelta | None = None
-            if result["props"].get("duration"):
+            if result.get("props", {}).get("duration"):
                 length = parse_duration_string(result["props"]["duration"])
 
             res.add(
@@ -174,11 +182,11 @@ def response(resp: "SXNG_Response") -> EngineResults:
                     {
                         "template": "videos.html",
                         "url": result["url"],
-                        "title": html.unescape(result["title"]),
+                        "title": html_to_text(result.get("title", "no title available")),
-                        "content": html.unescape(result["snippet"]),
+                        "content": html_to_text(result.get("snippet", "")),
                         "thumbnail": result.get("image", {}).get("url"),
                         "publishedDate": published_date,
-                        "author": result["props"].get("creator_name"),
+                        "author": result.get("props", {}).get("creator_name"),
                         "length": length,
                     }
                 )

searx/engines/lemmy.py

@@ -92,7 +92,7 @@ def _get_communities(json):
                 'title': result['community']['title'],
                 'content': markdown_to_text(result['community'].get('description', '')),
                 'thumbnail': result['community'].get('icon', result['community'].get('banner')),
-                'publishedDate': datetime.strptime(counts['published'][:19], '%Y-%m-%dT%H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(counts['published'][:19]),
                 'metadata': metadata,
             }
         )
@@ -141,7 +141,7 @@ def _get_posts(json):
                 'title': result['post']['name'],
                 'content': content,
                 'thumbnail': thumbnail,
-                'publishedDate': datetime.strptime(result['post']['published'][:19], '%Y-%m-%dT%H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(result['post']['published'][:19]),
                 'metadata': metadata,
             }
         )
@@ -170,7 +170,7 @@ def _get_comments(json):
                 'url': result['comment']['ap_id'],
                 'title': result['post']['name'],
                 'content': markdown_to_text(result['comment']['content']),
-                'publishedDate': datetime.strptime(result['comment']['published'][:19], '%Y-%m-%dT%H:%M:%S'),
+                'publishedDate': datetime.fromisoformat(result['comment']['published'][:19]),
                 'metadata': metadata,
             }
         )

searx/engines/magnific.py

@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Magnific_ is a database for images.
+
+.. _Magnific: https://www.magnific.com
+"""
+
+from urllib.parse import urlencode
+
+import typing as t
+
+from searx.result_types import EngineResults
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
+
+
+about = {
+    "website": "https://www.magnific.com",
+    "wikidata_id": "Q104211654",
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+base_url = "https://www.magnific.com"
+
+categories = ["images"]
+paging = True
+
+free_images_only = True
+"""
+Whether to only load images that may be used for free, without a Magnific account.
+"""
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    args = {"term": query, "filters[ai-generated][excluded]": 1, "page": params["pageno"], "locale": "en"}
+    if free_images_only:
+        args["filters[license]"] = "free"
+
+    params["headers"]["Referer"] = f"{base_url}/search"
+    params["url"] = f"{base_url}/api/regular/search?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response"):
+    res = EngineResults()
+
+    result: dict[str, t.Any]  # TBH: dict[str, t.Any]
+    for result in resp.json()["items"]:
+        res.add(
+            res.types.Image(
+                title=result["name"],
+                url=result["url"],
+                thumbnail_src=result["preview"]["url"],
+                img_src=result["preview"]["url"],
+                resolution=f"{result['preview']['width']}x{result['preview']['height']}",
+            )
+        )
+
+    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/mastodon.py

@@ -60,7 +60,7 @@ def response(resp):
                     'title': result['username'] + f" ({result['followers_count']} followers)",
                     'content': result['note'],
                     'thumbnail': result.get('avatar'),
-                    'publishedDate': datetime.strptime(result['created_at'][:10], "%Y-%m-%d"),
+                    'publishedDate': datetime.fromisoformat(result['created_at'][:10]),
                 }
             )
         elif mastodon_type == "hashtags":

searx/engines/mediathekviewweb.py

@@ -11,9 +11,9 @@ about = {
     "use_official_api": True,
     "require_api_key": False,
     "results": 'JSON',
-    "language": "de",
 }
 
+language = "de"
 categories = ['videos']
 paging = True
 time_range_support = False

searx/engines/mojeek.py

@@ -20,6 +20,7 @@ about = {
 }
 paging = True  # paging is only supported for general search
 safesearch = True
+language_support = True
 time_range_support = True  # time range search is supported for general and news
 max_page = 10
 

searx/engines/moviepilot.py

@@ -35,8 +35,9 @@ about = {
     'use_official_api': False,
     'require_api_key': False,
     'results': 'JSON',
-    'language': 'de',
 }
+language = "de"
+
 paging = True
 categories = ["movies"]
 

searx/engines/naver.py

@@ -26,8 +26,8 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": "HTML",
-    "language": "ko",
 }
+language = "ko"
 
 categories = []
 paging = True
@@ -99,23 +99,35 @@ def parse_general(data):
 
     dom = html.fromstring(data)
 
-    for item in eval_xpath_list(dom, "//ul[contains(@class, 'lst_total')]/li[contains(@class, 'bx')]"):
+    for item in eval_xpath_list(dom, "//div[contains(@class, 'fds-web-normal-doc-root')]"):
-        thumbnail = None
+        thumbnail = extract_text(
+            eval_xpath(
+                item,
+                ".//div[contains(@class, 'sds-comps-image') and not(contains(@class, 'sds-comps-image-circle'))]/img/@src",
+            )
+        )
+
+        title = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-headline1')]"))
+
+        url = None
         try:
-            thumbnail = eval_xpath_getindex(item, ".//div[contains(@class, 'thumb_single')]//img/@data-lazysrc", 0)
+            url = eval_xpath_getindex(
+                item, ".//a[starts-with(@href, 'http') and not(contains(@href, 'keep.naver.com'))]/@href", 0
+            )
         except (ValueError, TypeError, SearxEngineXPathException):
             pass
 
-        results.add(
+        content = extract_text(eval_xpath(item, ".//span[contains(@class, 'sds-comps-text-type-body1')]"))
-            MainResult(
+
-                title=extract_text(eval_xpath(item, ".//a[contains(@class, 'link_tit')]")),
+        if title and url:
-                url=eval_xpath_getindex(item, ".//a[contains(@class, 'link_tit')]/@href", 0),
+            results.add(
-                content=extract_text(
+                MainResult(
-                    eval_xpath(item, ".//div[contains(@class, 'total_dsc_wrap')]//a[contains(@class, 'api_txt_lines')]")
+                    title=title,
-                ),
+                    url=url,
-                thumbnail=thumbnail,
+                    content=content or "",
+                    thumbnail=thumbnail or "",
+                )
             )
-        )
 
     return results
 
@@ -173,7 +185,7 @@ def parse_news(data):
                     title=title,
                     url=url,
                     content=content,
-                    thumbnail=thumbnail,
+                    thumbnail=thumbnail or "",
                 )
             )
 
@@ -196,7 +208,7 @@ def parse_videos(data):
 
         length = None
         try:
-            length = parse_duration_string(extract_text(eval_xpath(item, ".//span[contains(@class, 'time')]")))
+            length = parse_duration_string(extract_text(eval_xpath(item, ".//span[contains(@class, 'time')]")) or "")
         except (ValueError, TypeError):
             pass
 

searx/engines/neocities.py

@@ -0,0 +1,66 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Neocities_ is open source software for creating blogs.
+
+.. _Neocities : https://github.com/neocities/neocities
+"""
+
+from urllib.parse import urlencode
+import typing as t
+
+from lxml import html
+
+from searx.utils import eval_xpath, eval_xpath_list, extract_text
+from searx.result_types import EngineResults
+
+if t.TYPE_CHECKING:
+    from extended_types import SXNG_Response
+    from search.processors import OnlineParams
+
+
+# Engine metadata
+about = {
+    "website": "https://neocities.org/",
+    "wikidata_id": "Q17071099",
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "HTML",
+}
+
+# Engine configuration
+categories = ["general", "blogs"]
+paging = True
+
+# Search URL
+base_url = "https://neocities.org"
+
+results_xpath = "//div[@class='result-item']"
+url_xpath = './/div[@class="result-url"]/a/@href'
+title_xpath = './/h3[@class="result-title"]/a/text()'
+content_xpath = './/p[@class="result-snippet"]//text()'
+screenshot_xpath = './/a[@class="result-screenshot"]/img/@src'
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    query_params: dict[str, t.Any] = {"q": query}
+    if params['pageno'] > 1:
+        offset = (params["pageno"] - 1) * 100
+        query_params["start"] = offset
+    params["url"] = f"{base_url}/search?{urlencode(query_params)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    results = EngineResults()
+    dom = html.fromstring(resp.text)
+
+    for result in eval_xpath_list(dom, results_xpath):
+        results.add(
+            results.types.MainResult(
+                url=extract_text(eval_xpath(result, url_xpath)),
+                title=extract_text(eval_xpath(result, title_xpath)) or "",
+                content=extract_text(eval_xpath(result, content_xpath)) or "",
+                thumbnail=base_url + (extract_text(eval_xpath(result, screenshot_xpath)) or ""),
+            )
+        )
+
+    return results

searx/engines/neosearch.py

@@ -0,0 +1,92 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Neosearch_ aims to be a privacy-first alternative to Google.
+
+.. _Neosearch: https://neosearch.org/About
+"""
+
+from json import loads
+import typing as t
+from urllib.parse import urlencode
+
+from searx.extended_types import SXNG_Response
+from searx.result_types import EngineResults
+
+if t.TYPE_CHECKING:
+    from searx.enginelib.traits import EngineTraits
+    from searx.search.processors import OnlineParams
+
+    traits: EngineTraits
+
+about = {
+    "website": "https://neosearch.org",
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "JSON",
+}
+
+base_url = "https://neosearch.org"
+categories = ["general"]
+
+paging = False
+
+
+def request(query: str, params: "OnlineParams"):
+    args = {"q": query, "generate": "auto"}
+    countrycode = params["searxng_locale"].split("-")[-1].upper()
+    if countrycode in traits.custom["countrycodes"]:
+        args["loc"] = countrycode
+    params["url"] = f"{base_url}/search?{urlencode(args)}"
+
+
+def response(resp: "SXNG_Response") -> EngineResults:
+    res = EngineResults()
+
+    # first line contains something like `{"location": "de"}`
+    # second line contains the actual results
+    json_resp = loads(resp.text.splitlines()[-1])
+    for lens in json_resp["lenses"]:
+        for category in lens["categories"]:
+            for result in category["links"]:
+                if not result["url"]:
+                    continue
+
+                res.add(
+                    res.types.MainResult(
+                        url=result["url"],
+                        title=result["title"],
+                        content=result["snippet"] or result["description"],
+                    )
+                )
+
+    for suggestion in json_resp.get("suggestions", []):
+        res.add(res.types.LegacyResult(suggestion=suggestion))
+
+    return res
+
+
+def fetch_traits(engine_traits: "EngineTraits") -> None:
+    # pylint: disable=import-outside-toplevel
+    from searx.network import get
+    from searx.utils import extr, js_obj_str_to_python
+    from babel.core import get_global
+
+    resp = get(base_url)
+
+    locations_js_raw = extr(resp.text, "const LOCATIONS = ", ";")
+    if not locations_js_raw:
+        raise RuntimeError("failed to find locations in neosearch HTML response")
+    locations: list[dict[str, str]] = js_obj_str_to_python(locations_js_raw)
+
+    babel_reg_list = get_global("territory_languages").keys()
+
+    countrycodes: list[str] = []
+    for loc in locations:
+        _reg = loc["code"].upper()
+        if _reg not in babel_reg_list:
+            print(f"ERROR: region tag {_reg} is unknown by babel")
+            continue
+        countrycodes.append(_reg)
+
+    countrycodes.sort()
+    engine_traits.custom["countrycodes"] = countrycodes

searx/engines/niconico.py

@@ -13,8 +13,8 @@ about = {
     "use_official_api": False,
     "require_api_key": False,
     "results": "HTML",
-    "language": "ja",
 }
+language = "ja"
 
 categories = ["videos"]
 paging = True

searx/engines/nvd.py

@@ -44,7 +44,7 @@ def response(resp) -> EngineResults:
 
         cve_id = item["cve"]["id"]
         description = item["cve"]["descriptions"][0]["value"]
-        date = datetime.strptime(item["cve"]["published"], "%Y-%m-%dT%H:%M:%S.%f")
+        date = datetime.fromisoformat(item["cve"]["published"])
 
         # Extract severity (Low, Medium, High, or Critical) and CVSS score, if available
         info = item["cve"].get("metrics", {}).get("cvssMetricV31", [{}])[0].get("cvssData", {})

searx/engines/odysee.py

@@ -26,6 +26,7 @@ about = {
 # Engine configuration
 paging = True
 time_range_support = True
+language_support = True
 results_per_page = 20
 categories = ["videos"]
 
@@ -75,7 +76,7 @@ def response(resp):
         release_time = item["release_time"]
         duration = item["duration"]
 
-        release_date = datetime.strptime(release_time.split("T")[0], "%Y-%m-%d")
+        release_date = datetime.fromisoformat(release_time.split("T")[0])
         formatted_date = datetime.fromtimestamp(release_date.timestamp())
 
         url = f"https://odysee.com/{name}:{claim_id}"

searx/engines/peertube.py

@@ -25,6 +25,7 @@ about = {
     "require_api_key": False,
     "results": "JSON",
 }
+language_support = True
 
 # engine dependent config
 categories = ["videos"]

searx/engines/photon.py

@@ -28,7 +28,7 @@ search_string = 'api/?{query}&limit={limit}'
 result_base_url = 'https://openstreetmap.org/{osm_type}/{osm_id}'
 
 # list of supported languages
-supported_languages = ['de', 'en', 'fr', 'it']
+photon_supported_languages = ["de", "en", "fr", "it"]
 
 
 # do search-request
@@ -37,7 +37,7 @@ def request(query, params):
 
     if params['language'] != 'all':
         language = params['language'].split('_')[0]
-        if language in supported_languages:
+        if language in photon_supported_languages:
             params['url'] = params['url'] + "&lang=" + language
 
     # using SearXNG User-Agent

searx/engines/picjumbo.py

@@ -0,0 +1,63 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Picjumbo_ provides free stock photos.
+
+.. _Picjumbo: https://picjumbo.com
+"""
+
+from urllib.parse import urlparse, urlunparse
+import typing as t
+
+from lxml import html
+
+from searx.result_types import EngineResults
+from searx.utils import eval_xpath, eval_xpath_list, extract_text
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
+
+
+about = {
+    "website": "https://picjumbo.com",
+    "wikidata_id": None,
+    "official_api_documentation": None,
+    "use_official_api": False,
+    "require_api_key": False,
+    "results": "HTML",
+}
+
+base_url = "https://picjumbo.com"
+
+categories = ["images"]
+paging = True
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    params["url"] = f"{base_url}/search/{query}/page/{params['pageno']}"
+
+
+def _get_max_res_url(url: str) -> str:
+    """Get the maximum resolution of the image based on the thumbnail URL."""
+    parsed_url = urlparse(url)
+    max_res_url = parsed_url._replace(query="w=10000&quality=100")
+    return urlunparse(max_res_url)
+
+
+def response(resp: "SXNG_Response"):
+    res = EngineResults()
+
+    doc = html.fromstring(resp.text)
+
+    for result in eval_xpath_list(doc, "//div[contains(@class, 'photo_query')]/div[contains(@class, 'photo_item')]"):
+        thumbnail = extract_text(eval_xpath(result, ".//img[contains(@class, 'image')]/@src")) or ""
+        res.add(
+            res.types.Image(
+                url=extract_text(eval_xpath(result, ".//a[contains(@class, 'image')]/@href")) or "",
+                title=extract_text(eval_xpath(result, ".//h3")) or "",
+                content=extract_text(eval_xpath(result, ".//meta[@itemprop='keywords']/@content")) or "",
+                thumbnail_src=thumbnail,
+                img_src=_get_max_res_url(thumbnail),
+            )
+        )
+
+    return res

searx/engines/podchaser.py

@@ -54,7 +54,7 @@ def response(resp: "SXNG_Response"):
                 title=result["title"],
                 content=result["description"],
                 thumbnail=result["image_url"],
-                publishedDate=datetime.strptime(result["created_at"], "%Y-%m-%d %H:%M:%S"),
+                publishedDate=datetime.fromisoformat(result["created_at"]),
                 metadata=" | ".join(metadata),
             )
         )

searx/engines/presearch.py

@@ -77,7 +77,7 @@ from searx.utils import gen_useragent, html_to_text, parse_duration_string
 
 about = {
     "website": "https://presearch.io",
-    "wikidiata_id": "Q7240905",
+    "wikidata_id": "Q7240905",
     "official_api_documentation": "https://docs.presearch.io/nodes/api",
     "use_official_api": False,
     "require_api_key": False,