[upd] github-actions: Bump actions/setup-node from 6.4.0 to 7.0.0 (#6423)

Bumps [actions/setup-node](https://github.com/actions/setup-node) from 6.4.0 to 7.0.0.
- [Release notes](https://github.com/actions/setup-node/releases)
- [Commits](48b55a011b...8207627860)

---
updated-dependencies:
- dependency-name: actions/setup-node
  dependency-version: 7.0.0
  dependency-type: direct:production
  update-type: version-update:semver-major
...

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

.github/workflows/integration.yml

@@ -67,7 +67,7 @@ jobs:
           python-version: "${{ env.PYTHON_VERSION }}"
 
       - name: Setup Node.js
-        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e  # v6.4.0
+        uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020  # v7.0.0
         with:
           node-version: "26"
           check-latest: "true"

requirements-dev.txt

@@ -4,7 +4,7 @@ cov-core==1.15.0
 black==25.9.0
 pylint==4.0.6
 splinter==0.21.0
-selenium==4.45.0
+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

requirements.txt

@@ -13,7 +13,7 @@ sniffio==1.3.1
 valkey==6.1.1
 markdown-it-py==4.2.0
 msgspec==0.21.1
-typer==0.26.8
+typer==0.27.0
 isodate==0.7.2
 whitenoise==6.12.0
 typing-extensions==4.16.0

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/enginelib/__init__.py

@@ -47,7 +47,7 @@ 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
     )
 )

searx/engines/heexy.py

@@ -68,7 +68,9 @@ def _get_api_token(query: str) -> str:
     if cached_token:
         return cached_token
 
-    resp = get(f"{base_url}/search?q={query}", headers={"User-Agent": gen_useragent()})
+    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")
 
@@ -76,7 +78,7 @@ def _get_api_token(query: str) -> str:
     if not token:
         raise SearxEngineAPIException("failed to obtain request token: no token found")
 
-    CACHE.set("token", token)
+    CACHE.set("token", token, expire=3 * 60)
     return token
 
 

searx/engines/public_domain_image_archive.py

@@ -140,7 +140,7 @@ def response(resp):
         results.append(
             {
                 'template': 'images.html',
-                'url': _clean_url(f"{about['website']}/images/{result['objectID']}"),
+                'url': _clean_url(f"{pdia_base_url}/images/{result['objectID']}"),
                 'img_src': _clean_url(base_image_url),
                 'thumbnail_src': _clean_url(base_image_url + THUMBNAIL_SUFFIX),
                 'title': f"{result['title'].strip()} by {result['artist']} {result.get('displayYear', '')}",

searx/engines/qwant.py

@@ -51,6 +51,7 @@ from urllib.parse import urlencode
 import babel
 from flask_babel import gettext  # pyright: ignore[reportUnknownVariableType]
 
+from searx.enginelib import EngineCache
 from searx.enginelib.traits import EngineTraits
 from searx.exceptions import (
     SearxEngineAccessDeniedException,
@@ -105,9 +106,19 @@ qwant_news_locales = [
 ]
 # fmt: on
 
+base_url = "https://www.qwant.com"
 api_url = "https://api.qwant.com/v3/search/"
 """URL of Qwant's API (JSON)"""
 
+CACHE: EngineCache
+"""Cache for storing the ``datadome`` cookie."""
+
+
+def setup(engine_settings: dict[str, t.Any]) -> bool:
+    global CACHE  # pylint: disable=global-statement
+    CACHE = EngineCache(engine_settings["name"])
+    return True
+
 
 def request(query: str, params: "OnlineParams") -> None:
     """Qwant search request"""
@@ -129,24 +140,29 @@ def request(query: str, params: "OnlineParams") -> None:
         "tgp": test_group_value,
         "device": "desktop",
         "safesearch": params["safesearch"],
-        "display": True,
-        "llm": True,
+        # True would be encoded to "True", instead of "true", which makes the request
+        # easier to detect and block
+        "displayed": "true",
+        "llm": "true",
     }
 
-    # shuffle query parameters to be harder to fingerprint
-    args = list(args.items())
-    random.shuffle(args)
-    args = dict(args)
-
     params["raise_for_httperror"] = False
 
     params["url"] = f"{api_url}{qwant_categ}?{urlencode(args)}"
 
+    params["cookies"]["datadome"] = CACHE.get("datadome")
+    params["headers"].update({"Accept": "application/json", "Referer": f"{base_url}/", "Origin": base_url})
+
 
 def response(resp: "SXNG_Response") -> EngineResults:
     """Parse results from Qwant's API"""
     # pylint: disable=too-many-locals, too-many-branches, too-many-statements
 
+    # cache datadome cookie - changes on each request
+    datadome = resp.cookies.get("datadome")
+    if datadome:
+        CACHE.set("datadome", datadome)
+
     res = EngineResults()
 
     # Try to load JSON result
@@ -163,8 +179,8 @@ def response(resp: "SXNG_Response") -> EngineResults:
         error_code = data.get("error_code")
         if error_code == 24:
             raise SearxEngineTooManyRequestsException()
-        if search_results.get("data", {}).get("error_data", {}).get("captchaUrl") is not None:
-            raise SearxEngineCaptchaException()
+        if search_results.get("url") is not None:
+            raise SearxEngineCaptchaException(suspended_time=0)
         if resp.status_code == 403:
             raise SearxEngineAccessDeniedException()
         msg = ",".join(data.get("message", ["unknown"]))
@@ -302,7 +318,7 @@ def fetch_traits(engine_traits: EngineTraits):
     from searx.utils import extr
 
     resp = get(
-        about["website"],  # pyright: ignore[reportArgumentType]
+        base_url,  # pyright: ignore[reportArgumentType]
         timeout=5,
     )
     if not resp.ok:

searx/engines/tiger.py

@@ -117,7 +117,7 @@ def _obtain_session_code() -> str:
     if not code:
         raise SearxEngineAPIException("failed to obtain session code")
 
-    CACHE.set("session", code, expire=60 * 24 * 60)  # cookie is valid for two months
+    CACHE.set("session", code, expire=60 * 24 * 60 * 60)  # cookie is valid for two months
     return code
 
 

searx/engines/tusksearch.py

@@ -13,7 +13,7 @@ from dateutil import parser
 
 from searx.exceptions import SearxEngineAPIException
 from searx.network import get
-from searx.utils import html_to_text
+from searx.utils import gen_useragent, html_to_text
 from searx.result_types import EngineResults
 
 if t.TYPE_CHECKING:
@@ -52,7 +52,7 @@ def _obtain_x_sid() -> tuple[str, str]:
     The header key is usually called `x-sid-{UUIDv4}`, and the value is
     usually a plain UUIDv4 (but a different one than in the header key).
     """
-    resp = get(f"{api_url}/revcontent/embed.js")
+    resp = get(f"{api_url}/revcontent/embed.js", headers={"User-Agent": gen_useragent()})
     if not resp.ok:
         raise SearxEngineAPIException("failed to obtain request x-sid token")
 
@@ -89,12 +89,14 @@ def request(query: str, params: "OnlineParams") -> None:
         params["url"] = f"{api_url}/Search/Web?{urlencode(args)}"
 
     x_sid_header, x_sid_value = _obtain_x_sid()
-    params["headers"] = {
-        x_sid_header: x_sid_value,
-        # required - we send a random longitude and latitude instead of the actual user location
-        'x-lon': str(random.random() * 90),
-        'x-lat': str(random.random() * 90),
-    }
+    params["headers"].update(
+        {
+            x_sid_header: x_sid_value,
+            # required - we send a random longitude and latitude instead of the actual user location
+            "x-lon": str(round(random.random() * 90, 4)),
+            "x-lat": str(round(random.random() * 90, 4)),
+        }
+    )
 
 
 def response(resp: "SXNG_Response"):

searx/result_types/_base.py

@@ -52,6 +52,12 @@ def _normalize_url_fields(result: "Result | LegacyResult"):
             result.parsed_url = urllib.parse.urlparse(result.url)
 
     if result.parsed_url:
+        # properly format special characters (e.g. "ä", "ö") in IDN domains
+        # e.g. "xn--strung-xxa.de" becomes "störung.de"
+        if result.parsed_url.netloc.startswith("xn--"):
+            netloc = result.parsed_url.netloc.encode().decode("idna")
+            result.parsed_url = result.parsed_url._replace(netloc=netloc)
+
         result.parsed_url = result.parsed_url._replace(
             # if the result has no scheme, use http as default
             scheme=result.parsed_url.scheme or "http",

searx/settings.yml

@@ -477,6 +477,24 @@ engines:
     engine: arxiv
     shortcut: arx
 
+  - name: avalw
+    engine: json_engine
+    shortcut: av
+    categories: general
+    paging: true
+    search_url: https://avalw.org/api/search?q={query}&page={pageno}&limit=10&tbm=all
+    results_query: results
+    url_query: url
+    title_query: title
+    content_query: snippet
+    thumbnail: image_url
+    disabled: true
+    inactive: true
+    about:
+      website: https://avalw.com
+      description: "Search engine from the Romanian news company AVALW S.R.L."
+      results: JSON
+
   - name: ayo
     engine: xpath
     categories: general

searx/templates/simple/result_templates/images.html

@@ -60,7 +60,7 @@
       </p>
       <p class="result-filesize">{{ _label(_("Filesize"), result.filesize) }}</p>
       <p class="result-source">{{ _label(_("Source"), result.source) }}</p>
-      <p class="result-engine">{{ _label(_("Engine"), result.engine) }}</p>
+      <p class="result-engines">{{ _label(_("Engines"), ", ".join(result.engines)) }}</p>
       <p class="result-url"><span>{{ _("View source") }}:</span>{{- "" -}}
         <a {{ _target(results_on_new_tab) }} href="{{ result.url }}">{{ result.url }}</a>
       </p>

searx/webapp.py

@@ -845,7 +845,10 @@ def autocompleter():
         mimetype = 'application/json'
     else:
         # the suggestion request comes from browser's URL bar
-        suggestions = json.dumps([sug_prefix, results])
+        relevances = {
+            'google:suggestrelevance': [600 - i for i in range(len(results))]
+        }  # chromium only shows 3 suggestions unless we attach relevances
+        suggestions = json.dumps([sug_prefix, results, [], [], relevances])
         mimetype = 'application/x-suggestions+json'
 
     suggestions = escape(suggestions, False)