Merge f49d1a9b90 into cd384a8a60

Bumps [selenium](https://github.com/SeleniumHQ/Selenium) from 4.25.0 to 4.26.1.
- [Release notes](https://github.com/SeleniumHQ/Selenium/releases)
- [Commits](https://github.com/SeleniumHQ/Selenium/commits)

---
updated-dependencies:
- dependency-name: selenium
  dependency-type: direct:development
  update-type: version-update:semver-minor
...

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

.github/workflows/checker.yml

@@ -1,5 +1,5 @@
 name: "Checker"
-on:
+on:  # yamllint disable-line rule:truthy
   schedule:
     - cron: "0 4 * * 5"
   workflow_dispatch:

.github/workflows/data-update.yml

@@ -1,5 +1,5 @@
 name: "Update searx.data"
-on:
+on:  # yamllint disable-line rule:truthy
   schedule:
     - cron: "59 23 28 * *"
   workflow_dispatch:

.github/workflows/integration.yml

@@ -1,6 +1,6 @@
 name: Integration
 
-on:
+on:  # yamllint disable-line rule:truthy
   push:
     branches: ["master"]
   pull_request:
@@ -16,7 +16,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-20.04]
-        python-version:  ["3.9", "3.10", "3.11", "3.12",]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -111,7 +111,7 @@ jobs:
           BRANCH: gh-pages
           FOLDER: dist/docs
           CLEAN: true  # Automatically remove deleted files from the deploy branch
-        SINGLE_COMMIT: True
+          SINGLE_COMMIT: true
           COMMIT_MESSAGE: '[doc] build from commit ${{ github.sha }}'
 
   babel:

.github/workflows/security.yml

@@ -1,5 +1,5 @@
 name: "Security checks"
-on:
+on:  # yamllint disable-line rule:truthy
   schedule:
     - cron: "42 05 * * *"
   workflow_dispatch:

.github/workflows/translations-update.yml

@@ -1,5 +1,5 @@
 name: "Update translations"
-on:
+on:  # yamllint disable-line rule:truthy
   schedule:
     - cron: "05 07 * * 5"
   workflow_dispatch:

manage

@@ -57,7 +57,7 @@ while IFS= read -r line; do
     if [ "$line" != "tests/unit/settings/syntaxerror_settings.yml" ]; then
         YAMLLINT_FILES+=("$line")
     fi
-done <<< "$(git ls-files './tests/*.yml' './searx/*.yml' './utils/templates/etc/searxng/*.yml')"
+done <<< "$(git ls-files './tests/*.yml' './searx/*.yml' './utils/templates/etc/searxng/*.yml' '.github/*.yml' '.github/*/*.yml')"
 
 RST_FILES=(
     'README.rst'

requirements-dev.txt

@@ -4,7 +4,7 @@ cov-core==1.15.0
 black==24.3.0
 pylint==3.3.1
 splinter==0.21.0
-selenium==4.25.0
+selenium==4.26.1
 Pallets-Sphinx-Themes==2.3.0
 Sphinx==7.4.7
 sphinx-issues==5.0.0

searx/search/checker/impl.py

@@ -2,11 +2,11 @@
 # pylint: disable=missing-module-docstring, invalid-name
 
 import gc
+import time
 import typing
 import types
 import functools
 import itertools
-from time import time
 from timeit import default_timer
 from urllib.parse import urlparse
 
@@ -66,15 +66,15 @@ def _download_and_check_if_image(image_url: str) -> bool:
     This function should not be called directly: use _is_url_image
     otherwise the cache of functools.lru_cache contains data: URL which might be huge.
     """
-    retry = 2
+    retry = 3
 
     while retry > 0:
-        a = time()
+        a = default_timer()
         try:
             # use "image_proxy" (avoid HTTP/2)
+            network.set_timeout_for_thread(2)
             network.set_context_network_name('image_proxy')
-            r, stream = network.stream(
+            r = network.get(
-                'GET',
                 image_url,
                 timeout=10.0,
                 allow_redirects=True,
@@ -90,19 +90,20 @@ def _download_and_check_if_image(image_url: str) -> bool:
                     'Cache-Control': 'max-age=0',
                 },
             )
-            r.close()
             if r.status_code == 200:
                 is_image = r.headers.get('content-type', '').startswith('image/')
             else:
                 is_image = False
             del r
-            del stream
             return is_image
         except httpx.TimeoutException:
-            logger.error('Timeout for %s: %i', image_url, int(time() - a))
+            logger.error('Timeout for %s: %i', image_url, int(default_timer() - a))
+            time.sleep(1)
             retry -= 1
-        except httpx.HTTPError:
+        except httpx.HTTPStatusError as e:
-            logger.exception('Exception for %s', image_url)
+            logger.error('Exception for %s: HTTP status=%i', image_url, e.response.status_code)
+        except httpx.HTTPError as e:
+            logger.error('Exception for %s: %s, %s', image_url, e.__class__.__name__, ",".join(e.args))
             return False
     return False