[enh] container: reproducible layers (#5222)

* [enh] container: reproducible layers

We are not aiming for reproducibility compliance, but we look to make most
builder layers reproducible without caching at least for a short period of time
(until the builder's base image changes or the child dependencies of a
requirements.txt package are updated).

This feature is only available on Podman.

This targets https://github.com/searxng/searxng/pull/5086 main goal.

* [fix] misc: apply suggestions

Suggested: https://github.com/searxng/searxng/pull/5222#discussion_r2364630496
Suggested: https://github.com/searxng/searxng/pull/5222#discussion_r2364630511

* [enh] container: prevent useless layer

.github/workflows/container.yml

@@ -134,6 +134,7 @@ jobs:
         uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8  # v5.0.0
         with:
           persist-credentials: "false"
+          fetch-depth: "0"
 
       - name: Setup cache Python
         uses: actions/cache@0400d5f644dc74513175e3cd8d07132dd4860809  # v4.2.4

client/simple/src/less/result_types/paper.less

@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+/*
+  Layout of the Paper result class
+*/
+
+.result-paper {
+  .attributes {
+    display: table;
+    border-spacing: 0.125rem;
+
+    div {
+      display: table-row;
+
+      span {
+        font-size: 0.9rem;
+        margin-top: 0.25rem;
+        display: table-cell;
+
+        time {
+          font-size: 0.9rem;
+        }
+      }
+
+      span:first-child {
+        color: var(--color-base-font);
+        min-width: 10rem;
+      }
+
+      span:nth-child(2) {
+        color: var(--color-result-publishdate-font);
+      }
+    }
+  }
+
+  .content {
+    margin-top: 0.25rem;
+  }
+
+  .comments {
+    font-size: 0.9rem;
+    margin: 0.25rem 0 0 0;
+    padding: 0;
+    word-wrap: break-word;
+    line-height: 1.24;
+    font-style: italic;
+  }
+}
+
+@media screen and (max-width: @phone) {
+  .result-paper {
+    .attributes {
+      display: block;
+
+      div {
+        display: block;
+
+        span {
+          display: inline;
+        }
+
+        span:first-child {
+          font-weight: bold;
+        }
+
+        span:nth-child(2) {
+          .ltr-margin-left(0.5rem);
+        }
+      }
+    }
+  }
+}

client/simple/src/less/style.less

@@ -309,11 +309,11 @@ article[data-vim-selected].category-social {
   }
 }
 
-.result-paper,
 .result-packages {
   .attributes {
     display: table;
     border-spacing: 0.125rem;
+    margin-top: 0.3rem;
 
     div {
       display: table-row;
@@ -353,12 +353,6 @@ article[data-vim-selected].category-social {
   }
 }
 
-.result-packages {
-  .attributes {
-    margin-top: 0.3rem;
-  }
-}
-
 .template_group_images {
   display: flex;
   flex-wrap: wrap;
@@ -1118,7 +1112,6 @@ summary.title {
     display: none;
   }
 
-  .result-paper,
   .result-packages {
     .attributes {
       display: block;
@@ -1164,3 +1157,4 @@ pre code {
 
 // import layouts of the Result types
 @import "result_types/keyvalue.less";
+@import "result_types/paper.less";

container/builder.dockerfile

@@ -1,27 +1,29 @@
 FROM ghcr.io/searxng/base:searxng-builder AS builder
 
-COPY ./requirements*.txt ./
+ARG TIMESTAMP_VENV="0"
 
-ARG TIMESTAMP="0"
+COPY ./requirements.txt ./requirements-server.txt ./
 
-RUN --mount=type=cache,id=uv,target=/root/.cache/uv set -eux; \
+RUN --mount=type=cache,id=uv,target=/root/.cache/uv set -eux -o pipefail; \
+    export SOURCE_DATE_EPOCH="$TIMESTAMP_VENV"; \
     uv venv; \
     uv pip install --no-managed-python --compile-bytecode --requirements ./requirements.txt --requirements ./requirements-server.txt; \
     uv cache prune --ci; \
-    find ./.venv/ -exec touch -h -t $TIMESTAMP {} +
+    find ./.venv/lib/python*/site-packages/*.dist-info/ -type f -name "RECORD" -exec sort -t, -k1,1 -o {} {} \;; \
+    find ./.venv/ -exec touch -h --date="@$TIMESTAMP_VENV" {} +; \
+    unset SOURCE_DATE_EPOCH
 
+# use "--exclude=./searx/version_frozen.py" when actions/runner-images updates to Podman 5.0+
 COPY ./searx/ ./searx/
 
 ARG TIMESTAMP_SETTINGS="0"
 
-RUN set -eux; \
+RUN set -eux -o pipefail; \
     python -m compileall -q ./searx/; \
-    touch -c -t $TIMESTAMP_SETTINGS ./searx/settings.yml; \
     find ./searx/static/ -type f \
     \( -name "*.html" -o -name "*.css" -o -name "*.js" -o -name "*.svg" \) \
     -exec gzip -9 -k {} + \
     -exec brotli -9 -k {} + \
     -exec gzip --test {}.gz + \
     -exec brotli --test {}.br +; \
-    # Move always changing files to /usr/local/searxng/
+    touch -c --date="@$TIMESTAMP_SETTINGS" ./searx/settings.yml
-    mv ./searx/version_frozen.py ./

container/dist.dockerfile

@@ -6,7 +6,7 @@ ARG CONTAINER_IMAGE_NAME="searxng"
 COPY --chown=searxng:searxng --from=localhost/$CONTAINER_IMAGE_ORGANIZATION/$CONTAINER_IMAGE_NAME:builder /usr/local/searxng/.venv/ ./.venv/
 COPY --chown=searxng:searxng --from=localhost/$CONTAINER_IMAGE_ORGANIZATION/$CONTAINER_IMAGE_NAME:builder /usr/local/searxng/searx/ ./searx/
 COPY --chown=searxng:searxng ./container/ ./
-COPY --chown=searxng:searxng --from=localhost/$CONTAINER_IMAGE_ORGANIZATION/$CONTAINER_IMAGE_NAME:builder /usr/local/searxng/version_frozen.py ./searx/
+#COPY --chown=searxng:searxng ./searx/version_frozen.py ./searx/
 
 ARG CREATED="0001-01-01T00:00:00Z"
 ARG VERSION="unknown"
@@ -30,7 +30,6 @@ ENV SEARXNG_VERSION="$VERSION" \
     GRANIAN_HOST="::" \
     GRANIAN_PORT="8080" \
     GRANIAN_WEBSOCKETS="false" \
-    GRANIAN_LOOP="uvloop" \
     GRANIAN_BLOCKING_THREADS="4" \
     GRANIAN_WORKERS_KILL_TIMEOUT="30s" \
     GRANIAN_BLOCKING_THREADS_IDLE_TIMEOUT="5m"

docs/dev/engines/online/arxiv.rst

@@ -0,0 +1,8 @@
+.. _arxiv engine:
+
+=====
+arXiv
+=====
+
+.. automodule:: searx.engines.arxiv
+   :members:

docs/dev/engines/online/astrophysics_data_system.rst

@@ -0,0 +1,8 @@
+.. _astrophysics_data_system engine:
+
+==============================
+Astrophysics Data System (ADS)
+==============================
+
+.. automodule:: searx.engines.astrophysics_data_system
+   :members:

docs/dev/engines/online/crossref.rst

@@ -0,0 +1,8 @@
+.. _crossref engine:
+
+========
+Crossref
+========
+
+.. automodule:: searx.engines.crossref
+   :members:

docs/dev/engines/online/openalex.rst

@@ -1,100 +1,8 @@
 .. _openalex engine:
 
-=========
-OpenAlex
-=========
-
-Overview
 ========
-
+OpenAlex
-The OpenAlex engine integrates the `OpenAlex`_ Works API to return scientific paper
+========
-results using the :origin:`paper.html <searx/templates/simple/result_templates/paper.html>`
-template. It is an "online" JSON engine that uses the official public API and does
-not require an API key.
-
-.. _OpenAlex: https://openalex.org
-.. _OpenAlex API overview: https://docs.openalex.org/how-to-use-the-api/api-overview
-
-Key features
-------------
-
-- Uses the official Works endpoint (JSON)
-- Paging support via ``page`` and ``per-page``
-- Relevance sorting (``sort=relevance_score:desc``)
-- Language filter support (maps SearXNG language to ``filter=language:<iso2>``)
-- Maps fields commonly used in scholarly results: title, authors, abstract
-  (reconstructed from inverted index), journal/venue, publisher, DOI, tags
-  (concepts), PDF/HTML links, pages, volume, issue, published date, and a short
-  citations comment
-- Supports OpenAlex "polite pool" by adding a ``mailto`` parameter
-
-
-Configuration
-=============
-
-Minimal example for :origin:`settings.yml <searx/settings.yml>`:
-
-.. code:: yaml
-
-   - name: openalex
-     engine: openalex
-     shortcut: oa
-     categories: science, scientific publications
-     timeout: 5.0
-     # Recommended by OpenAlex: join the polite pool with an email address
-     mailto: "[email protected]"
-
-Notes
------
-
-- The ``mailto`` key is optional but recommended by OpenAlex for better service.
-- Language is inherited from the user's UI language; when it is not ``all``, the
-  engine adds ``filter=language:<iso2>`` (e.g. ``language:fr``). If OpenAlex has
-  few results for that language, you may see fewer items.
-- Results typically include a main link. When the primary landing page from
-  OpenAlex is a DOI resolver, the engine will use that stable link. When an open
-  access link is available, it is exposed via the ``PDF`` and/or ``HTML`` links
-  in the result footer.
-
-
-What is returned
-================
-
-Each result uses the ``paper.html`` template and may include:
-
-- ``title`` and ``content`` (abstract; reconstructed from the inverted index)
-- ``authors`` (display names)
-- ``journal`` (host venue display name) and ``publisher``
-- ``doi`` (normalized to the plain DOI, without the ``https://doi.org/`` prefix)
-- ``tags`` (OpenAlex concepts display names)
-- ``pdf_url`` (Open access PDF if available) and ``html_url`` (landing page)
-- ``publishedDate`` (parsed from ``publication_date``)
-- ``pages``, ``volume``, ``number`` (issue)
-- ``type`` and a brief ``comments`` string with citation count
-
-
-Rate limits & polite pool
-=========================
-
-OpenAlex offers a free public API with generous daily limits. For extra courtesy
-and improved service quality, include a contact email in each request via
-``mailto``. You can set it directly in the engine configuration as shown above.
-See: `OpenAlex API overview`_.
-
-
-Troubleshooting
-===============
-
-- Few or no results in a non-English UI language:
-  Ensure the selected language has sufficient coverage at OpenAlex, or set the
-  UI language to English and retry.
-- Preference changes fail while testing locally:
-  Make sure your ``server.secret_key`` and ``server.base_url`` are set in your
-  instance settings so signed cookies work; see :ref:`settings server`.
-
-
-Implementation
-===============
 
 .. automodule:: searx.engines.openalex
    :members:

docs/dev/engines/online/openlibrary.rst

@@ -0,0 +1,8 @@
+.. _openlibrary engine:
+
+============
+Open Library
+============
+
+.. automodule:: searx.engines.openlibrary
+   :members:

docs/dev/engines/online/pubmed.rst

@@ -0,0 +1,8 @@
+.. _pubmed engine:
+
+======
+PubMed
+======
+
+.. automodule:: searx.engines.pubmed
+   :members:

docs/dev/engines/online/semantic_scholar.rst

@@ -0,0 +1,8 @@
+.. _semantic_scholar engine:
+
+================
+Semantic Scholar
+================
+
+.. automodule:: searx.engines.semantic_scholar
+   :members:

docs/dev/engines/online/springer.rst

@@ -0,0 +1,8 @@
+.. _springer engine:
+
+===============
+Springer Nature
+===============
+
+.. automodule:: searx.engines.springer
+   :members:

docs/dev/result_types/main/paper.rst

@@ -0,0 +1,7 @@
+.. _result_types.paper:
+
+=============
+Paper Results
+=============
+
+.. automodule:: searx.result_types.paper

docs/dev/result_types/main_result.rst

@@ -16,6 +16,7 @@ following types have been implemented so far ..
    main/mainresult
    main/keyvalue
    main/code
+   main/paper
 
 The :ref:`LegacyResult <LegacyResult>` is used internally for the results that
 have not yet been typed.  The templates can be used as orientation until the
@@ -26,7 +27,6 @@ final typing is complete.
 - :ref:`template videos`
 - :ref:`template torrent`
 - :ref:`template map`
-- :ref:`template paper`
 - :ref:`template packages`
 - :ref:`template files`
 - :ref:`template products`

manage

@@ -159,7 +159,6 @@ webapp.run() {
         GRANIAN_HOST="::" \
         GRANIAN_PORT="8888" \
         GRANIAN_WEBSOCKETS="false" \
-        GRANIAN_LOOP="uvloop" \
         GRANIAN_BLOCKING_THREADS="4" \
         GRANIAN_WORKERS_KILL_TIMEOUT="30s" \
         GRANIAN_BLOCKING_THREADS_IDLE_TIMEOUT="5m" \

requirements.txt

@@ -10,7 +10,6 @@ pyyaml==6.0.2
 httpx[http2]==0.28.1
 httpx-socks[asyncio]==0.10.0
 Brotli==1.1.0
-uvloop==0.21.0
 setproctitle==1.3.7
 valkey==6.1.1
 markdown-it-py==3.0.0

searx/engines/annas_archive.py

@@ -23,10 +23,12 @@ for *newest* articles and journals (PDF) / by shortcut ``!aaa <search-term>``.
 
   - name: annas articles
     engine: annas_archive
+    categories = ["general", "articles"]
     shortcut: aaa
-    aa_content: 'magazine'
+    aa_content: "magazine"
-    aa_ext: 'pdf'
+    aa_ext: "pdf"
-    aa_sort: 'newest'
+    aa_sort: "newest"
+
 
 Implementations
 ===============
@@ -47,6 +49,7 @@ from searx.result_types import EngineResults
 
 if t.TYPE_CHECKING:
     from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
 
 # about
 about: dict[str, t.Any] = {
@@ -59,7 +62,7 @@ about: dict[str, t.Any] = {
 }
 
 # engine dependent config
-categories: list[str] = ["files"]
+categories = ["files", "books"]
 paging: bool = True
 
 # search-url
@@ -72,14 +75,14 @@ aa_content: str = ""
 
 To not filter use an empty string (default).
 """
-aa_sort: str = ''
+aa_sort: str = ""
 """Sort Anna's results, possible values::
 
     newest, oldest, largest, smallest
 
 To sort by *most relevant* use an empty string (default)."""
 
-aa_ext: str = ''
+aa_ext: str = ""
 """Filter Anna's results by a file ending.  Common filters for example are
 ``pdf`` and ``epub``.
 
@@ -91,29 +94,31 @@ aa_ext: str = ''
 """
 
 
-def init(engine_settings: dict[str, t.Any]) -> None:  # pylint: disable=unused-argument
+def setup(engine_settings: dict[str, t.Any]) -> bool:  # pylint: disable=unused-argument
     """Check of engine's settings."""
-    traits = EngineTraits(**ENGINE_TRAITS['annas archive'])
+    traits = EngineTraits(**ENGINE_TRAITS["annas archive"])
 
-    if aa_content and aa_content not in traits.custom['content']:
+    if aa_content and aa_content not in traits.custom["content"]:
-        raise ValueError(f'invalid setting content: {aa_content}')
+        raise ValueError(f"invalid setting content: {aa_content}")
 
-    if aa_sort and aa_sort not in traits.custom['sort']:
+    if aa_sort and aa_sort not in traits.custom["sort"]:
-        raise ValueError(f'invalid setting sort: {aa_sort}')
+        raise ValueError(f"invalid setting sort: {aa_sort}")
 
-    if aa_ext and aa_ext not in traits.custom['ext']:
+    if aa_ext and aa_ext not in traits.custom["ext"]:
-        raise ValueError(f'invalid setting ext: {aa_ext}')
+        raise ValueError(f"invalid setting ext: {aa_ext}")
+
+    return True
 
 
-def request(query: str, params: dict[str, t.Any]) -> None:
+def request(query: str, params: "OnlineParams") -> None:
-    lang = traits.get_language(params["language"], traits.all_locale)
+    lang = traits.get_language(params["searxng_locale"], traits.all_locale)
     args = {
-        'lang': lang,
+        "lang": lang,
-        'content': aa_content,
+        "content": aa_content,
-        'ext': aa_ext,
+        "ext": aa_ext,
-        'sort': aa_sort,
+        "sort": aa_sort,
-        'q': query,
+        "q": query,
-        'page': params['pageno'],
+        "page": params["pageno"],
     }
     # filter out None and empty values
     filtered_args = dict((k, v) for k, v in args.items() if v)
@@ -126,29 +131,28 @@ def response(resp: "SXNG_Response") -> EngineResults:
 
     # The rendering of the WEB page is strange; positions of Anna's result page
     # are enclosed in SGML comments.  These comments are *uncommented* by some
-    # JS code, see query of class '.js-scroll-hidden' in Anna's HTML template:
+    # JS code, see query of class ".js-scroll-hidden" in Anna's HTML template:
     #   https://annas-software.org/AnnaArchivist/annas-archive/-/blob/main/allthethings/templates/macros/md5_list.html
 
-    for item in eval_xpath_list(dom, '//main//div[contains(@class, "js-aarecord-list-outer")]/div'):
+    for item in eval_xpath_list(dom, "//main//div[contains(@class, 'js-aarecord-list-outer')]/div"):
         try:
             kwargs: dict[str, t.Any] = _get_result(item)
         except SearxEngineXPathException:
             continue
-        res.add(res.types.LegacyResult(**kwargs))
+        res.add(res.types.Paper(**kwargs))
     return res
 
 
 def _get_result(item: ElementBase) -> dict[str, t.Any]:
     return {
-        'template': 'paper.html',
+        "url": base_url + eval_xpath_getindex(item, "./a/@href", 0),
-        'url': base_url + eval_xpath_getindex(item, './a/@href', 0),
+        "title": extract_text(eval_xpath(item, "./div//a[starts-with(@href, '/md5')]")),
-        'title': extract_text(eval_xpath(item, './div//a[starts-with(@href, "/md5")]')),
+        "authors": [extract_text(eval_xpath_getindex(item, ".//a[starts-with(@href, '/search')]", 0))],
-        'authors': [extract_text(eval_xpath_getindex(item, './/a[starts-with(@href, "/search")]', 0))],
+        "publisher": extract_text(
-        'publisher': extract_text(
+            eval_xpath_getindex(item, ".//a[starts-with(@href, '/search')]", 1, default=None), allow_none=True
-            eval_xpath_getindex(item, './/a[starts-with(@href, "/search")]', 1, default=None), allow_none=True
         ),
-        'content': extract_text(eval_xpath(item, './/div[contains(@class, "relative")]')),
+        "content": extract_text(eval_xpath(item, ".//div[contains(@class, 'relative')]")),
-        'thumbnail': extract_text(eval_xpath_getindex(item, './/img/@src', 0, default=None), allow_none=True),
+        "thumbnail": extract_text(eval_xpath_getindex(item, ".//img/@src", 0, default=None), allow_none=True),
     }
 
 
@@ -160,25 +164,25 @@ def fetch_traits(engine_traits: EngineTraits):
     from searx.network import get  # see https://github.com/searxng/searxng/issues/762
     from searx.locales import language_tag
 
-    engine_traits.all_locale = ''
+    engine_traits.all_locale = ""
-    engine_traits.custom['content'] = []
+    engine_traits.custom["content"] = []
-    engine_traits.custom['ext'] = []
+    engine_traits.custom["ext"] = []
-    engine_traits.custom['sort'] = []
+    engine_traits.custom["sort"] = []
 
-    resp = get(base_url + '/search')
+    resp = get(base_url + "/search")
     if not resp.ok:
         raise RuntimeError("Response from Anna's search page is not OK.")
     dom = html.fromstring(resp.text)
 
     # supported language codes
 
-    lang_map = {}
+    lang_map: dict[str, str] = {}
     for x in eval_xpath_list(dom, "//form//input[@name='lang']"):
         eng_lang = x.get("value")
-        if eng_lang in ('', '_empty', 'nl-BE', 'und') or eng_lang.startswith('anti__'):
+        if eng_lang in ("", "_empty", "nl-BE", "und") or eng_lang.startswith("anti__"):
             continue
         try:
-            locale = babel.Locale.parse(lang_map.get(eng_lang, eng_lang), sep='-')
+            locale = babel.Locale.parse(lang_map.get(eng_lang, eng_lang), sep="-")
         except babel.UnknownLocaleError:
             # silently ignore unknown languages
             # print("ERROR: %s -> %s is unknown by babel" % (x.get("data-name"), eng_lang))
@@ -193,16 +197,16 @@ def fetch_traits(engine_traits: EngineTraits):
 
     for x in eval_xpath_list(dom, "//form//input[@name='content']"):
         if not x.get("value").startswith("anti__"):
-            engine_traits.custom['content'].append(x.get("value"))
+            engine_traits.custom["content"].append(x.get("value"))
 
     for x in eval_xpath_list(dom, "//form//input[@name='ext']"):
         if not x.get("value").startswith("anti__"):
-            engine_traits.custom['ext'].append(x.get("value"))
+            engine_traits.custom["ext"].append(x.get("value"))
 
     for x in eval_xpath_list(dom, "//form//select[@name='sort']//option"):
-        engine_traits.custom['sort'].append(x.get("value"))
+        engine_traits.custom["sort"].append(x.get("value"))
 
     # for better diff; sort the persistence of these traits
-    engine_traits.custom['content'].sort()
+    engine_traits.custom["content"].sort()
-    engine_traits.custom['ext'].sort()
+    engine_traits.custom["ext"].sort()
-    engine_traits.custom['sort'].sort()
+    engine_traits.custom["sort"].sort()

searx/engines/arxiv.py

@@ -1,110 +1,129 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""ArXiV (Scientific preprints)
+"""arXiv is a free distribution service and an open-access archive for nearly
+2.4 million scholarly articles in the fields of physics, mathematics, computer
+science, quantitative biology, quantitative finance, statistics, electrical
+engineering and systems science, and economics.
 
+The engine uses the `arXiv API`_.
+
+.. _arXiv API: https://info.arxiv.org/help/api/user-manual.html
 """
 
+import typing as t
+
 from datetime import datetime
+from urllib.parse import urlencode
 
 from lxml import etree
 from lxml.etree import XPath
 from searx.utils import eval_xpath, eval_xpath_list, eval_xpath_getindex
+from searx.result_types import EngineResults
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
 
-# about
 about = {
-    "website": 'https://arxiv.org',
+    "website": "https://arxiv.org",
-    "wikidata_id": 'Q118398',
+    "wikidata_id": "Q118398",
-    "official_api_documentation": 'https://arxiv.org/help/api',
+    "official_api_documentation": "https://info.arxiv.org/help/api/user-manual.html",
     "use_official_api": True,
     "require_api_key": False,
-    "results": 'XML-RSS',
+    "results": "XML-RSS",
 }
 
-categories = ['science', 'scientific publications']
+categories = ["science", "scientific publications"]
 paging = True
+arxiv_max_results = 10
+arxiv_search_prefix = "all"
+"""Search fields, for more details see, `Details of Query Construction`_.
 
-base_url = (
+.. _Details of Query Construction:
-    'https://export.arxiv.org/api/query?search_query=all:' + '{query}&start={offset}&max_results={number_of_results}'
+   https://info.arxiv.org/help/api/user-manual.html#51-details-of-query-construction
-)
+"""
 
-# engine dependent config
+base_url = "https://export.arxiv.org/api/query"
-number_of_results = 10
+"""`arXiv API`_ URL, for more details see Query-Interface_
+
+.. _Query-Interface: https://info.arxiv.org/help/api/user-manual.html#_query_interface
+"""
 
-# xpaths
 arxiv_namespaces = {
     "atom": "http://www.w3.org/2005/Atom",
     "arxiv": "http://arxiv.org/schemas/atom",
 }
-xpath_entry = XPath('//atom:entry', namespaces=arxiv_namespaces)
+xpath_entry = XPath("//atom:entry", namespaces=arxiv_namespaces)
-xpath_title = XPath('.//atom:title', namespaces=arxiv_namespaces)
+xpath_title = XPath(".//atom:title", namespaces=arxiv_namespaces)
-xpath_id = XPath('.//atom:id', namespaces=arxiv_namespaces)
+xpath_id = XPath(".//atom:id", namespaces=arxiv_namespaces)
-xpath_summary = XPath('.//atom:summary', namespaces=arxiv_namespaces)
+xpath_summary = XPath(".//atom:summary", namespaces=arxiv_namespaces)
-xpath_author_name = XPath('.//atom:author/atom:name', namespaces=arxiv_namespaces)
+xpath_author_name = XPath(".//atom:author/atom:name", namespaces=arxiv_namespaces)
-xpath_doi = XPath('.//arxiv:doi', namespaces=arxiv_namespaces)
+xpath_doi = XPath(".//arxiv:doi", namespaces=arxiv_namespaces)
-xpath_pdf = XPath('.//atom:link[@title="pdf"]', namespaces=arxiv_namespaces)
+xpath_pdf = XPath(".//atom:link[@title='pdf']", namespaces=arxiv_namespaces)
-xpath_published = XPath('.//atom:published', namespaces=arxiv_namespaces)
+xpath_published = XPath(".//atom:published", namespaces=arxiv_namespaces)
-xpath_journal = XPath('.//arxiv:journal_ref', namespaces=arxiv_namespaces)
+xpath_journal = XPath(".//arxiv:journal_ref", namespaces=arxiv_namespaces)
-xpath_category = XPath('.//atom:category/@term', namespaces=arxiv_namespaces)
+xpath_category = XPath(".//atom:category/@term", namespaces=arxiv_namespaces)
-xpath_comment = XPath('./arxiv:comment', namespaces=arxiv_namespaces)
+xpath_comment = XPath("./arxiv:comment", namespaces=arxiv_namespaces)
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams") -> None:
-    # basic search
-    offset = (params['pageno'] - 1) * number_of_results
 
-    string_args = {'query': query, 'offset': offset, 'number_of_results': number_of_results}
+    args = {
-
+        "search_query": f"{arxiv_search_prefix}:{query}",
-    params['url'] = base_url.format(**string_args)
+        "start": (params["pageno"] - 1) * arxiv_max_results,
-
+        "max_results": arxiv_max_results,
-    return params
+    }
+    params["url"] = f"{base_url}?{urlencode(args)}"
 
 
-def response(resp):
+def response(resp: "SXNG_Response") -> EngineResults:
-    results = []
+
+    res = EngineResults()
+
     dom = etree.fromstring(resp.content)
     for entry in eval_xpath_list(dom, xpath_entry):
-        title = eval_xpath_getindex(entry, xpath_title, 0).text
 
-        url = eval_xpath_getindex(entry, xpath_id, 0).text
+        title: str = eval_xpath_getindex(entry, xpath_title, 0).text
-        abstract = eval_xpath_getindex(entry, xpath_summary, 0).text
 
-        authors = [author.text for author in eval_xpath_list(entry, xpath_author_name)]
+        url: str = eval_xpath_getindex(entry, xpath_id, 0).text
+        abstract: str = eval_xpath_getindex(entry, xpath_summary, 0).text
+
+        authors: list[str] = [author.text for author in eval_xpath_list(entry, xpath_author_name)]
 
         #  doi
         doi_element = eval_xpath_getindex(entry, xpath_doi, 0, default=None)
-        doi = None if doi_element is None else doi_element.text
+        doi: str = "" if doi_element is None else doi_element.text
 
         # pdf
         pdf_element = eval_xpath_getindex(entry, xpath_pdf, 0, default=None)
-        pdf_url = None if pdf_element is None else pdf_element.attrib.get('href')
+        pdf_url: str = "" if pdf_element is None else pdf_element.attrib.get("href")
 
         # journal
         journal_element = eval_xpath_getindex(entry, xpath_journal, 0, default=None)
-        journal = None if journal_element is None else journal_element.text
+        journal: str = "" if journal_element is None else journal_element.text
 
         # tags
         tag_elements = eval_xpath(entry, xpath_category)
-        tags = [str(tag) for tag in tag_elements]
+        tags: list[str] = [str(tag) for tag in tag_elements]
 
         # comments
         comments_elements = eval_xpath_getindex(entry, xpath_comment, 0, default=None)
-        comments = None if comments_elements is None else comments_elements.text
+        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.strptime(eval_xpath_getindex(entry, xpath_published, 0).text, "%Y-%m-%dT%H:%M:%SZ")
 
-        res_dict = {
+        res.add(
-            'template': 'paper.html',
+            res.types.Paper(
-            'url': url,
+                url=url,
-            'title': title,
+                title=title,
-            'publishedDate': publishedDate,
+                publishedDate=publishedDate,
-            'content': abstract,
+                content=abstract,
-            'doi': doi,
+                doi=doi,
-            'authors': authors,
+                authors=authors,
-            'journal': journal,
+                journal=journal,
-            'tags': tags,
+                tags=tags,
-            'comments': comments,
+                comments=comments,
-            'pdf_url': pdf_url,
+                pdf_url=pdf_url,
-        }
+            )
+        )
 
-        results.append(res_dict)
+    return res
-
-    return results

searx/engines/astrophysics_data_system.py

@@ -1,93 +1,163 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-""".. sidebar:: info
+"""The Astrophysics Data System (ADS_) is a digital library portal for
+researchers in astronomy and physics, operated by the Smithsonian Astrophysical
+Observatory (SAO) under a NASA grant.  The ADS_ is a solr instance, but not with
+the standard API paths.
 
-The Astrophysics Data System (ADS) is a digital library portal for researchers in astronomy and physics,
+.. note::
-operated by the Smithsonian Astrophysical Observatory (SAO) under a NASA grant.
-The engine is adapted from the solr engine.
 
+   The ADS_ engine requires an :py:obj:`API key <api_key>`.
+
+This engine uses the `search/query`_ API endpoint.  Since the user's search term
+is passed through, the `search syntax`_ of ADS can be used (at least to some
+extent).
+
+.. _ADS: https://ui.adsabs.harvard.edu
+.. _search/query: https://ui.adsabs.harvard.edu/help/api/api-docs.html#get-/search/query
+.. _search syntax: https://ui.adsabs.harvard.edu/help/search/search-syntax
+
+
+Configuration
+=============
+
+The engine has the following additional settings:
+
+- :py:obj:`api_key`
+- :py:obj:`ads_sort`
+
+.. code:: yaml
+
+  - name: astrophysics data system
+    api_key: "..."
+    inactive: false
+
+
+Implementations
+===============
 """
 
-# pylint: disable=global-statement
+import typing as t
 
 from datetime import datetime
-from json import loads
 from urllib.parse import urlencode
+
+from searx.utils import html_to_text
 from searx.exceptions import SearxEngineAPIException
+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://ui.adsabs.harvard.edu/',
+    "website": "https://ui.adsabs.harvard.edu/",
-    "wikidata_id": 'Q752099',
+    "wikidata_id": "Q752099",
-    "official_api_documentation": 'https://ui.adsabs.harvard.edu/help/api/api-docs.html',
+    "official_api_documentation": "https://ui.adsabs.harvard.edu/help/api/api-docs.html",
     "use_official_api": True,
     "require_api_key": True,
-    "results": 'JSON',
+    "results": "JSON",
 }
 
-base_url = 'https://api.adsabs.harvard.edu/v1/search'
+categories = ["science", "scientific publications"]
-result_base_url = 'https://ui.adsabs.harvard.edu/abs/'
-rows = 10
-sort = ''  # sorting: asc or desc
-field_list = ['bibcode', 'author', 'title', 'abstract', 'doi', 'date']  # list of field names to display on the UI
-default_fields = ''  # default field to query
-query_fields = ''  # query fields
 paging = True
-api_key = 'unset'
+base_url = "https://api.adsabs.harvard.edu/v1/search/query"
+
+api_key = "unset"
+"""Get an API token as described in https://ui.adsabs.harvard.edu/help/api"""
+
+ads_field_list = [
+    "abstract",
+    "author",
+    "bibcode",
+    "comment",
+    "date",
+    "doi",
+    "isbn",
+    "issn",
+    "keyword",
+    "page",
+    "page_count",
+    "page_range",
+    "pub",
+    "pubdate",
+    "pubnote",
+    "read_count",
+    "title",
+    "volume",
+    "year",
+]
+"""Set of fields to return in the response from ADS."""
+
+ads_rows = 10
+"""How many records to return for the ADS request."""
+
+ads_sort = "read_count desc"
+"""The format is 'field' + 'direction' where direction is one of 'asc' or 'desc'
+and field is any of the valid indexes."""
 
 
-def init(_):
+def setup(engine_settings: dict[str, t.Any]) -> bool:
-    if api_key == 'unset':
+    """Initialization of the ADS_ engine, checks whether the :py:obj:`api_key`
-        raise SearxEngineAPIException('missing ADS API key')
+    is set, otherwise the engine is inactive.
+    """
+    key: str = engine_settings.get("api_key", "")
+    if key and key not in ("unset", "unknown", "..."):
+        return True
+    logger.error("Astrophysics Data System (ADS) API key is not set or invalid.")
+    return False
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams") -> None:
-    query_params = {'q': query, 'rows': rows}
-    if field_list:
-        query_params['fl'] = ','.join(field_list)
-    if query_fields:
-        query_params['qf'] = ','.join(query_fields)
-    if default_fields:
-        query_params['df'] = default_fields
-    if sort:
-        query_params['sort'] = sort
 
-    query_params['start'] = rows * (params['pageno'] - 1)
+    args: dict[str, str | int] = {
+        "q": query,
+        "fl": ",".join(ads_field_list),
+        "rows": ads_rows,
+        "start": ads_rows * (params["pageno"] - 1),
+    }
+    if ads_sort:
+        args["sort"] = ads_sort
 
-    params['headers']['Authorization'] = f'Bearer {api_key}'
+    params["headers"]["Authorization"] = f"Bearer {api_key}"
-    params['url'] = f"{base_url}/query?{urlencode(query_params)}"
+    params["url"] = f"{base_url}?{urlencode(args)}"
-
-    return params
 
 
-def response(resp):
+def response(resp: "SXNG_Response") -> EngineResults:
-    try:
-        resp_json = loads(resp.text)
-    except Exception as e:
-        raise SearxEngineAPIException("failed to parse response") from e
 
-    if 'error' in resp_json:
+    res = EngineResults()
-        raise SearxEngineAPIException(resp_json['error']['msg'])
+    json_data: dict[str, dict[str, t.Any]] = resp.json()
 
-    resp_json = resp_json["response"]
+    if "error" in json_data:
-    result_len = resp_json["numFound"]
+        raise SearxEngineAPIException(json_data["error"]["msg"])
-    results = []
 
-    for res in resp_json["docs"]:
+    def _str(k: str) -> str:
-        author = res.get("author")
+        return str(doc.get(k, ""))
 
-        if author:
+    def _list(k: str) -> list[str]:
-            author = author[0] + ' et al.'
+        return doc.get(k, [])
 
-        results.append(
+    for doc in json_data["response"]["docs"]:
-            {
+        authors: list[str] = doc["author"]
-                'url': result_base_url + res.get("bibcode") + "/",
+        if len(authors) > 15:
-                'title': res.get("title")[0],
+            # There are articles with hundreds of authors
-                'author': author,
+            authors = authors[:15] + ["et al."]
-                'content': res.get("abstract"),
+
-                'doi': res.get("doi"),
+        paper = res.types.Paper(
-                'publishedDate': datetime.fromisoformat(res.get("date")),
+            url=f"https://ui.adsabs.harvard.edu/abs/{doc.get('bibcode')}/",
-            }
+            title=html_to_text(_list("title")[0]),
+            authors=authors,
+            content=html_to_text(_str("abstract")),
+            doi=_list("doi")[0],
+            issn=_list("issn"),
+            isbn=_list("isbn"),
+            tags=_list("keyword"),
+            pages=",".join(_list("page")),
+            publisher=_str("pub") + " " + _str("year"),
+            publishedDate=datetime.fromisoformat(_str("date")),
+            volume=_str("volume"),
+            views=_str("read_count"),
+            comments=" / ".join(_list("pubnote")),
         )
+        res.add(paper)
 
-    results.append({'number_of_results': result_len})
+    return res
-
-    return results

searx/engines/core.py

@@ -5,6 +5,10 @@ research from repositories and journals.
 
 .. _CORE: https://core.ac.uk/about
 
+.. note::
+
+   The CORE engine requires an :py:obj:`API key <api_key>`.
+
 .. _core engine config:
 
 Configuration
@@ -17,135 +21,141 @@ The engine has the following additional settings:
 .. code:: yaml
 
   - name: core.ac.uk
-    engine: core
-    categories: science
-    shortcut: cor
     api_key: "..."
-    timeout: 5
+    inactive: false
 
 Implementations
 ===============
 
 """
-# pylint: disable=too-many-branches
+
+import typing as t
 
 from datetime import datetime
 from urllib.parse import urlencode
 
-from searx.exceptions import SearxEngineAPIException
+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://core.ac.uk',
+    "website": "https://core.ac.uk",
-    "wikidata_id": 'Q22661180',
+    "wikidata_id": "Q22661180",
-    "official_api_documentation": 'https://api.core.ac.uk/docs/v3',
+    "official_api_documentation": "https://api.core.ac.uk/docs/v3",
     "use_official_api": True,
     "require_api_key": True,
-    "results": 'JSON',
+    "results": "JSON",
 }
 
-api_key = 'unset'
+api_key = ""
 """For an API key register at https://core.ac.uk/services/api and insert
 the API key in the engine :ref:`core engine config`."""
 
-categories = ['science', 'scientific publications']
+categories = ["science", "scientific publications"]
 paging = True
 nb_per_page = 10
-base_url = 'https://api.core.ac.uk/v3/search/works/'
+base_url = "https://api.core.ac.uk/v3/search/works/"
 
 
-def request(query, params):
+def setup(engine_settings: dict[str, t.Any]) -> bool:
-    if api_key == 'unset':
+    """Initialization of the CORE_ engine, checks whether the :py:obj:`api_key`
-        raise SearxEngineAPIException('missing CORE API key')
+    is set, otherwise the engine is inactive.
+    """
+
+    key: str = engine_settings.get("api_key", "")
+    if key and key not in ("unset", "unknown", "..."):
+        return True
+    logger.error("CORE's API key is not set or invalid.")
+    return False
+
+
+def request(query: str, params: "OnlineParams") -> None:
 
     # API v3 uses different parameters
     search_params = {
-        'q': query,
+        "q": query,
-        'offset': (params['pageno'] - 1) * nb_per_page,
+        "offset": (params["pageno"] - 1) * nb_per_page,
-        'limit': nb_per_page,
+        "limit": nb_per_page,
-        'sort': 'relevance',
+        "sort": "relevance",
     }
 
-    params['url'] = base_url + '?' + urlencode(search_params)
+    params["url"] = base_url + "?" + urlencode(search_params)
-    params['headers'] = {'Authorization': f'Bearer {api_key}'}
+    params["headers"] = {"Authorization": f"Bearer {api_key}"}
-
-    return params
 
 
-def response(resp):
+def response(resp: "SXNG_Response") -> EngineResults:
-    results = []
+    # pylint: disable=too-many-branches
+    res = EngineResults()
     json_data = resp.json()
 
-    for result in json_data.get('results', []):
+    for result in json_data.get("results", []):
         # Get title
-        if not result.get('title'):
+        if not result.get("title"):
             continue
 
         # Get URL - try different options
-        url = None
+        url: str | None = None
 
         # Try DOI first
-        doi = result.get('doi')
+        doi: str = result.get("doi")
         if doi:
-            url = f'https://doi.org/{doi}'
+            url = f"https://doi.org/{doi}"
 
-        if url is None and result.get('doi'):
+        if url is None and result.get("doi"):
             # use the DOI reference
-            url = 'https://doi.org/' + str(result['doi'])
+            url = "https://doi.org/" + str(result["doi"])
-        elif result.get('id'):
+        elif result.get("id"):
-            url = 'https://core.ac.uk/works/' + str(result['id'])
+            url = "https://core.ac.uk/works/" + str(result["id"])
-        elif result.get('downloadUrl'):
+        elif result.get("downloadUrl"):
-            url = result['downloadUrl']
+            url = result["downloadUrl"]
-        elif result.get('sourceFulltextUrls'):
+        elif result.get("sourceFulltextUrls"):
-            url = result['sourceFulltextUrls']
+            url = result["sourceFulltextUrls"]
         else:
             continue
 
         # Published date
         published_date = None
 
-        raw_date = result.get('publishedDate') or result.get('depositedDate')
+        raw_date = result.get("publishedDate") or result.get("depositedDate")
         if raw_date:
             try:
-                published_date = datetime.fromisoformat(result['publishedDate'].replace('Z', '+00:00'))
+                published_date = datetime.fromisoformat(result["publishedDate"].replace("Z", "+00:00"))
             except (ValueError, AttributeError):
                 pass
 
         # Handle journals
         journals = []
-        if result.get('journals'):
+        if result.get("journals"):
-            journals = [j.get('title') for j in result['journals'] if j.get('title')]
+            journals = [j.get("title") for j in result["journals"] if j.get("title")]
 
         # Handle publisher
-        publisher = result.get('publisher', '').strip("'")
+        publisher = result.get("publisher", "").strip("'")
-        if publisher:
-            publisher = publisher.strip("'")
 
         # Handle authors
-        authors = set()
+        authors: set[str] = set()
-        for i in result.get('authors', []):
+        for i in result.get("authors", []):
-            name = i.get("name")
+            name: str | None = i.get("name")
             if name:
                 authors.add(name)
 
-        results.append(
+        res.add(
-            {
+            res.types.Paper(
-                'template': 'paper.html',
+                title=result.get("title"),
-                'title': result.get('title'),
+                url=url,
-                'url': url,
+                content=result.get("fullText", "") or "",
-                'content': result.get('fullText', '') or '',
+                tags=result.get("fieldOfStudy", []),
-                # 'comments': '',
+                publishedDate=published_date,
-                'tags': result.get('fieldOfStudy', []),
+                type=result.get("documentType", "") or "",
-                'publishedDate': published_date,
+                authors=authors,
-                'type': result.get('documentType', '') or '',
+                editor=", ".join(result.get("contributors", [])),
-                'authors': authors,
+                publisher=publisher,
-                'editor': ', '.join(result.get('contributors', [])),
+                journal=", ".join(journals),
-                'publisher': publisher,
+                doi=result.get("doi"),
-                'journal': ', '.join(journals),
+                pdf_url=result.get("downloadUrl", {}) or result.get("sourceFulltextUrls", {}),
-                'doi': result.get('doi'),
+            )
-                # 'issn' : ''
-                # 'isbn' : ''
-                'pdf_url': result.get('downloadUrl', {}) or result.get("sourceFulltextUrls", {}),
-            }
         )
 
-    return results
+    return res

searx/engines/crossref.py

@@ -1,14 +1,27 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""CrossRef"""
+"""Crossref_ is the sustainable source of community-owned scholarly metadata and
+is relied upon by thousands of systems across the research ecosystem and the
+globe.
+
+.. _Crossref: https://www.crossref.org/documentation/retrieve-metadata/
+
+"""
+
+import typing as t
 
 from urllib.parse import urlencode
 from datetime import datetime
+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.crossref.org/",
     "wikidata_id": "Q5188229",
-    "official_api_documentation": "https://api.crossref.org",
+    "official_api_documentation": "https://api.crossref.org/swagger-ui/",
-    "use_official_api": False,
+    "use_official_api": True,
     "require_api_key": False,
     "results": "JSON",
 }
@@ -16,48 +29,69 @@ about = {
 categories = ["science", "scientific publications"]
 paging = True
 search_url = "https://api.crossref.org/works"
+"""Returns a list of all works (journal articles, conference proceedings, books,
+components, etc), 20 per page (`Works/get_works`_).
+
+.. _Works/get_works: https://api.crossref.org/swagger-ui/index.html#/Works/get_works
+"""
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams") -> None:
-    params["url"] = search_url + "?" + urlencode({"query": query, "offset": 20 * (params["pageno"] - 1)})
+    args = {
-    return params
+        "query": query,
+        "offset": 20 * (params["pageno"] - 1),
+    }
+    params["url"] = f"{search_url}?{urlencode(args)}"
 
 
-def response(resp):
+def response(resp: "SXNG_Response") -> EngineResults:
-    results = []
+    res = EngineResults()
-    for record in resp.json()["message"]["items"]:
+    json_data = resp.json()
+
+    def field(k: str) -> str:
+        return str(record.get(k, ""))
+
+    for record in json_data["message"]["items"]:
 
         if record["type"] == "component":
-            # These seem to be files published along with papers. Not something you'd search for
+            # These seem to be files published along with papers. Not something
+            # you'd search for.
             continue
-        result = {
+        title: str = ""
-            "template": "paper.html",
+        journal: str = ""
-            "content": record.get("abstract", ""),
+
-            "doi": record.get("DOI"),
-            "pages": record.get("page"),
-            "publisher": record.get("publisher"),
-            "tags": record.get("subject"),
-            "type": record.get("type"),
-            "url": record.get("URL"),
-            "volume": record.get("volume"),
-        }
         if record["type"] == "book-chapter":
-            result["title"] = record["container-title"][0]
+            title = record["container-title"][0]
-            if record["title"][0].lower().strip() != result["title"].lower().strip():
+            if record["title"][0].lower().strip() != title.lower().strip():
-                result["title"] += f" ({record['title'][0]})"
+                title += f" ({record['title'][0]})"
         else:
-            result["title"] = record["title"][0] if "title" in record else record.get("container-title", [None])[0]
+            title = record["title"][0] if "title" in record else record.get("container-title", [None])[0]
-            result["journal"] = record.get("container-title", [None])[0] if "title" in record else None
+            journal = record.get("container-title", [None])[0] if "title" in record else ""
+
+        item = res.types.Paper(
+            title=title,
+            journal=journal,
+            content=field("abstract"),
+            doi=field("DOI"),
+            pages=field("page"),
+            publisher=field("publisher"),
+            tags=record.get("subject"),
+            type=field("type"),
+            url=field("URL"),
+            volume=field("volume"),
+        )
+        res.add(item)
 
         if "resource" in record and "primary" in record["resource"] and "URL" in record["resource"]["primary"]:
-            result["url"] = record["resource"]["primary"]["URL"]
+            item.url = record["resource"]["primary"]["URL"]
+
         if "published" in record and "date-parts" in record["published"]:
-            result["publishedDate"] = datetime(*(record["published"]["date-parts"][0] + [1, 1][:3]))
+            item.publishedDate = datetime(*(record["published"]["date-parts"][0] + [1, 1][:3]))
-        result["authors"] = [a.get("given", "") + " " + a.get("family", "") for a in record.get("author", [])]
+
-        result["isbn"] = record.get("isbn") or [i["value"] for i in record.get("isbn-type", [])]
+        item.authors = [a.get("given", "") + " " + a.get("family", "") for a in record.get("author", [])]
+        item.isbn = record.get("isbn") or [i["value"] for i in record.get("isbn-type", [])]
+
         # All the links are not PDFs, even if the URL ends with ".pdf"
-        # result["pdf_url"] = record.get("link", [{"URL": None}])[0]["URL"]
+        # item.pdf_url = record.get("link", [{"URL": None}])[0]["URL"]
 
-        results.append(result)
+    return res
-
-    return results

searx/engines/demo_online.py

@@ -57,7 +57,7 @@ about = {
 _my_online_engine = None
 
 
-def setup(engine_settings: dict[str, t.Any]) -> bool:
+def setup(engine_settings: "OnlineParams") -> bool:
     """Dynamic setup of the engine settings.
 
     For more details see :py:obj:`searx.enginelib.Engine.setup`."""

searx/engines/google.py

@@ -11,6 +11,8 @@ engines:
 
 """
 
+import typing as t
+
 import re
 import random
 import string
@@ -28,8 +30,10 @@ from searx.exceptions import SearxEngineCaptchaException
 from searx.enginelib.traits import EngineTraits
 from searx.result_types import EngineResults
 
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
 
-# about
 about = {
     "website": 'https://www.google.com',
     "wikidata_id": 'Q9366',
@@ -89,7 +93,7 @@ def ui_async(start: int) -> str:
     return ",".join([arc_id, use_ac, _fmt])
 
 
-def get_google_info(params, eng_traits):
+def get_google_info(params: "OnlineParams", eng_traits: EngineTraits) -> dict[str, t.Any]:
     """Composing various (language) properties for the google engines (:ref:`google
     API`).
 
@@ -144,7 +148,7 @@ def get_google_info(params, eng_traits):
 
     """
 
-    ret_val = {
+    ret_val: dict[str, t.Any] = {
         'language': None,
         'country': None,
         'subdomain': None,
@@ -273,7 +277,7 @@ def detect_google_sorry(resp):
         raise SearxEngineCaptchaException()
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams") -> None:
     """Google search request"""
     # pylint: disable=line-too-long
     start = (params['pageno'] - 1) * 10
@@ -317,7 +321,6 @@ def request(query, params):
 
     params['cookies'] = google_info['cookies']
     params['headers'].update(google_info['headers'])
-    return params
 
 
 # =26;[3,"dimg_ZNMiZPCqE4apxc8P3a2tuAQ_137"]a87;data:image/jpeg;base64,/9j/4AAQSkZJRgABA
@@ -341,7 +344,7 @@ def parse_data_images(text: str):
     return data_image_map
 
 
-def response(resp) -> EngineResults:
+def response(resp: "SXNG_Response"):
     """Get response from google's search request"""
     # pylint: disable=too-many-branches, too-many-statements
     detect_google_sorry(resp)

searx/engines/google_scholar.py

@@ -1,12 +1,29 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""This is the implementation of the Google Scholar engine.
+"""Google Scholar is a freely accessible web search engine that indexes the full
+text or metadata of scholarly literature across an array of publishing formats
+and disciplines.
 
 Compared to other Google services the Scholar engine has a simple GET REST-API
-and there does not exists `async` API.  Even though the API slightly vintage we
+and there does not exists ``async`` API.  Even though the API slightly vintage
-can make use of the :ref:`google API` to assemble the arguments of the GET
+we can make use of the :ref:`google API` to assemble the arguments of the GET
 request.
+
+Configuration
+=============
+
+.. code:: yaml
+
+  - name: google scholar
+    engine: google_scholar
+    shortcut: gos
+
+Implementations
+===============
+
 """
 
+import typing as t
+
 from urllib.parse import urlencode
 from datetime import datetime
 from lxml import html
@@ -16,6 +33,7 @@ from searx.utils import (
     eval_xpath_getindex,
     eval_xpath_list,
     extract_text,
+    ElementType,
 )
 
 from searx.exceptions import SearxEngineCaptchaException
@@ -26,18 +44,23 @@ from searx.engines.google import (
     time_range_dict,
 )
 
-# about
+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://scholar.google.com',
+    "website": "https://scholar.google.com",
-    "wikidata_id": 'Q494817',
+    "wikidata_id": "Q494817",
-    "official_api_documentation": 'https://developers.google.com/custom-search',
+    "official_api_documentation": "https://developers.google.com/custom-search",
     "use_official_api": False,
     "require_api_key": False,
-    "results": 'HTML',
+    "results": "HTML",
 }
 
 # engine dependent config
-categories = ['science', 'scientific publications']
+categories = ["science", "scientific publications"]
 paging = True
 max_page = 50
 """`Google max 50 pages`_
@@ -50,9 +73,97 @@ safesearch = False
 send_accept_language_header = True
 
 
-def time_range_args(params):
+def request(query: str, params: "OnlineParams") -> None:
+    """Google-Scholar search request"""
+
+    google_info = get_google_info(params, traits)
+    # subdomain is: scholar.google.xy
+    google_info["subdomain"] = google_info["subdomain"].replace("www.", "scholar.")
+
+    args = {
+        "q": query,
+        **google_info["params"],
+        "start": (params["pageno"] - 1) * 10,
+        "as_sdt": "2007",  # include patents / to disable set "0,5"
+        "as_vis": "0",  # include citations / to disable set "1"
+    }
+    args.update(time_range_args(params))
+
+    params["url"] = "https://" + google_info["subdomain"] + "/scholar?" + urlencode(args)
+    params["cookies"] = google_info["cookies"]
+    params["headers"].update(google_info["headers"])
+
+
+def response(resp: "SXNG_Response") -> EngineResults:  # pylint: disable=too-many-locals
+    """Parse response from Google Scholar"""
+
+    res = EngineResults()
+    dom = html.fromstring(resp.text)
+    detect_google_captcha(dom)
+
+    # parse results
+    for result in eval_xpath_list(dom, "//div[@data-rp]"):
+
+        title = extract_text(eval_xpath(result, ".//h3[1]//a"))
+        if not title:
+            # this is a [ZITATION] block
+            continue
+
+        pub_type: str = extract_text(eval_xpath(result, ".//span[@class='gs_ctg2']")) or ""
+        if pub_type:
+            pub_type = pub_type[1:-1].lower()
+
+        url: str = eval_xpath_getindex(result, ".//h3[1]//a/@href", 0)
+        content: str = extract_text(eval_xpath(result, ".//div[@class='gs_rs']")) or ""
+        authors, journal, publisher, publishedDate = parse_gs_a(
+            extract_text(eval_xpath(result, ".//div[@class='gs_a']"))
+        )
+        if publisher in url:
+            publisher = ""
+
+        # cited by
+        comments: str = (
+            extract_text(eval_xpath(result, ".//div[@class='gs_fl']/a[starts-with(@href,'/scholar?cites=')]")) or ""
+        )
+
+        # link to the html or pdf document
+        html_url: str = ""
+        pdf_url: str = ""
+        doc_url = eval_xpath_getindex(result, ".//div[@class='gs_or_ggsm']/a/@href", 0, default=None)
+        doc_type = extract_text(eval_xpath(result, ".//span[@class='gs_ctg2']"))
+        if doc_type == "[PDF]":
+            pdf_url = doc_url
+        else:
+            html_url = doc_url
+
+        res.add(
+            res.types.Paper(
+                type=pub_type,
+                url=url,
+                title=title,
+                authors=authors,
+                publisher=publisher,
+                journal=journal,
+                publishedDate=publishedDate,
+                content=content,
+                comments=comments,
+                html_url=html_url,
+                pdf_url=pdf_url,
+            )
+        )
+
+    # parse suggestion
+    for suggestion in eval_xpath(dom, "//div[contains(@class, 'gs_qsuggest_wrap')]//li//a"):
+        res.add(res.types.LegacyResult(suggestion=extract_text(suggestion)))
+
+    for correction in eval_xpath(dom, "//div[@class='gs_r gs_pda']/a"):
+        res.add(res.types.LegacyResult(correction=extract_text(correction)))
+    return res
+
+
+def time_range_args(params: "OnlineParams") -> dict[str, int]:
     """Returns a dictionary with a time range arguments based on
-    ``params['time_range']``.
+    ``params["time_range"]``.
 
     Google Scholar supports a detailed search by year.  Searching by *last
     month* or *last week* (as offered by SearXNG) is uncommon for scientific
@@ -60,21 +171,23 @@ def time_range_args(params):
 
     To limit the result list when the users selects a range, all the SearXNG
     ranges (*day*, *week*, *month*, *year*) are mapped to *year*.  If no range
-    is set an empty dictionary of arguments is returned.  Example;  when
+    is set an empty dictionary of arguments is returned.
-    user selects a time range (current year minus one in 2022):
+
+    Example; when user selects a time range and we find ourselves in the year
+    2025 (current year minus one):
 
     .. code:: python
 
-        { 'as_ylo' : 2021 }
+        { "as_ylo" : 2024 }
 
     """
-    ret_val = {}
+    ret_val: dict[str, int] = {}
-    if params['time_range'] in time_range_dict:
+    if params["time_range"] in time_range_dict:
-        ret_val['as_ylo'] = datetime.now().year - 1
+        ret_val["as_ylo"] = datetime.now().year - 1
     return ret_val
 
 
-def detect_google_captcha(dom):
+def detect_google_captcha(dom: ElementType):
     """In case of CAPTCHA Google Scholar open its own *not a Robot* dialog and is
     not redirected to ``sorry.google.com``.
     """
@@ -82,29 +195,7 @@ def detect_google_captcha(dom):
         raise SearxEngineCaptchaException()
 
 
-def request(query, params):
+def parse_gs_a(text: str | None) -> tuple[list[str], str, str, datetime | None]:
-    """Google-Scholar search request"""
-
-    google_info = get_google_info(params, traits)
-    # subdomain is: scholar.google.xy
-    google_info['subdomain'] = google_info['subdomain'].replace("www.", "scholar.")
-
-    args = {
-        'q': query,
-        **google_info['params'],
-        'start': (params['pageno'] - 1) * 10,
-        'as_sdt': '2007',  # include patents / to disable set '0,5'
-        'as_vis': '0',  # include citations / to disable set '1'
-    }
-    args.update(time_range_args(params))
-
-    params['url'] = 'https://' + google_info['subdomain'] + '/scholar?' + urlencode(args)
-    params['cookies'] = google_info['cookies']
-    params['headers'].update(google_info['headers'])
-    return params
-
-
-def parse_gs_a(text: str | None):
     """Parse the text written in green.
 
     Possible formats:
@@ -113,98 +204,28 @@ def parse_gs_a(text: str | None):
     * "{authors} - {publisher}"
     """
     if text is None or text == "":
-        return None, None, None, None
+        return [], "", "", None
 
-    s_text = text.split(' - ')
+    s_text = text.split(" - ")
-    authors = s_text[0].split(', ')
+    authors: list[str] = s_text[0].split(", ")
-    publisher = s_text[-1]
+    publisher: str = s_text[-1]
     if len(s_text) != 3:
-        return authors, None, publisher, None
+        return authors, "", publisher, None
 
     # the format is "{authors} - {journal}, {year} - {publisher}" or "{authors} - {year} - {publisher}"
     # get journal and year
-    journal_year = s_text[1].split(', ')
+    journal_year = s_text[1].split(", ")
     # journal is optional and may contains some coma
     if len(journal_year) > 1:
-        journal = ', '.join(journal_year[0:-1])
+        journal: str = ", ".join(journal_year[0:-1])
-        if journal == '…':
+        if journal == "…":
-            journal = None
+            journal = ""
     else:
-        journal = None
+        journal = ""
     # year
     year = journal_year[-1]
     try:
-        publishedDate = datetime.strptime(year.strip(), '%Y')
+        publishedDate = datetime.strptime(year.strip(), "%Y")
     except ValueError:
         publishedDate = None
     return authors, journal, publisher, publishedDate
-
-
-def response(resp):  # pylint: disable=too-many-locals
-    """Parse response from Google Scholar"""
-    results = []
-
-    # convert the text to dom
-    dom = html.fromstring(resp.text)
-    detect_google_captcha(dom)
-
-    # parse results
-    for result in eval_xpath_list(dom, '//div[@data-rp]'):
-
-        title = extract_text(eval_xpath(result, './/h3[1]//a'))
-
-        if not title:
-            # this is a [ZITATION] block
-            continue
-
-        pub_type = extract_text(eval_xpath(result, './/span[@class="gs_ctg2"]'))
-        if pub_type:
-            pub_type = pub_type[1:-1].lower()
-
-        url = eval_xpath_getindex(result, './/h3[1]//a/@href', 0)
-        content = extract_text(eval_xpath(result, './/div[@class="gs_rs"]'))
-        authors, journal, publisher, publishedDate = parse_gs_a(
-            extract_text(eval_xpath(result, './/div[@class="gs_a"]'))
-        )
-        if publisher in url:
-            publisher = None
-
-        # cited by
-        comments = extract_text(eval_xpath(result, './/div[@class="gs_fl"]/a[starts-with(@href,"/scholar?cites=")]'))
-
-        # link to the html or pdf document
-        html_url = None
-        pdf_url = None
-        doc_url = eval_xpath_getindex(result, './/div[@class="gs_or_ggsm"]/a/@href', 0, default=None)
-        doc_type = extract_text(eval_xpath(result, './/span[@class="gs_ctg2"]'))
-        if doc_type == "[PDF]":
-            pdf_url = doc_url
-        else:
-            html_url = doc_url
-
-        results.append(
-            {
-                'template': 'paper.html',
-                'type': pub_type,
-                'url': url,
-                'title': title,
-                'authors': authors,
-                'publisher': publisher,
-                'journal': journal,
-                'publishedDate': publishedDate,
-                'content': content,
-                'comments': comments,
-                'html_url': html_url,
-                'pdf_url': pdf_url,
-            }
-        )
-
-    # parse suggestion
-    for suggestion in eval_xpath(dom, '//div[contains(@class, "gs_qsuggest_wrap")]//li//a'):
-        # append suggestion
-        results.append({'suggestion': extract_text(suggestion)})
-
-    for correction in eval_xpath(dom, '//div[@class="gs_r gs_pda"]/a'):
-        results.append({'correction': extract_text(correction)})
-
-    return results

searx/engines/openalex.py

@@ -1,14 +1,103 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-# pylint: disable=missing-module-docstring
+"""The OpenAlex engine integrates the `OpenAlex`_ Works API to return scientific
-#
+paper results using the :ref:`result_types.paper` class.  It is an "online" JSON
-# Engine is documented in: docs/dev/engines/online/openalex.rst
+engine that uses the official public API and does not require an API key.
 
+.. _OpenAlex: https://openalex.org
+.. _OpenAlex API overview: https://docs.openalex.org/how-to-use-the-api/api-overview
+
+Key features
+------------
+
+- Uses the official Works endpoint (JSON)
+- Paging support via ``page`` and ``per-page``
+- Relevance sorting (``sort=relevance_score:desc``)
+- Language filter support (maps SearXNG language to ``filter=language:<iso2>``)
+- Maps fields commonly used in scholarly results: title, authors, abstract
+  (reconstructed from inverted index), journal/venue, publisher, DOI, tags
+  (concepts), PDF/HTML links, pages, volume, issue, published date, and a short
+  citations comment
+- Supports OpenAlex "polite pool" by adding a ``mailto`` parameter
+
+
+Configuration
+=============
+
+Minimal example for :origin:`settings.yml <searx/settings.yml>`:
+
+.. code:: yaml
+
+   - name: openalex
+     engine: openalex
+     shortcut: oa
+     categories: science, scientific publications
+     timeout: 5.0
+     # Recommended by OpenAlex: join the polite pool with an email address
+     mailto: "[email protected]"
+
+Notes
+-----
+
+- The ``mailto`` key is optional but recommended by OpenAlex for better service.
+- Language is inherited from the user's UI language; when it is not ``all``, the
+  engine adds ``filter=language:<iso2>`` (e.g. ``language:fr``). If OpenAlex has
+  few results for that language, you may see fewer items.
+- Results typically include a main link. When the primary landing page from
+  OpenAlex is a DOI resolver, the engine will use that stable link. When an open
+  access link is available, it is exposed via the ``PDF`` and/or ``HTML`` links
+  in the result footer.
+
+
+What is returned
+================
+
+Each result uses the :ref:`result_types.paper` class and may include:
+
+- ``title`` and ``content`` (abstract; reconstructed from the inverted index)
+- ``authors`` (display names)
+- ``journal`` (host venue display name) and ``publisher``
+- ``doi`` (normalized to the plain DOI, without the ``https://doi.org/`` prefix)
+- ``tags`` (OpenAlex concepts display names)
+- ``pdf_url`` (Open access PDF if available) and ``html_url`` (landing page)
+- ``publishedDate`` (parsed from ``publication_date``)
+- ``pages``, ``volume``, ``number`` (issue)
+- ``type`` and a brief ``comments`` string with citation count
+
+
+Rate limits & polite pool
+=========================
+
+OpenAlex offers a free public API with generous daily limits. For extra courtesy
+and improved service quality, include a contact email in each request via
+``mailto``. You can set it directly in the engine configuration as shown above.
+See: `OpenAlex API overview`_.
+
+
+Troubleshooting
+===============
+
+- Few or no results in a non-English UI language:
+  Ensure the selected language has sufficient coverage at OpenAlex, or set the
+  UI language to English and retry.
+- Preference changes fail while testing locally:
+  Make sure your ``server.secret_key`` and ``server.base_url`` are set in your
+  instance settings so signed cookies work; see :ref:`settings server`.
+
+
+Implementation
+===============
+
+"""
 
 import typing as t
+
 from datetime import datetime
 from urllib.parse import urlencode
 from searx.result_types import EngineResults
-from searx.extended_types import SXNG_Response
+
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
 
 # about
 about = {
@@ -31,7 +120,7 @@ search_url = "https://api.openalex.org/works"
 mailto = ""
 
 
-def request(query: str, params: dict[str, t.Any]) -> None:
+def request(query: str, params: "OnlineParams") -> None:
     # Build OpenAlex query using search parameter and paging
     args = {
         "search": query,
@@ -60,7 +149,7 @@ def request(query: str, params: dict[str, t.Any]) -> None:
     params["url"] = f"{search_url}?{urlencode(args)}"
 
 
-def response(resp: SXNG_Response) -> EngineResults:
+def response(resp: "SXNG_Response") -> EngineResults:
     data = resp.json()
     res = EngineResults()
 
@@ -71,12 +160,11 @@ def response(resp: SXNG_Response) -> EngineResults:
         authors = _extract_authors(item)
         journal, publisher, pages, volume, number, published_date = _extract_biblio(item)
         doi = _doi_to_plain(item.get("doi"))
-        tags = _extract_tags(item) or None
+        tags = _extract_tags(item)
         comments = _extract_comments(item)
 
         res.add(
-            res.types.LegacyResult(
+            res.types.Paper(
-                template="paper.html",
                 url=url,
                 title=title,
                 content=content,
@@ -99,7 +187,7 @@ def response(resp: SXNG_Response) -> EngineResults:
     return res
 
 
-def _stringify_pages(biblio: dict[str, t.Any]) -> str | None:
+def _stringify_pages(biblio: dict[str, t.Any]) -> str:
     first_page = biblio.get("first_page")
     last_page = biblio.get("last_page")
     if first_page and last_page:
@@ -108,7 +196,7 @@ def _stringify_pages(biblio: dict[str, t.Any]) -> str | None:
         return str(first_page)
     if last_page:
         return str(last_page)
-    return None
+    return ""
 
 
 def _parse_date(value: str | None) -> datetime | None:
@@ -123,9 +211,9 @@ def _parse_date(value: str | None) -> datetime | None:
     return None
 
 
-def _doi_to_plain(doi_value: str | None) -> str | None:
+def _doi_to_plain(doi_value: str | None) -> str:
     if not doi_value:
-        return None
+        return ""
     # OpenAlex `doi` field is commonly a full URL like https://doi.org/10.1234/abcd
     return doi_value.removeprefix("https://doi.org/")
 
@@ -151,14 +239,17 @@ def _reconstruct_abstract(
     return text if text != "" else None
 
 
-def _extract_links(item: dict[str, t.Any]) -> tuple[str, str | None, str | None]:
+def _extract_links(item: dict[str, t.Any]) -> tuple[str, str, str]:
-    primary_location = item.get("primary_location", {})
+    primary_location: dict[str, str] = item.get("primary_location", {})
-    landing_page_url: str | None = primary_location.get("landing_page_url")
+    open_access: dict[str, str] = item.get("open_access", {})
+
+    landing_page_url: str = primary_location.get("landing_page_url") or ""
     work_url: str = item.get("id", "")
+
     url: str = landing_page_url or work_url
-    open_access = item.get("open_access", {})
+    html_url: str = landing_page_url
-    pdf_url: str | None = primary_location.get("pdf_url") or open_access.get("oa_url")
+    pdf_url: str = primary_location.get("pdf_url") or open_access.get("oa_url") or ""
-    html_url: str | None = landing_page_url
+
     return url, html_url, pdf_url
 
 
@@ -185,20 +276,21 @@ def _extract_tags(item: dict[str, t.Any]) -> list[str]:
 
 def _extract_biblio(
     item: dict[str, t.Any],
-) -> tuple[str | None, str | None, str | None, str | None, str | None, datetime | None]:
+) -> tuple[str, str, str, str, str, datetime | None]:
-    host_venue = item.get("host_venue", {})
+    host_venue: dict[str, str] = item.get("host_venue", {})
-    biblio = item.get("biblio", {})
+    biblio: dict[str, str] = item.get("biblio", {})
-    journal: str | None = host_venue.get("display_name")
+
-    publisher: str | None = host_venue.get("publisher")
+    journal: str = host_venue.get("display_name", "")
-    pages = _stringify_pages(biblio)
+    publisher: str = host_venue.get("publisher", "")
-    volume = biblio.get("volume")
+    pages: str = _stringify_pages(biblio)
-    number = biblio.get("issue")
+    volume = biblio.get("volume", "")
+    number = biblio.get("issue", "")
     published_date = _parse_date(item.get("publication_date"))
     return journal, publisher, pages, volume, number, published_date
 
 
-def _extract_comments(item: dict[str, t.Any]) -> str | None:
+def _extract_comments(item: dict[str, t.Any]) -> str:
     cited_by_count = item.get("cited_by_count")
     if isinstance(cited_by_count, int):
         return f"{cited_by_count} citations"
-    return None
+    return ""

searx/engines/openlibrary.py

@@ -1,71 +1,109 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""Open library (books)
+"""`Open Library`_ is an open, editable library catalog, building towards a web
-"""
+page for every book ever published.
-from urllib.parse import urlencode
-import re
 
+.. _Open Library: https://openlibrary.org
+
+Configuration
+=============
+
+The service sometimes takes a very long time to respond, the ``timeout`` may
+need to be adjusted.
+
+.. code:: yaml
+
+  - name: openlibrary
+    engine: openlibrary
+    shortcut: ol
+    timeout: 10
+
+
+Implementations
+===============
+
+"""
+
+from datetime import datetime
+import typing as t
+
+from urllib.parse import urlencode
 from dateutil import parser
 
+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://openlibrary.org',
+    "website": "https://openlibrary.org",
-    'wikidata_id': 'Q1201876',
+    "wikidata_id": "Q1201876",
-    'require_api_key': False,
+    "require_api_key": False,
-    'use_official_api': False,
+    "use_official_api": False,
-    'official_api_documentation': 'https://openlibrary.org/developers/api',
+    "official_api_documentation": "https://openlibrary.org/developers/api",
 }
 
 paging = True
-categories = []
+categories = ["general", "books"]
 
 base_url = "https://openlibrary.org"
+search_api = "https://openlibrary.org/search.json"
+"""The engine uses the API at the endpoint search.json_.
+
+.. _search.json: https://openlibrary.org/dev/docs/api/search
+"""
 results_per_page = 10
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams") -> None:
     args = {
-        'q': query,
+        "q": query,
-        'page': params['pageno'],
+        "page": params["pageno"],
-        'limit': results_per_page,
+        "limit": results_per_page,
+        "fields": "*",
     }
-    params['url'] = f"{base_url}/search.json?{urlencode(args)}"
+    params["url"] = f"{search_api}?{urlencode(args)}"
-    return params
+    logger.debug("REST API: %s", params["url"])
 
 
-def _parse_date(date):
+def response(resp: "SXNG_Response") -> EngineResults:
-    try:
+    res = EngineResults()
-        return parser.parse(date)
+    json_data = resp.json()
-    except parser.ParserError:
-        return None
 
-
+    for item in json_data.get("docs", []):
-def response(resp):
+        cover = ""
-    results = []
+        if "lending_identifier_s" in item:
-
-    for item in resp.json().get("docs", []):
-        cover = None
-        if 'lending_identifier_s' in item:
             cover = f"https://archive.org/services/img/{item['lending_identifier_s']}"
 
-        published = item.get('publish_date')
+        published = item.get("publish_date")
         if published:
             published_dates = [date for date in map(_parse_date, published) if date]
             if published_dates:
                 published = min(published_dates)
 
         if not published:
-            published = parser.parse(str(item.get('first_published_year')))
+            published = _parse_date(str(item.get("first_publish_year")))
 
-        result = {
+        content = " / ".join(item.get("first_sentence", []))
-            'template': 'paper.html',
+        res.add(
-            'url': f"{base_url}{item['key']}",
+            res.types.Paper(
-            'title': item['title'],
+                url=f"{base_url}/{item['key']}",
-            'content': re.sub(r"\{|\}", "", item['first_sentence'][0]) if item.get('first_sentence') else '',
+                title=item["title"],
-            'isbn': item.get('isbn', [])[:5],
+                content=content,
-            'authors': item.get('author_name', []),
+                isbn=item.get("isbn", [])[:5],
-            'thumbnail': cover,
+                authors=item.get("author_name", []),
-            'publishedDate': published,
+                thumbnail=cover,
-            'tags': item.get('subject', [])[:10] + item.get('place', [])[:10],
+                publishedDate=published,
-        }
+                tags=item.get("subject", [])[:10] + item.get("place", [])[:10],
-        results.append(result)
+            )
+        )
+    return res
 
-    return results
+
+def _parse_date(date: str) -> datetime | None:
+    if not date:
+        return None
+    try:
+        return parser.parse(date)
+    except parser.ParserError:
+        return None

searx/engines/pubmed.py

@@ -1,132 +1,151 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""PubMed (Scholar publications)
+"""PubMed_ comprises more than 39 million citations for biomedical literature
+from MEDLINE, life science journals, and online books. Citations may include
+links to full text content from PubMed Central and publisher web sites.
+
+.. _PubMed: https://pubmed.ncbi.nlm.nih.gov/
+
+Configuration
+=============
+
+.. code:: yaml
+
+   - name: pubmed
+     engine: pubmed
+     shortcut: pub
+
+Implementations
+===============
 
 """
 
+import typing as t
+
 from datetime import datetime
 from urllib.parse import urlencode
 
 from lxml import etree
+
+from searx.result_types import EngineResults
 from searx.network import get
 from searx.utils import (
     eval_xpath_getindex,
     eval_xpath_list,
     extract_text,
+    ElementType,
 )
 
-# about
+if t.TYPE_CHECKING:
+    from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
+
+
 about = {
-    "website": 'https://www.ncbi.nlm.nih.gov/pubmed/',
+    "website": "https://www.ncbi.nlm.nih.gov/pubmed/",
-    "wikidata_id": 'Q1540899',
+    "wikidata_id": "Q1540899",
     "official_api_documentation": {
-        'url': 'https://www.ncbi.nlm.nih.gov/home/develop/api/',
+        "url": "https://www.ncbi.nlm.nih.gov/home/develop/api/",
-        'comment': 'More info on api: https://www.ncbi.nlm.nih.gov/books/NBK25501/',
+        "comment": "More info on api: https://www.ncbi.nlm.nih.gov/books/NBK25501/",
     },
     "use_official_api": True,
     "require_api_key": False,
-    "results": 'XML',
+    "results": "XML",
 }
 
-categories = ['science', 'scientific publications']
+categories = ["science", "scientific publications"]
 
-base_url = (
+eutils_api = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
-    'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi' + '?db=pubmed&{query}&retstart={offset}&retmax={hits}'
-)
 
 # engine dependent config
 number_of_results = 10
-pubmed_url = 'https://www.ncbi.nlm.nih.gov/pubmed/'
+pubmed_url = "https://www.ncbi.nlm.nih.gov/pubmed/"
 
 
-def request(query, params):
+def request(query: str, params: "OnlineParams") -> None:
-    # basic search
-    offset = (params['pageno'] - 1) * number_of_results
 
-    string_args = {
+    args = urlencode(
-        'query': urlencode({'term': query}),
+        {
-        'offset': offset,
+            "db": "pubmed",
-        'hits': number_of_results,
+            "term": query,
-    }
+            "retstart": (params["pageno"] - 1) * number_of_results,
-
+            "hits": number_of_results,
-    params['url'] = base_url.format(**string_args)
-
-    return params
-
-
-def response(resp):  # pylint: disable=too-many-locals
-    results = []
-
-    # First retrieve notice of each result
-    pubmed_retrieve_api_url = (
-        'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?' + 'db=pubmed&retmode=xml&id={pmids_string}'
-    )
-
-    pmids_results = etree.XML(resp.content)
-    pmids = pmids_results.xpath('//eSearchResult/IdList/Id')
-    pmids_string = ''
-
-    for item in pmids:
-        pmids_string += item.text + ','
-
-    retrieve_notice_args = {'pmids_string': pmids_string}
-
-    retrieve_url_encoded = pubmed_retrieve_api_url.format(**retrieve_notice_args)
-
-    search_results_response = get(retrieve_url_encoded).content
-    search_results = etree.XML(search_results_response)
-    for entry in eval_xpath_list(search_results, '//PubmedArticle'):
-        medline = eval_xpath_getindex(entry, './MedlineCitation', 0)
-
-        title = eval_xpath_getindex(medline, './/Article/ArticleTitle', 0).text
-        pmid = eval_xpath_getindex(medline, './/PMID', 0).text
-        url = pubmed_url + pmid
-        content = extract_text(
-            eval_xpath_getindex(medline, './/Abstract/AbstractText//text()', 0, default=None), allow_none=True
-        )
-        doi = extract_text(
-            eval_xpath_getindex(medline, './/ELocationID[@EIdType="doi"]/text()', 0, default=None), allow_none=True
-        )
-        journal = extract_text(
-            eval_xpath_getindex(medline, './Article/Journal/Title/text()', 0, default=None), allow_none=True
-        )
-        issn = extract_text(
-            eval_xpath_getindex(medline, './Article/Journal/ISSN/text()', 0, default=None), allow_none=True
-        )
-        authors = []
-        for author in eval_xpath_list(medline, './Article/AuthorList/Author'):
-            f = eval_xpath_getindex(author, './ForeName', 0, default=None)
-            l = eval_xpath_getindex(author, './LastName', 0, default=None)
-            f = '' if f is None else f.text
-            l = '' if l is None else l.text
-            authors.append((f + ' ' + l).strip())
-
-        res_dict = {
-            'template': 'paper.html',
-            'url': url,
-            'title': title,
-            'content': content or "",
-            'journal': journal,
-            'issn': [issn],
-            'authors': authors,
-            'doi': doi,
         }
+    )
+    esearch_url = f"{eutils_api}/esearch.fcgi?{args}"
+    # DTD: https://eutils.ncbi.nlm.nih.gov/eutils/dtd/20060628/esearch.dtd
+    esearch_resp: "SXNG_Response" = get(esearch_url)
+    pmids_results = etree.XML(esearch_resp.content)
+    pmids: list[str] = [i.text for i in pmids_results.xpath("//eSearchResult/IdList/Id")]
+
+    # send efetch request with the IDs from esearch response
+    args = urlencode(
+        {
+            "db": "pubmed",
+            "retmode": "xml",
+            "id": ",".join(pmids),
+        }
+    )
+    efetch_url = f"{eutils_api}/efetch.fcgi?{args}"
+    params["url"] = efetch_url
+
+
+def response(resp: "SXNG_Response") -> EngineResults:  # pylint: disable=too-many-locals
+
+    # DTD: https://dtd.nlm.nih.gov/ncbi/pubmed/out/pubmed_250101.dtd
+
+    # parse efetch response
+    efetch_xml = etree.XML(resp.content)
+    res = EngineResults()
+
+    def _field_txt(xml: ElementType, xpath_str: str) -> str:
+        elem = eval_xpath_getindex(xml, xpath_str, 0, default="")
+        return extract_text(elem, allow_none=True) or ""
+
+    for pubmed_article in eval_xpath_list(efetch_xml, "//PubmedArticle"):
+
+        medline_citation: ElementType = eval_xpath_getindex(pubmed_article, "./MedlineCitation", 0)
+        pubmed_data: ElementType = eval_xpath_getindex(pubmed_article, "./PubmedData", 0)
+
+        title: str = eval_xpath_getindex(medline_citation, ".//Article/ArticleTitle", 0).text
+        pmid: str = eval_xpath_getindex(medline_citation, ".//PMID", 0).text
+        url: str = pubmed_url + pmid
+        content = _field_txt(medline_citation, ".//Abstract/AbstractText//text()")
+        doi = _field_txt(medline_citation, ".//ELocationID[@EIdType='doi']/text()")
+        journal = _field_txt(medline_citation, "./Article/Journal/Title/text()")
+        issn = _field_txt(medline_citation, "./Article/Journal/ISSN/text()")
+
+        authors: list[str] = []
+
+        for author in eval_xpath_list(medline_citation, "./Article/AuthorList/Author"):
+            f = eval_xpath_getindex(author, "./ForeName", 0, default=None)
+            l = eval_xpath_getindex(author, "./LastName", 0, default=None)
+            author_name = f"{f.text if f is not None else ''} {l.text if l is not None else ''}".strip()
+            if author_name:
+                authors.append(author_name)
 
         accepted_date = eval_xpath_getindex(
-            entry, './PubmedData/History//PubMedPubDate[@PubStatus="accepted"]', 0, default=None
+            pubmed_data, "./History//PubMedPubDate[@PubStatus='accepted']", 0, default=None
         )
+        pub_date = None
         if accepted_date is not None:
-            year = eval_xpath_getindex(accepted_date, './Year', 0)
+            year = eval_xpath_getindex(accepted_date, "./Year", 0)
-            month = eval_xpath_getindex(accepted_date, './Month', 0)
+            month = eval_xpath_getindex(accepted_date, "./Month", 0)
-            day = eval_xpath_getindex(accepted_date, './Day', 0)
+            day = eval_xpath_getindex(accepted_date, "./Day", 0)
             try:
-                publishedDate = datetime.strptime(
+                pub_date = datetime(year=int(year.text), month=int(month.text), day=int(day.text))
-                    year.text + '-' + month.text + '-' + day.text,
+            except ValueError:
-                    '%Y-%m-%d',
+                pass
-                )
-                res_dict['publishedDate'] = publishedDate
-            except Exception as e:  # pylint: disable=broad-exception-caught
-                print(e)
 
-        results.append(res_dict)
+        res.add(
-
+            res.types.Paper(
-    return results
+                url=url,
+                title=title,
+                content=content,
+                journal=journal,
+                issn=[issn],
+                authors=authors,
+                doi=doi,
+                publishedDate=pub_date,
+            )
+        )
+    return res

searx/engines/semantic_scholar.py

@@ -1,125 +1,163 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""Semantic Scholar (Science)"""
+"""`Semantic Scholar`_ provides free, AI-driven search and discovery tools, and
+open resources for the global research community.  `Semantic Scholar`_ index
+over 200 million academic papers sourced from publisher partnerships, data
+providers, and web crawls.
+
+.. _Semantic Scholar: https://www.semanticscholar.org/about
+
+Configuration
+=============
+
+To get in use of this engine add the following entry to your engines list in
+``settings.yml``:
+
+.. code:: yaml
+
+   - name: semantic scholar
+     engine: semantic_scholar
+     shortcut: se
+
+Implementations
+===============
+
+"""
+
+import typing as t
 
-from json import dumps
 from datetime import datetime
 from lxml import html
+from flask_babel import gettext  # pyright: ignore[reportUnknownVariableType]
 
-from flask_babel import gettext
 from searx.network import get
 from searx.utils import eval_xpath_getindex, html_to_text
+from searx.enginelib import EngineCache
+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.semanticscholar.org/',
+    "website": "https://www.semanticscholar.org/",
-    "wikidata_id": 'Q22908627',
+    "wikidata_id": "Q22908627",
-    "official_api_documentation": 'https://api.semanticscholar.org/',
+    "official_api_documentation": "https://api.semanticscholar.org/",
     "use_official_api": True,
     "require_api_key": False,
-    "results": 'JSON',
+    "results": "JSON",
 }
 
-categories = ['science', 'scientific publications']
+categories = ["science", "scientific publications"]
 paging = True
-search_url = 'https://www.semanticscholar.org/api/1/search'
+search_url = "https://www.semanticscholar.org/api/1/search"
-base_url = 'https://www.semanticscholar.org'
+base_url = "https://www.semanticscholar.org"
+
+CACHE: EngineCache
+"""Persistent (SQLite) key/value cache that deletes its values after ``expire``
+seconds."""
 
 
-def _get_ui_version():
+def setup(engine_settings: dict[str, t.Any]) -> bool:
-    resp = get(base_url)
+    global CACHE  # pylint: disable=global-statement
-    if not resp.ok:
+    CACHE = EngineCache(engine_settings["name"])
-        raise RuntimeError("Can't determine Semantic Scholar UI version")
+    return True
-
-    doc = html.fromstring(resp.text)
-    ui_version = eval_xpath_getindex(doc, "//meta[@name='s2-ui-version']/@content", 0)
-    if not ui_version:
-        raise RuntimeError("Can't determine Semantic Scholar UI version")
-
-    return ui_version
 
 
-def request(query, params):
+def get_ui_version() -> str:
-    params['url'] = search_url
+    ret_val: str = CACHE.get("X-S2-UI-Version")
-    params['method'] = 'POST'
+    if not ret_val:
-    params['headers'].update(
+        resp = get(base_url)
+        if not resp.ok:
+            raise RuntimeError("Can't determine Semantic Scholar UI version")
+
+        doc = html.fromstring(resp.text)
+        ret_val = eval_xpath_getindex(doc, "//meta[@name='s2-ui-version']/@content", 0)
+        if not ret_val:
+            raise RuntimeError("Can't determine Semantic Scholar UI version")
+        # hold the cached value for 5min
+        CACHE.set("X-S2-UI-Version", value=ret_val, expire=300)
+        logger.debug("X-S2-UI-Version: %s", ret_val)
+    return ret_val
+
+
+def request(query: str, params: "OnlineParams") -> None:
+    params["url"] = search_url
+    params["method"] = "POST"
+    params["headers"].update(
         {
-            'Content-Type': 'application/json',
+            "Content-Type": "application/json",
-            'X-S2-UI-Version': _get_ui_version(),
+            "X-S2-UI-Version": get_ui_version(),
-            'X-S2-Client': "webapp-browser",
+            "X-S2-Client": "webapp-browser",
         }
     )
-    params['data'] = dumps(
+    params["json"] = {
-        {
+        "queryString": query,
-            "queryString": query,
+        "page": params["pageno"],
-            "page": params['pageno'],
+        "pageSize": 10,
-            "pageSize": 10,
+        "sort": "relevance",
-            "sort": "relevance",
+        "getQuerySuggestions": False,
-            "getQuerySuggestions": False,
+        "authors": [],
-            "authors": [],
+        "coAuthors": [],
-            "coAuthors": [],
+        "venues": [],
-            "venues": [],
+        "performTitleMatch": True,
-            "performTitleMatch": True,
+    }
-        }
-    )
-    return params
 
 
-def response(resp):
+def response(resp: "SXNG_Response") -> EngineResults:
-    res = resp.json()
+    res = EngineResults()
+    json_data = resp.json()
 
-    results = []
+    for result in json_data["results"]:
-    for result in res['results']:
+        url: str = result.get("primaryPaperLink", {}).get("url")
-        url = result.get('primaryPaperLink', {}).get('url')
+        if not url and result.get("links"):
-        if not url and result.get('links'):
+            url = result.get("links")[0]
-            url = result.get('links')[0]
         if not url:
-            alternatePaperLinks = result.get('alternatePaperLinks')
+            alternatePaperLinks = result.get("alternatePaperLinks")
             if alternatePaperLinks:
-                url = alternatePaperLinks[0].get('url')
+                url = alternatePaperLinks[0].get("url")
         if not url:
-            url = base_url + '/paper/%s' % result['id']
+            url = base_url + "/paper/%s" % result["id"]
 
-        # publishedDate
+        publishedDate: datetime | None
-        if 'pubDate' in result:
+        if "pubDate" in result:
-            publishedDate = datetime.strptime(result['pubDate'], "%Y-%m-%d")
+            publishedDate = datetime.strptime(result["pubDate"], "%Y-%m-%d")
         else:
             publishedDate = None
 
         # authors
-        authors = [author[0]['name'] for author in result.get('authors', [])]
+        authors: list[str] = [author[0]["name"] for author in result.get("authors", [])]
 
         # pick for the first alternate link, but not from the crawler
-        pdf_url = None
+        pdf_url: str = ""
-        for doc in result.get('alternatePaperLinks', []):
+        for doc in result.get("alternatePaperLinks", []):
-            if doc['linkType'] not in ('crawler', 'doi'):
+            if doc["linkType"] not in ("crawler", "doi"):
-                pdf_url = doc['url']
+                pdf_url = doc["url"]
                 break
 
         # comments
-        comments = None
+        comments: str = ""
-        if 'citationStats' in result:
+        if "citationStats" in result:
             comments = gettext(
-                '{numCitations} citations from the year {firstCitationVelocityYear} to {lastCitationVelocityYear}'
+                "{numCitations} citations from the year {firstCitationVelocityYear} to {lastCitationVelocityYear}"
             ).format(
-                numCitations=result['citationStats']['numCitations'],
+                numCitations=result["citationStats"]["numCitations"],
-                firstCitationVelocityYear=result['citationStats']['firstCitationVelocityYear'],
+                firstCitationVelocityYear=result["citationStats"]["firstCitationVelocityYear"],
-                lastCitationVelocityYear=result['citationStats']['lastCitationVelocityYear'],
+                lastCitationVelocityYear=result["citationStats"]["lastCitationVelocityYear"],
             )
 
-        results.append(
+        res.add(
-            {
+            res.types.Paper(
-                'template': 'paper.html',
+                title=result["title"]["text"],
-                'url': url,
+                url=url,
-                'title': result['title']['text'],
+                content=html_to_text(result["paperAbstract"]["text"]),
-                'content': html_to_text(result['paperAbstract']['text']),
+                journal=result.get("venue", {}).get("text") or result.get("journal", {}).get("name"),
-                'journal': result.get('venue', {}).get('text') or result.get('journal', {}).get('name'),
+                doi=result.get("doiInfo", {}).get("doi"),
-                'doi': result.get('doiInfo', {}).get('doi'),
+                tags=result.get("fieldsOfStudy"),
-                'tags': result.get('fieldsOfStudy'),
+                authors=authors,
-                'authors': authors,
+                pdf_url=pdf_url,
-                'pdf_url': pdf_url,
+                publishedDate=publishedDate,
-                'publishedDate': publishedDate,
+                comments=comments,
-                'comments': comments,
+            )
-            }
         )
 
-    return results
+    return res

searx/engines/springer.py

@@ -1,71 +1,175 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
-"""Springer Nature (science)
+"""`Springer Nature`_ is a global publisher dedicated to providing service to
+research community with official Springer-API_ (API-Playground_).
+
+.. note::
+
+   The Springer engine requires an API key, which can be obtained via the
+   `Springer subscription`_.
+
+Since the search term is passed 1:1 to the API, SearXNG users can use the
+`Supported Query Parameters`_.
+
+- ``!springer (doi:10.1007/s10948-025-07019-1 OR doi:10.1007/s10948-025-07035-1)``
+- ``!springer keyword:ybco``
+
+However, please note that the available options depend on the subscription type.
+
+For example, the ``year:`` filter requires a *Premium Plan* subscription.
+
+- ``!springer keyword:ybco year:2024``
+
+The engine uses the REST Meta-API_ `v2` endpoint, but there is also a `Python
+API Wrapper`_.
+
+.. _Python API Wrapper: https://pypi.org/project/springernature-api-client/
+.. _Springer Nature: https://www.springernature.com/
+.. _Springer subscription:  https://dev.springernature.com/subscription/
+.. _Springer-API: https://dev.springernature.com/docs/introduction/
+.. _API-Playground: https://dev.springernature.com/docs/live-documentation/
+.. _Meta-API: https://dev.springernature.com/docs/api-endpoints/meta-api/
+.. _Supported Query Parameters: https://dev.springernature.com/docs/supported-query-params/
+
+
+Configuration
+=============
+
+The engine has the following additional settings:
+
+- :py:obj:`api_key`
+
+.. code:: yaml
+
+  - name: springer nature
+    api_key: "..."
+    inactive: false
+
+
+Implementations
+===============
 
 """
 
+import typing as t
+
 from datetime import datetime
-from json import loads
 from urllib.parse import urlencode
 
-from searx.exceptions import SearxEngineAPIException
+from searx.network import raise_for_httperror
+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.springernature.com/',
+    "website": "https://www.springernature.com/",
-    "wikidata_id": 'Q21096327',
+    "wikidata_id": "Q21096327",
-    "official_api_documentation": 'https://dev.springernature.com/',
+    "official_api_documentation": "https://dev.springernature.com/docs/live-documentation/",
     "use_official_api": True,
     "require_api_key": True,
-    "results": 'JSON',
+    "results": "JSON",
 }
 
-categories = ['science', 'scientific publications']
+categories = ["science", "scientific publications"]
+
 paging = True
 nb_per_page = 10
-api_key = 'unset'
+"""Number of results to return in the request, see `Pagination and Limits`_ for
+more details.
 
-base_url = 'https://api.springernature.com/metadata/json?'
+.. _Pagination and Limits:
+    https://dev.springernature.com/docs/advanced-querying/pagination-limits/
+"""
+
+api_key = ""
+"""Key used for the Meta-API_.  Get your API key from: `Springer subscription`_"""
+
+base_url = "https://api.springernature.com/meta/v2/json"
+"""An enhanced endpoint with additional metadata fields and optimized queries
+for more efficient and comprehensive retrieval (Meta-API_ `v2`).
+"""
 
 
-def request(query, params):
+def setup(engine_settings: dict[str, t.Any]) -> bool:
-    if api_key == 'unset':
+    """Initialization of the Springer engine, checks whether the
-        raise SearxEngineAPIException('missing Springer-Nature API key')
+    :py:obj:`api_key` is set, otherwise the engine is inactive.
-    args = urlencode({'q': query, 's': nb_per_page * (params['pageno'] - 1), 'p': nb_per_page, 'api_key': api_key})
+    """
-    params['url'] = base_url + args
+    key: str = engine_settings.get("api_key", "")
-    logger.debug("query_url --> %s", params['url'])
+    try:
-    return params
+        # Springer's API key is a hex value
+        int(key, 16)
+        return True
+    except ValueError:
+        logger.error("Springer's API key is not set or invalid.")
+        return False
 
 
-def response(resp):
+def request(query: str, params: "OnlineParams") -> None:
-    results = []
+    args = {
-    json_data = loads(resp.text)
+        "api_key": api_key,
+        "q": query,
+        "s": nb_per_page * (params["pageno"] - 1),
+        "p": nb_per_page,
+    }
+    params["url"] = f"{base_url}?{urlencode(args)}"
+    # For example, the ``year:`` filter requires a *Premium Plan* subscription.
+    params["raise_for_httperror"] = False
 
-    for record in json_data['records']:
+
-        published = datetime.strptime(record['publicationDate'], '%Y-%m-%d')
+def response(resp: "SXNG_Response") -> EngineResults:
-        authors = [" ".join(author['creator'].split(', ')[::-1]) for author in record['creators']]
+
-        tags = record.get('genre')
+    res = EngineResults()
-        if isinstance(tags, str):
+    json_data = resp.json()
-            tags = [tags]
+
-        results.append(
+    if (
-            {
+        resp.status_code == 403
-                'template': 'paper.html',
+        and json_data["status"].lower() == "fail"
-                'url': record['url'][0]['value'].replace('http://', 'https://', 1),
+        and "premium feature" in json_data["message"].lower()
-                'title': record['title'],
+    ):
-                'content': record['abstract'],
+        return res
-                'comments': record['publicationName'],
+    raise_for_httperror(resp)
-                'tags': tags,
+
-                'publishedDate': published,
+    def field(k: str) -> str:
-                'type': record.get('contentType'),
+        return str(record.get(k, ""))
-                'authors': authors,
+
-                # 'editor': '',
+    for record in json_data["records"]:
-                'publisher': record.get('publisher'),
+        published = datetime.strptime(record["publicationDate"], "%Y-%m-%d")
-                'journal': record.get('publicationName'),
+        authors: list[str] = [" ".join(author["creator"].split(", ")[::-1]) for author in record["creators"]]
-                'volume': record.get('volume') or None,
+
-                'pages': '-'.join([x for x in [record.get('startingPage'), record.get('endingPage')] if x]),
+        pdf_url = ""
-                'number': record.get('number') or None,
+        html_url = ""
-                'doi': record.get('doi'),
+        url_list: list[dict[str, str]] = record["url"]
-                'issn': [x for x in [record.get('issn')] if x],
+
-                'isbn': [x for x in [record.get('isbn')] if x],
+        for item in url_list:
-                # 'pdf_url' : ''
+            if item["platform"] != "web":
-            }
+                continue
+            val = item["value"].replace("http://", "https://", 1)
+            if item["format"] == "html":
+                html_url = val
+            elif item["format"] == "pdf":
+                pdf_url = val
+
+        paper = res.types.Paper(
+            url=html_url,
+            # html_url=html_url,
+            pdf_url=pdf_url,
+            title=field("title"),
+            content=field("abstract"),
+            comments=field("publicationName"),
+            tags=record.get("keyword", []),
+            publishedDate=published,
+            type=field("contentType"),
+            authors=authors,
+            publisher=field("publisher"),
+            journal=field("publicationName"),
+            volume=field("volume"),
+            pages="-".join([x for x in [field("startingPage"), field("endingPage")] if x]),
+            number=field("number"),
+            doi=field("doi"),
+            issn=[x for x in [field("issn")] if x],
+            isbn=[x for x in [field("isbn")] if x],
         )
-    return results
+        res.add(paper)
+
+    return res

searx/engines/zlibrary.py

@@ -39,15 +39,16 @@ from urllib.parse import quote
 from lxml import html
 from flask_babel import gettext  # pyright: ignore[reportUnknownVariableType]
 
-from searx.utils import extract_text, eval_xpath, eval_xpath_list
+from searx.utils import extract_text, eval_xpath, eval_xpath_list, ElementType
 from searx.enginelib.traits import EngineTraits
 from searx.data import ENGINE_TRAITS
 from searx.exceptions import SearxException
+from searx.result_types import EngineResults
 
 if t.TYPE_CHECKING:
     from searx.extended_types import SXNG_Response
+    from searx.search.processors import OnlineParams
 
-# about
 about: dict[str, t.Any] = {
     "website": "https://zlibrary-global.se",
     "wikidata_id": "Q104863992",
@@ -57,7 +58,7 @@ about: dict[str, t.Any] = {
     "results": "HTML",
 }
 
-categories: list[str] = ["files"]
+categories: list[str] = ["files", "books"]
 paging: bool = True
 base_url: str = "https://zlibrary-global.se"
 
@@ -74,8 +75,12 @@ zlib_ext: str = ""
 ``PDF`` and ``EPUB``.
 """
 
+i18n_language = gettext("Language")
+i18n_book_rating = gettext("Book rating")
+i18n_file_quality = gettext("File quality")
 
-def init(engine_settings: dict[str, t.Any] | None = None) -> None:  # pylint: disable=unused-argument
+
+def setup(engine_settings: dict[str, t.Any]) -> bool:  # pylint: disable=unused-argument
     """Check of engine's settings."""
     traits: EngineTraits = EngineTraits(**ENGINE_TRAITS["z-library"])
 
@@ -85,10 +90,11 @@ def init(engine_settings: dict[str, t.Any] | None = None) -> None:  # pylint: di
         raise ValueError(f"invalid setting year_from: {zlib_year_from}")
     if zlib_year_to and zlib_year_to not in traits.custom["year_to"]:
         raise ValueError(f"invalid setting year_to: {zlib_year_to}")
+    return True
 
 
-def request(query: str, params: dict[str, t.Any]) -> dict[str, t.Any]:
+def request(query: str, params: "OnlineParams") -> None:
-    lang: str = traits.get_language(params["language"], traits.all_locale)  # type: ignore
+    lang: str | None = traits.get_language(params["searxng_locale"], traits.all_locale)
     search_url: str = (
         base_url
         + "/s/{search_query}/?page={pageno}"
@@ -106,41 +112,35 @@ def request(query: str, params: dict[str, t.Any]) -> dict[str, t.Any]:
         zlib_ext=zlib_ext,
     )
     params["verify"] = False
-    return params
 
 
-def domain_is_seized(dom):
+def response(resp: "SXNG_Response") -> EngineResults:
-    return bool(dom.xpath('//title') and "seized" in dom.xpath('//title')[0].text.lower())
+    res = EngineResults()
-
-
-def response(resp: "SXNG_Response") -> list[dict[str, t.Any]]:
-    results: list[dict[str, t.Any]] = []
     dom = html.fromstring(resp.text)
 
     if domain_is_seized(dom):
         raise SearxException(f"zlibrary domain is seized: {base_url}")
 
     for item in dom.xpath('//div[@id="searchResultBox"]//div[contains(@class, "resItemBox")]'):
-        results.append(_parse_result(item))
+        kwargs = _parse_result(item)
+        res.add(res.types.Paper(**kwargs))
 
-    return results
+    return res
 
 
-def _text(item, selector: str) -> str | None:
+def domain_is_seized(dom: ElementType):
+    return bool(dom.xpath('//title') and "seized" in dom.xpath('//title')[0].text.lower())
+
+
+def _text(item: ElementType, selector: str) -> str | None:
     return extract_text(eval_xpath(item, selector))
 
 
-i18n_language = gettext("Language")
+def _parse_result(item: ElementType) -> dict[str, t.Any]:
-i18n_book_rating = gettext("Book rating")
-i18n_file_quality = gettext("File quality")
-
-
-def _parse_result(item) -> dict[str, t.Any]:
 
     author_elements = eval_xpath_list(item, './/div[@class="authors"]//a[@itemprop="author"]')
 
     result = {
-        "template": "paper.html",
         "url": base_url + item.xpath('(.//a[starts-with(@href, "/book/")])[1]/@href')[0],
         "title": _text(item, './/*[@itemprop="name"]'),
         "authors": [extract_text(author) for author in author_elements],
@@ -148,15 +148,15 @@ def _parse_result(item) -> dict[str, t.Any]:
         "type": _text(item, './/div[contains(@class, "property__file")]//div[contains(@class, "property_value")]'),
     }
 
-    thumbnail: str = _text(item, './/img[contains(@class, "cover")]/@data-src')
+    thumbnail = _text(item, './/img[contains(@class, "cover")]/@data-src')
-    if not thumbnail.startswith('/'):
+    if thumbnail and not thumbnail.startswith('/'):
         result["thumbnail"] = thumbnail
 
     year = _text(item, './/div[contains(@class, "property_year")]//div[contains(@class, "property_value")]')
     if year:
         result["publishedDate"] = datetime.strptime(year, '%Y')
 
-    content = []
+    content: list[str] = []
     language = _text(item, './/div[contains(@class, "property_language")]//div[contains(@class, "property_value")]')
     if language:
         content.append(f"{i18n_language}: {language.capitalize()}")
@@ -173,9 +173,10 @@ def _parse_result(item) -> dict[str, t.Any]:
 
 def fetch_traits(engine_traits: EngineTraits) -> None:
     """Fetch languages and other search arguments from zlibrary's search form."""
-    # pylint: disable=import-outside-toplevel, too-many-branches
+    # pylint: disable=import-outside-toplevel, too-many-branches, too-many-statements
 
     import babel
+    import babel.core
     import httpx
 
     from searx.network import get  # see https://github.com/searxng/searxng/issues/762
@@ -197,7 +198,7 @@ def fetch_traits(engine_traits: EngineTraits) -> None:
 
     if not resp.ok:
         raise RuntimeError("Response from zlibrary's search page is not OK.")
-    dom = html.fromstring(resp.text)  # type: ignore
+    dom = html.fromstring(resp.text)
 
     if domain_is_seized(dom):
         print(f"ERROR: zlibrary domain is seized: {base_url}")
@@ -206,25 +207,30 @@ def fetch_traits(engine_traits: EngineTraits) -> None:
 
     engine_traits.all_locale = ""
     engine_traits.custom["ext"] = []
-    engine_traits.custom["year_from"] = []
-    engine_traits.custom["year_to"] = []
 
+    l: list[str]
+    # years_from
+    l = []
     for year in eval_xpath_list(dom, "//div[@id='advSearch-noJS']//select[@id='sf_yearFrom']/option"):
-        engine_traits.custom["year_from"].append(year.get("value"))
+        l.append(year.get("value") or "")
+    engine_traits.custom["year_from"] = l
 
+    # years_to
+    l = []
     for year in eval_xpath_list(dom, "//div[@id='advSearch-noJS']//select[@id='sf_yearTo']/option"):
-        engine_traits.custom["year_to"].append(year.get("value"))
+        l.append(year.get("value") or "")
+    engine_traits.custom["year_to"] = l
 
+    # ext (file extensions)
+    l = []
     for ext in eval_xpath_list(dom, "//div[@id='advSearch-noJS']//select[@id='sf_extensions']/option"):
-        value: str | None = ext.get("value")
+        l.append(ext.get("value") or "")
-        if value is None:
+    engine_traits.custom["ext"] = l
-            value = ""
-        engine_traits.custom["ext"].append(value)
 
     # Handle languages
     # Z-library uses English names for languages, so we need to map them to their respective locales
     language_name_locale_map: dict[str, babel.Locale] = {}
-    for locale in babel.core.localedata.locale_identifiers():  # type: ignore
+    for locale in babel.core.localedata.locale_identifiers():
         # Create a Locale object for the current locale
         loc = babel.Locale.parse(locale)
         if loc.english_name is None:

searx/network/client.py

@@ -13,13 +13,9 @@ import threading
 import httpx
 from httpx_socks import AsyncProxyTransport
 from python_socks import parse_proxy_url, ProxyConnectionError, ProxyTimeoutError, ProxyError
-import uvloop
 
 from searx import logger
 
-
-uvloop.install()
-
 CertTypes = str | tuple[str, str] | tuple[str, str, str]
 SslContextKeyType = tuple[str | None, CertTypes | None, bool, bool]
 

searx/network/network.py

@@ -280,9 +280,9 @@ class Network:
             client.cookies = httpx.Cookies(cookies)
             try:
                 if stream:
-                    response = client.stream(method, url, **kwargs)
+                    return client.stream(method, url, **kwargs)
-                else:
+
-                    response = await client.request(method, url, **kwargs)
+                response = await client.request(method, url, **kwargs)
                 if self.is_valid_response(response) or retries <= 0:
                     return self.patch_response(response, do_raise_for_httperror)
             except httpx.RemoteProtocolError as e:

searx/result_types/__init__.py

@@ -22,6 +22,7 @@ __all__ = [
     "Translations",
     "WeatherAnswer",
     "Code",
+    "Paper",
 ]
 
 import typing as t
@@ -31,6 +32,7 @@ from ._base import Result, MainResult, LegacyResult
 from .answer import AnswerSet, Answer, Translations, WeatherAnswer
 from .keyvalue import KeyValue
 from .code import Code
+from .paper import Paper
 
 
 class ResultList(list[Result | LegacyResult], abc.ABC):
@@ -44,6 +46,7 @@ class ResultList(list[Result | LegacyResult], abc.ABC):
         Answer = Answer
         KeyValue = KeyValue
         Code = Code
+        Paper = Paper
         MainResult = MainResult
         Result = Result
         Translations = Translations

searx/result_types/_base.py

@@ -362,7 +362,11 @@ class MainResult(Result):  # pylint: disable=missing-class-docstring
     """The date on which the object was published."""
 
     pubdate: str = ""
-    """String representation of :py:obj:`MainResult.publishedDate`"""
+    """String representation of :py:obj:`MainResult.publishedDate`
+
+    Deprecated: it is still partially used in the templates, but will one day be
+    completely eliminated.
+    """
 
     length: time.struct_time | None = None
     """Playing duration in seconds."""

searx/result_types/paper.py

@@ -0,0 +1,96 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Typification of the *paper* results.
+
+.. _BibTeX field types: https://en.wikipedia.org/wiki/BibTeX#Field_types
+.. _BibTeX format: https://www.bibtex.com/g/bibtex-format/
+
+Results of this type are rendered in the :origin:`paper.html
+<searx/templates/simple/result_templates/paper.html>` template.
+
+Related topics:
+
+- `BibTeX field types`_
+- `BibTeX format`_
+
+----
+
+.. autoclass:: Paper
+   :members:
+   :show-inheritance:
+
+"""
+# pylint: disable=too-few-public-methods, disable=invalid-name
+
+from __future__ import annotations
+
+__all__ = ["Paper"]
+
+import typing as t
+
+from searx.weather import DateTime
+from ._base import MainResult
+
+
+@t.final
+class Paper(MainResult, kw_only=True):
+    """Result type suitable for displaying scientific papers and other
+    documents."""
+
+    template: str = "paper.html"
+
+    date_of_publication: DateTime | None = None
+    """Date the document was published."""
+
+    content: str = ""
+    """An abstract or excerpt from the document."""
+
+    comments: str = ""
+    """Free text display in italic below the content."""
+
+    tags: list[str] = []
+    """Free tag list."""
+
+    type: str = ""
+    """Short description of medium type, e.g. *book*, *pdf* or *html* ..."""
+
+    authors: list[str] | set[str] = []
+    """List of authors of the work (authors with a "s" suffix, the "author" is
+    in the :py:obj:`MainResult.author`)."""
+
+    editor: str = ""
+    """Editor of the book/paper."""
+
+    publisher: str = ""
+    """Name of the publisher."""
+
+    journal: str = ""
+    """Name of the journal or magazine the article was published in."""
+
+    volume: str | int = ""
+    """Volume number."""
+
+    pages: str = ""
+    """Page range where the article is."""
+
+    number: str = ""
+    """Number of the report or the issue number for a journal article."""
+
+    doi: str = ""
+    """DOI number (like ``10.1038/d41586-018-07848-2``)."""
+
+    issn: list[str] = []
+    """List of ISSN numbers like ``1476-4687``"""
+
+    isbn: list[str] = []
+    """List of ISBN numbers like ``9780201896831``"""
+
+    pdf_url: str = ""
+    """URL to the full article, the PDF version"""
+
+    html_url: str = ""
+    """URL to full article, HTML version"""
+
+    def __post_init__(self):
+        super().__post_init__()
+        if self.date_of_publication is None and self.publishedDate is not None:
+            self.date_of_publication = DateTime(self.publishedDate)

searx/settings.yml

@@ -407,13 +407,12 @@ engines:
       require_api_key: false
       results: JSON
 
-  # - name: astrophysics data system
+  - name: astrophysics data system
-  #   engine: astrophysics_data_system
+    engine: astrophysics_data_system
-  #   sort: asc
+    shortcut: ads
-  #   weight: 5
+    # read https://docs.searxng.org/dev/engines/online/astrophysics_data_system.html
-  #   categories: [science]
+    api_key: ""
-  #   api_key: your-new-key
+    inactive: true
-  #   shortcut: ads
 
   - name: alpine linux packages
     engine: alpinelinux
@@ -424,6 +423,7 @@ engines:
     engine: annas_archive
     disabled: true
     shortcut: aa
+    timeout: 5
 
   - name: ansa
     engine: ansa
@@ -490,7 +490,6 @@ engines:
   - name: arxiv
     engine: arxiv
     shortcut: arx
-    timeout: 4.0
 
   - name: ask
     engine: ask
@@ -659,12 +658,12 @@ engines:
     timeout: 30
     disabled: true
 
-  # - name: core.ac.uk
+  - name: core.ac.uk
-  #   engine: core
+    engine: core
-  #   categories: science
+    shortcut: cor
-  #   shortcut: cor
+    # read https://docs.searxng.org/dev/engines/online/core.html
-  #   # get your API key from: https://core.ac.uk/api-keys/register/
+    api_key: ""
-  #   api_key: 'unset'
+    inactive: true
 
   - name: cppreference
     engine: cppreference
@@ -1254,9 +1253,10 @@ engines:
   - name: z-library
     engine: zlibrary
     shortcut: zlib
-    categories: files
     timeout: 7.0
     disabled: true
+    # https://github.com/searxng/searxng/issues/3610
+    inactive: true
 
   - name: library of congress
     engine: loc
@@ -1517,7 +1517,7 @@ engines:
   - name: openlibrary
     engine: openlibrary
     shortcut: ol
-    timeout: 5
+    timeout: 10
     disabled: true
 
   - name: openmeteo
@@ -1735,7 +1735,6 @@ engines:
   - name: pubmed
     engine: pubmed
     shortcut: pub
-    timeout: 3.0
 
   - name: pypi
     shortcut: pypi
@@ -1965,7 +1964,6 @@ engines:
 
   - name: semantic scholar
     engine: semantic_scholar
-    disabled: true
     shortcut: se
 
   # Spotify needs API credentials
@@ -1986,13 +1984,13 @@ engines:
   #   query_fields: '' # query fields
   #   enable_http: true
 
-  # - name: springer nature
+  - name: springer nature
-  #   engine: springer
+    engine: springer
-  #   # get your API key from: https://dev.springernature.com/signup
+    shortcut: springer
-  #   # working API key, for test & debug: "a69685087d07eca9f13db62f65b8f601"
+    timeout: 5
-  #   api_key: 'unset'
+    # read https://docs.searxng.org/dev/engines/online/springer.html
-  #   shortcut: springer
+    api_key: ""
-  #   timeout: 15.0
+    inactive: true
 
   - name: startpage
     engine: startpage

searx/templates/simple/result_templates/paper.html

@@ -1,34 +1,92 @@
 {% from 'simple/macros.html' import result_header, result_sub_header, result_sub_footer, result_footer, result_link with context %}
 
-{{ result_header(result, favicons, image_proxify) -}}
+{{ result_header(result, favicons, image_proxify) }}
+
 <div class="attributes">
-  {%- if result.publishedDate %}<div class="result_publishedDate"><span>{{ _("Published date") }}:</span><span><time class="published_date" datetime="{{ result.pubdate }}" >{{ result.publishedDate }}</time></span></div>{% endif -%}
+  {%- if result.date_of_publication %}
-  {%- if result.authors %}<div class="result_authors"><span>{{ _("Author") }}:</span><span>{{ result.authors | join(", ") }}</span></div>{% endif -%}
+    <div>
+      <span>{{ _("Published date") }}:</span>
+      <span>{{ result.date_of_publication.l10n_date("long", "UI") }}</span>
+    </div>
+  {% endif -%}
+  {%- if result.authors %}
+    <div>
+      <span>{{ _("Author") }}:</span>
+      <span>{{ result.authors | join(", ") }}</span>
+    </div>
+  {% endif -%}
   {%- if result.journal -%}
-    <div class="result_journal">
+    <div>
-      <span>{{- _("Journal") }}:</span><span>{{ result.journal -}}
+      <span>{{- _("Journal") }}:</span>
-      {%- if result.volume -%}
+      <span>{{ result.journal -}}
-        &nbsp;{{- result.volume -}}
+        {%- if result.volume -%}
-        {%- if result.number -%}
+          &nbsp;{{- result.volume -}}
-          .{{- result.number -}}
+          {%- if result.number -%}.{{- result.number -}}{%- endif -%}
         {%- endif -%}
-      {%- endif -%}
+        {%- if result.pages -%}&nbsp;{{- result.pages -}}{%- endif -%}
-      {%- if result.pages -%}
-        &nbsp;{{- result.pages -}}
-      {%- endif -%}
       </span>
     </div>
   {%- endif %}
-  {%- if result.editor %}<div class="result_editor"><span>{{ _("Editor") }}:</span><span>{{ result.editor }}</span></div>{% endif -%}
+  {%- if result.editor %}
-  {%- if result.publisher %}<div class="result_publisher"><span>{{ _("Publisher") }}:</span><span>{{ result.publisher }}</span></div>{% endif -%}
+    <div>
-  {%- if result.type %}<div class="result_type"><span>{{ _("Type") }}:</span><span>{{ result.type }}</span></div>{% endif -%}
+      <span>{{ _("Editor") }}:</span>
-  {%- if result.tags %}<div class="result_tags"><span>{{ _("Tags") }}:</span><span>{{ result.tags | join(", ")}}</span></div>{%- endif -%}
+      <span>{{ result.editor }}</span>
-  {%- if result.doi %}<div class="result_doi"><span>{{ _("DOI") }}:</span><span>{{ result_link(doi_resolver + result.doi, result.doi) }}</span></div>{% endif -%}
+    </div>
-  {%- if result.issn %}<div class="result_issn"><span>{{ _("ISSN") }}:</span><span>{{ result.issn | join(", ") }}</span></div>{% endif -%}
+  {% endif -%}
-  {%- if result.isbn %}<div class="result_isbn"><span>{{ _("ISBN") }}:</span><span>{{ result.isbn | join(", ") }}</span></div>{% endif -%}
+  {%- if result.publisher %}
+    <div>
+      <span>{{ _("Publisher") }}:</span>
+      <span>{{ result.publisher }}</span>
+    </div>
+  {% endif -%}
+  {%- if result.type %}
+    <div>
+      <span>{{ _("Type") }}:</span>
+      <span>{{ result.type }}</span>
+    </div>
+  {% endif -%}
+  {%- if result.tags %}
+    <div>
+      <span>{{ _("Tags") }}:</span>
+      <span>{{ result.tags | join(", ")}}</span>
+    </div>
+  {%- endif -%}
+  {%- if result.doi %}
+    <div>
+      <span>{{ _("DOI") }}:</span>
+      <span>{{ result_link(doi_resolver + result.doi, result.doi) }}</span>
+    </div>
+  {% endif -%}
+  {%- if result.issn %}
+    <div>
+      <span>{{ _("ISSN") }}:</span>
+      <span>{{ result.issn | join(", ") }}</span>
+    </div>
+  {% endif -%}
+  {%- if result.isbn %}
+    <div class="result_isbn">
+      <span>{{ _("ISBN") }}:</span>
+      <span>{{ result.isbn | join(", ") }}</span>
+    </div>
+  {% endif -%}
+  {%- if result.views %}
+    <div>
+      <span>{{ _('Views') }}:</span>
+      <span>{{ result.views }}</span>
+    </div>
+  {% endif -%}
 </div>
-{%- if result.content -%}<p class="content">{{- result.content | safe -}}</p>{%- endif -%}
+{%- if result.content -%}
-{%- if result.comments -%}<p class="comments">{{- result.comments -}}</p>{%- endif -%}
+  <p class="content">{{- result.content | safe -}}</p>
+{%- endif -%}
+{%- if result.comments -%}
+  <p class="comments">{{- result.comments -}}</p>
+{%- endif -%}
+
+{%- if result.metadata %}
+  <div class="highlight">{{ result.metadata|safe }}</div>
+{% endif -%}
+
 <p class="altlink">
   {%- if result.pdf_url -%}{{ result_link(result.pdf_url, _('PDF')) }}{%- endif -%}
   {%- if result.html_url -%}{{ result_link(result.html_url, _('HTML')) }}{%- endif -%}

searx/translations/fi/LC_MESSAGES/messages.po

@@ -23,8 +23,8 @@ msgstr ""
 "Project-Id-Version: searx\n"
 "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
 "POT-Creation-Date: 2025-09-01 12:54+0000\n"
-"PO-Revision-Date: 2025-09-02 04:50+0000\n"
+"PO-Revision-Date: 2025-09-14 00:25+0000\n"
-"Last-Translator: return42 <return42@noreply.codeberg.org>\n"
+"Last-Translator: artnay <artnay@noreply.codeberg.org>\n"
 "Language-Team: Finnish <https://translate.codeberg.org/projects/searxng/"
 "searxng/fi/>\n"
 "Language: fi\n"
@@ -32,7 +32,7 @@ msgstr ""
 "Content-Type: text/plain; charset=utf-8\n"
 "Content-Transfer-Encoding: 8bit\n"
 "Plural-Forms: nplurals=2; plural=n != 1;\n"
-"X-Generator: Weblate 5.12.2\n"
+"X-Generator: Weblate 5.13.2\n"
 "Generated-By: Babel 2.17.0\n"
 
 #. CONSTANT_NAMES['NO_SUBGROUPING']
@@ -153,7 +153,7 @@ msgstr "web"
 #. CATEGORY_GROUPS['SCIENTIFIC PUBLICATIONS']
 #: searx/searxng.msg
 msgid "scientific publications"
-msgstr "Tieteelliset Julkaisut"
+msgstr "tieteelliset julkaisut"
 
 #. STYLE_NAMES['AUTO']
 #: searx/searxng.msg
@@ -223,12 +223,12 @@ msgstr "Kosteus"
 #. WEATHER_TERMS['MAX TEMP.']
 #: searx/searxng.msg
 msgid "Max temp."
-msgstr "Maksimi lämpötila."
+msgstr "Suurin lämpötila."
 
 #. WEATHER_TERMS['MIN TEMP.']
 #: searx/searxng.msg
 msgid "Min temp."
-msgstr "Minimi lämpötila."
+msgstr "Pienin lämpötila."
 
 #. WEATHER_TERMS['MORNING']
 #: searx/searxng.msg
@@ -268,7 +268,7 @@ msgstr "Lämpötila"
 #. WEATHER_TERMS['UV INDEX']
 #: searx/searxng.msg
 msgid "UV index"
-msgstr "UV indeksi"
+msgstr "UV-indeksi"
 
 #. WEATHER_TERMS['VISIBILITY']
 #: searx/searxng.msg
@@ -293,7 +293,7 @@ msgstr "Osittain pilvistä"
 #. WEATHER_CONDITIONS
 #: searx/searxng.msg
 msgid "Cloudy"
-msgstr "Pilvinen"
+msgstr "Pilvistä"
 
 #. WEATHER_CONDITIONS
 #: searx/searxng.msg
@@ -303,7 +303,7 @@ msgstr "Selkeää"
 #. WEATHER_CONDITIONS
 #: searx/searxng.msg
 msgid "Fog"
-msgstr "Sumu"
+msgstr "Sumuista"
 
 #. WEATHER_CONDITIONS
 #: searx/searxng.msg
@@ -463,7 +463,7 @@ msgstr ""
 #. WEATHER_CONDITIONS
 #: searx/searxng.msg
 msgid "Snow"
-msgstr ""
+msgstr "Lumisadetta"
 
 #. WEATHER_CONDITIONS
 #: searx/searxng.msg
@@ -524,7 +524,7 @@ msgstr "pisteet"
 #. SOCIAL_MEDIA_TERMS['TITLE']
 #: searx/searxng.msg
 msgid "title"
-msgstr "Otsikko"
+msgstr "otsikko"
 
 #. SOCIAL_MEDIA_TERMS['AUTHOR']
 #: searx/engines/hackernews.py:85 searx/searxng.msg
@@ -534,7 +534,7 @@ msgstr "tekijä"
 #. SOCIAL_MEDIA_TERMS['THREAD OPEN']
 #: searx/engines/discourse.py:149 searx/searxng.msg
 msgid "open"
-msgstr "Avaa"
+msgstr "avoin"
 
 #. SOCIAL_MEDIA_TERMS['THREAD CLOSED']
 #: searx/engines/discourse.py:149 searx/searxng.msg
@@ -685,7 +685,7 @@ msgid ""
 "{numCitations} citations from the year {firstCitationVelocityYear} to "
 "{lastCitationVelocityYear}"
 msgstr ""
-"{numCitations} Sitaatit vuodesta {firstCitationVelocityYear} vuoteen "
+"{numCitations} sitaattia vuodesta {firstCitationVelocityYear} vuoteen "
 "{lastCitationVelocityYear}"
 
 #: searx/engines/tineye.py:48
@@ -792,11 +792,11 @@ msgstr "Selaimesi tunnistetiedot: "
 
 #: searx/plugins/time_zone.py:34
 msgid "Timezones plugin"
-msgstr ""
+msgstr "Aikavyöhykkeiden liitännäinen"
 
 #: searx/plugins/time_zone.py:35
 msgid "Display the current time on different time zones."
-msgstr ""
+msgstr "Näytä aika eri aikavyöhykkeillä."
 
 #: searx/plugins/tor_check.py:42
 msgid "Tor check plugin"
@@ -924,7 +924,7 @@ msgstr "välimuistissa"
 
 #: searx/templates/simple/new_issue.html:64
 msgid "Start submitting a new issue on GitHub"
-msgstr "Avaa uusi issue GitHubissa"
+msgstr "Avaa uusi ongelma GitHubissa"
 
 #: searx/templates/simple/new_issue.html:66
 msgid "Please check for existing bugs about this engine on GitHub"
@@ -932,13 +932,12 @@ msgstr "Tarkista tämän hakukoneen tämänhetkiset ongelmat GitHubista"
 
 #: searx/templates/simple/new_issue.html:69
 msgid "I confirm there is no existing bug about the issue I encounter"
-msgstr "Vahvistan, että tästä bugista ei ole olemassaolevaa issue:ta"
+msgstr "Vahvistan, että tästä bugista ei ole olemassa ongelmaa"
 
 #: searx/templates/simple/new_issue.html:71
 msgid "If this is a public instance, please specify the URL in the bug report"
 msgstr ""
-"Jos kyseessä on julkinen instanssi, määritä sen URL-osoite "
+"Jos kyseessä on julkinen palvelin, määritä sen URL-osoite vikailmoituksessa"
-"vikailmoituksessa"
 
 #: searx/templates/simple/new_issue.html:72
 msgid "Submit a new issue on Github including the above information"
@@ -952,7 +951,7 @@ msgstr "Ei HTTPS-yhteyttä"
 #: searx/templates/simple/preferences.html:69
 #: searx/templates/simple/preferences.html:70
 msgid "View error logs and submit a bug report"
-msgstr "Katso virhelokit ja lähetä virhe raportti"
+msgstr "Katso virhelokit ja lähetä virheraportti"
 
 #: searx/templates/simple/preferences.html:74
 msgid "!bang for this engine"
@@ -960,7 +959,7 @@ msgstr "!bang tälle hakukoneelle"
 
 #: searx/templates/simple/preferences.html:80
 msgid "!bang for its categories"
-msgstr "!bang sen kategorioille"
+msgstr "!bang sen luokille"
 
 #: searx/templates/simple/preferences.html:102
 #: searx/templates/simple/stats.html:64
@@ -1283,7 +1282,7 @@ msgstr "Tuloksia ei löytynyt. Voit:"
 
 #: searx/templates/simple/messages/no_results.html:14
 msgid "There are no more results. You can try to:"
-msgstr "Tuloksia ei ole enään lisää. Voit yrittää:"
+msgstr "Ei enempää tuloksia. Voit yrittää:"
 
 #: searx/templates/simple/messages/no_results.html:19
 msgid "Refresh the page."
@@ -1299,7 +1298,7 @@ msgstr "Vaihtaa käytettävää hakukonetta asetuksista:"
 
 #: searx/templates/simple/messages/no_results.html:22
 msgid "Switch to another instance:"
-msgstr "Vaihtaa toiseen instanssiin:"
+msgstr "Vaihtaa toiseen palvelimeen:"
 
 #: searx/templates/simple/messages/no_results.html:24
 msgid "Search for another query or select another category."
@@ -1307,7 +1306,7 @@ msgstr "Hae toista kyselyä tai valitse toinen luokka."
 
 #: searx/templates/simple/messages/no_results.html:25
 msgid "Go back to the previous page using the previous page button."
-msgstr "Palaa edelliselle sivulle käyttäen edellinen sivu-nappia."
+msgstr "Palaa edelliselle sivulle käyttäen edellinen sivu -painiketta."
 
 #: searx/templates/simple/preferences/answerers.html:4
 #: searx/templates/simple/preferences/engines.html:23
@@ -1361,7 +1360,7 @@ msgstr ""
 
 #: searx/templates/simple/preferences/cookies.html:3
 msgid "With this list, you can assess the transparency of SearXNG."
-msgstr ""
+msgstr "Tämän listan perusteella voit arvioida SearXNG:n läpinäkyvyyttä."
 
 #: searx/templates/simple/preferences/cookies.html:9
 msgid "Cookie name"
@@ -1506,7 +1505,7 @@ msgstr "Kuvat välityspalvelimen kautta"
 
 #: searx/templates/simple/preferences/image_proxy.html:14
 msgid "Proxy image results through SearXNG"
-msgstr ""
+msgstr "Välitä kuvatulokset SearXNG-välityspalvelimen kautta"
 
 #: searx/templates/simple/preferences/infinite_scroll.html:2
 msgid "Infinite scroll"
@@ -1569,6 +1568,8 @@ msgid ""
 "Perform a search immediately if a category is selected. Disable to select"
 " multiple categories"
 msgstr ""
+"Suorita haku välittömästi, jos luokka on valittu. Poista käytöstä "
+"valitaksesi useita luokkia"
 
 #: searx/templates/simple/preferences/theme.html:2
 msgid "Theme"

searx/translations/vi/LC_MESSAGES/messages.po

@@ -23,13 +23,15 @@
 # haderachhh <haderachhh@noreply.codeberg.org>, 2025.
 # return42 <return42@noreply.codeberg.org>, 2025.
 # nhthinh <nhthinh@noreply.codeberg.org>, 2025.
+# recreationalprogamer <recreationalprogamer@noreply.codeberg.org>, 2025.
 msgid ""
 msgstr ""
 "Project-Id-Version: searx\n"
 "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n"
 "POT-Creation-Date: 2025-09-01 12:54+0000\n"
-"PO-Revision-Date: 2025-09-02 04:50+0000\n"
+"PO-Revision-Date: 2025-09-17 13:09+0000\n"
-"Last-Translator: return42 <return42@noreply.codeberg.org>\n"
+"Last-Translator: recreationalprogamer "
+"<recreationalprogamer@noreply.codeberg.org>\n"
 "Language-Team: Vietnamese <https://translate.codeberg.org/projects/searxng/"
 "searxng/vi/>\n"
 "Language: vi\n"
@@ -37,7 +39,7 @@ msgstr ""
 "Content-Type: text/plain; charset=utf-8\n"
 "Content-Transfer-Encoding: 8bit\n"
 "Plural-Forms: nplurals=1; plural=0;\n"
-"X-Generator: Weblate 5.12.2\n"
+"X-Generator: Weblate 5.13.2\n"
 "Generated-By: Babel 2.17.0\n"
 
 #. CONSTANT_NAMES['NO_SUBGROUPING']
@@ -53,17 +55,17 @@ msgstr "khác"
 #. CATEGORY_NAMES['FILES']
 #: searx/searxng.msg
 msgid "files"
-msgstr "các thư mục"
+msgstr "tệp"
 
 #. CATEGORY_NAMES['GENERAL']
 #: searx/searxng.msg
 msgid "general"
-msgstr "tổng quát"
+msgstr "chung"
 
 #. CATEGORY_NAMES['MUSIC']
 #: searx/searxng.msg
 msgid "music"
-msgstr "âm nhạc"
+msgstr "nhạc"
 
 #. CATEGORY_NAMES['SOCIAL_MEDIA']
 #: searx/searxng.msg
@@ -73,22 +75,22 @@ msgstr "mạng xã hội"
 #. CATEGORY_NAMES['IMAGES']
 #: searx/searxng.msg
 msgid "images"
-msgstr "hình ảnh"
+msgstr "ảnh"
 
 #. CATEGORY_NAMES['VIDEOS']
 #: searx/searxng.msg
 msgid "videos"
-msgstr "băng hình"
+msgstr "video"
 
 #. CATEGORY_NAMES['RADIO']
 #: searx/engines/radio_browser.py:151 searx/searxng.msg
 msgid "radio"
-msgstr "máy radio"
+msgstr "radio"
 
 #. CATEGORY_NAMES['TV']
 #: searx/searxng.msg
 msgid "tv"
-msgstr "tivi"
+msgstr "TV"
 
 #. CATEGORY_NAMES['IT']
 #: searx/searxng.msg
@@ -108,7 +110,7 @@ msgstr "bản đồ"
 #. CATEGORY_NAMES['ONIONS']
 #: searx/searxng.msg
 msgid "onions"
-msgstr "định tuyến onion"
+msgstr "trang onion"
 
 #. CATEGORY_NAMES['SCIENCE']
 #: searx/searxng.msg
@@ -118,22 +120,22 @@ msgstr "khoa học"
 #. CATEGORY_GROUPS['APPS']
 #: searx/searxng.msg
 msgid "apps"
-msgstr "Ứng dụng"
+msgstr "ứng dụng"
 
 #. CATEGORY_GROUPS['DICTIONARIES']
 #: searx/searxng.msg
 msgid "dictionaries"
-msgstr "Từ điển"
+msgstr "từ điển"
 
 #. CATEGORY_GROUPS['LYRICS']
 #: searx/searxng.msg
 msgid "lyrics"
-msgstr "Lời bài hát"
+msgstr "lời bài hát"
 
 #. CATEGORY_GROUPS['PACKAGES']
 #: searx/searxng.msg
 msgid "packages"
-msgstr "gói kiện/gói hàng"
+msgstr "gói"
 
 #. CATEGORY_GROUPS['Q_A']
 #: searx/searxng.msg
@@ -143,7 +145,7 @@ msgstr "hỏi đáp"
 #. CATEGORY_GROUPS['REPOS']
 #: searx/searxng.msg
 msgid "repos"
-msgstr "kho"
+msgstr "kho mã"
 
 #. CATEGORY_GROUPS['SOFTWARE_WIKIS']
 #: searx/searxng.msg
@@ -153,27 +155,27 @@ msgstr "wiki về phần mềm"
 #. CATEGORY_GROUPS['WEB']
 #: searx/searxng.msg
 msgid "web"
-msgstr "mạng lưới/mạng"
+msgstr "mạng"
 
 #. CATEGORY_GROUPS['SCIENTIFIC PUBLICATIONS']
 #: searx/searxng.msg
 msgid "scientific publications"
-msgstr "các công bố khoa học"
+msgstr "công bố khoa học"
 
 #. STYLE_NAMES['AUTO']
 #: searx/searxng.msg
 msgid "auto"
-msgstr "Tự động"
+msgstr "tự động"
 
 #. STYLE_NAMES['LIGHT']
 #: searx/searxng.msg
 msgid "light"
-msgstr "Sáng"
+msgstr "sáng"
 
 #. STYLE_NAMES['DARK']
 #: searx/searxng.msg
 msgid "dark"
-msgstr "Tối"
+msgstr "tối"
 
 #. STYLE_NAMES['BLACK']
 #: searx/searxng.msg
@@ -498,18 +500,18 @@ msgstr "người đăng ký"
 #. SOCIAL_MEDIA_TERMS['POSTS']
 #: searx/engines/lemmy.py:86 searx/searxng.msg
 msgid "posts"
-msgstr "những bài đăng"
+msgstr "bài đăng"
 
 #. SOCIAL_MEDIA_TERMS['ACTIVE USERS']
 #: searx/engines/lemmy.py:87 searx/searxng.msg
 msgid "active users"
-msgstr "Người dùng hoạt động"
+msgstr "người dùng hoạt động"
 
 #. SOCIAL_MEDIA_TERMS['COMMENTS']
 #: searx/engines/discourse.py:157 searx/engines/hackernews.py:82
 #: searx/engines/lemmy.py:130 searx/searxng.msg
 msgid "comments"
-msgstr "Bình luận"
+msgstr "bình luận"
 
 #. SOCIAL_MEDIA_TERMS['USER']
 #: searx/engines/lemmy.py:129 searx/engines/lemmy.py:164 searx/searxng.msg
@@ -578,7 +580,7 @@ msgstr "lỗi tìm kiếm"
 
 #: searx/webutils.py:36
 msgid "timeout"
-msgstr "Hết thời gian"
+msgstr "hết thời gian"
 
 #: searx/webutils.py:37
 msgid "parsing error"
@@ -590,7 +592,7 @@ msgstr "Lỗi giao thức HTTP"
 
 #: searx/webutils.py:39
 msgid "network error"
-msgstr "Lỗi mạng"
+msgstr "lỗi mạng"
 
 #: searx/webutils.py:40
 msgid "SSL error: certificate validation has failed"
@@ -610,7 +612,7 @@ msgstr "Lỗi kết nối HTTP"
 
 #: searx/webutils.py:56
 msgid "proxy error"
-msgstr "Lỗi proxy"
+msgstr "lỗi proxy"
 
 #: searx/webutils.py:57
 msgid "CAPTCHA"
@@ -622,11 +624,11 @@ msgstr "quá nhiều yêu cầu"
 
 #: searx/webutils.py:59
 msgid "access denied"
-msgstr "Truy cập bị từ chối"
+msgstr "truy cập bị từ chối"
 
 #: searx/webutils.py:60
 msgid "server API error"
-msgstr "Lỗi máy chủ API"
+msgstr "lỗi máy chủ API"
 
 #: searx/webutils.py:79
 msgid "Suspended"
@@ -635,7 +637,7 @@ msgstr "Treo/gián đoạn/chặn"
 #: searx/webutils.py:306
 #, python-brace-format
 msgid "{minutes} minute(s) ago"
-msgstr "{minutes} phút() trước"
+msgstr "{minutes} phút trước"
 
 #: searx/webutils.py:307
 #, python-brace-format
@@ -649,7 +651,7 @@ msgstr "Tạo các giá trị ngẫu nhiên khác nhau"
 #: searx/answerers/statistics.py:37
 #, python-brace-format
 msgid "Compute {func} of the arguments"
-msgstr "Tính toán {func} của các tham số"
+msgstr "Tính toán {func} của các đối số"
 
 #: searx/engines/openstreetmap.py:158
 msgid "Show route in map .."
@@ -662,7 +664,7 @@ msgstr "{title} (HẾT HẠN)"
 
 #: searx/engines/pdbe.py:103
 msgid "This entry has been superseded by"
-msgstr "Mục này đã được thay thế bởi"
+msgstr "Mục này đã được thay thế bằng"
 
 #: searx/engines/qwant.py:293
 msgid "Channel"
@@ -713,7 +715,7 @@ msgstr ""
 
 #: searx/engines/tineye.py:59
 msgid "The image could not be downloaded."
-msgstr "Hình ảnh không thể được hiển thị."
+msgstr "Không thể tải hình ảnh."
 
 #: searx/engines/zlibrary.py:138
 msgid "Book rating"
@@ -725,7 +727,7 @@ msgstr "Chất lượng tệp"
 
 #: searx/plugins/ahmia_filter.py:32
 msgid "Ahmia blacklist"
-msgstr "Ahmia blacklist"
+msgstr "Danh sách đen của Ahmia"
 
 #: searx/plugins/ahmia_filter.py:33
 msgid "Filter out onion results that appear in Ahmia's blacklist."
@@ -748,8 +750,8 @@ msgid ""
 "Converts strings to different hash digests. Available functions: md5, "
 "sha1, sha224, sha256, sha384, sha512."
 msgstr ""
-"Chuyển đổi chuỗi thành các giá trị băm với các hàm hỗ trợ: md5, sha1, "
+"Chuyển đổi xâu thành các giá trị băm với các hàm hỗ trợ: md5, sha1, sha224, "
-"sha224, sha256, sha384, sha512."
+"sha256, sha384, sha512."
 
 #: searx/plugins/hash_plugin.py:64
 msgid "hash digest"
@@ -797,15 +799,15 @@ msgstr "Tác nhân người dùng của bạn là: "
 
 #: searx/plugins/time_zone.py:34
 msgid "Timezones plugin"
-msgstr ""
+msgstr "Tiện ích múi giờ"
 
 #: searx/plugins/time_zone.py:35
 msgid "Display the current time on different time zones."
-msgstr ""
+msgstr "HIện thời gian hiện tại trong nhiều múi giờ khác nhau."
 
 #: searx/plugins/tor_check.py:42
 msgid "Tor check plugin"
-msgstr "Kiểm tra Tor plugin"
+msgstr "Plugin kiểm tra Tor"
 
 #: searx/plugins/tor_check.py:44
 msgid ""
@@ -818,7 +820,7 @@ msgstr ""
 
 #: searx/plugins/tor_check.py:65
 msgid "Could not download the list of Tor exit-nodes from"
-msgstr "Không thể tải xuống danh sách các đoạn trích xuất từ TOR từ"
+msgstr "Không thể tải xuống danh sách các nút thoát Tor từ"
 
 #: searx/plugins/tor_check.py:72
 msgid "You are using Tor and it looks like you have the external IP address"
@@ -877,7 +879,7 @@ msgstr "Được cung cấp bởi"
 
 #: searx/templates/simple/base.html:64
 msgid "a privacy-respecting, open metasearch engine"
-msgstr "một siêu công cụ tìm kiếm mã nguồn mỡ và tôn trọng quyền riêng tư"
+msgstr "một siêu công cụ tìm kiếm mã nguồn mở và tôn trọng quyền riêng tư"
 
 #: searx/templates/simple/base.html:65
 #: searx/templates/simple/result_templates/packages.html:59
@@ -886,11 +888,11 @@ msgstr "Mã nguồn"
 
 #: searx/templates/simple/base.html:66
 msgid "Issue tracker"
-msgstr "công cụ theo dõi các trục trặc"
+msgstr "Trang theo dõi vấn đề"
 
 #: searx/templates/simple/base.html:67 searx/templates/simple/stats.html:18
 msgid "Engine stats"
-msgstr "Các thông số về trình tìm kiếm"
+msgstr "Thông số về trình tìm kiếm"
 
 #: searx/templates/simple/base.html:69
 msgid "Public instances"
@@ -902,7 +904,7 @@ msgstr "Chính sách bảo mật"
 
 #: searx/templates/simple/base.html:75
 msgid "Contact instance maintainer"
-msgstr "Liên hệ người bảo toàn thực thể"
+msgstr "Liên hệ người bảo trì thực thể"
 
 #: searx/templates/simple/categories.html:30
 msgid "Click on the magnifier to perform search"
@@ -986,7 +988,7 @@ msgstr "P95"
 
 #: searx/templates/simple/preferences.html:136
 msgid "Failed checker test(s): "
-msgstr "Số bài kiểm định đã thất bại của công cụ kiểm tra: "
+msgstr "Số bài kiểm định thất bại: "
 
 #: searx/templates/simple/preferences.html:138
 msgid "Errors:"
@@ -1131,19 +1133,19 @@ msgstr "Tham số"
 #: searx/templates/simple/result_templates/files.html:36
 #: searx/templates/simple/stats.html:119
 msgid "Filename"
-msgstr "Tên file"
+msgstr "Tên tệp"
 
 #: searx/templates/simple/stats.html:120
 msgid "Function"
-msgstr "Chức năng"
+msgstr "Hàm"
 
 #: searx/templates/simple/stats.html:121
 msgid "Code"
-msgstr "Code"
+msgstr "Mã nguồn"
 
 #: searx/templates/simple/stats.html:128
 msgid "Checker"
-msgstr "Người kiểm duyệt"
+msgstr "Trình kiểm tra"
 
 #: searx/templates/simple/stats.html:131
 msgid "Failed test"
@@ -1156,7 +1158,7 @@ msgstr "Bình luận"
 #: searx/templates/simple/answer/translations.html:12
 #: searx/templates/simple/preferences/answerers.html:8
 msgid "Examples"
-msgstr "Các ví dụ"
+msgstr "Ví dụ"
 
 #: searx/templates/simple/answer/translations.html:21
 msgid "Definitions"
@@ -1206,7 +1208,7 @@ msgstr "Sao chép"
 
 #: searx/templates/simple/elements/suggestions.html:3
 msgid "Suggestions"
-msgstr "Các gợi ý"
+msgstr "Gợi ý"
 
 #: searx/templates/simple/filters/languages.html:1
 #: searx/templates/simple/preferences/language.html:2
@@ -1270,7 +1272,7 @@ msgstr "Tháng trước"
 
 #: searx/templates/simple/filters/time_range.html:15
 msgid "Last year"
-msgstr "Năm ngoái"
+msgstr "Năm trước"
 
 #: searx/templates/simple/messages/no_cookies.html:3
 msgid "Information!"
@@ -1302,7 +1304,7 @@ msgstr "Tìm kiếm truy vấn khác hoặc chọn danh mục khác (ở phía t
 
 #: searx/templates/simple/messages/no_results.html:21
 msgid "Change the search engine used in the preferences:"
-msgstr "Thay đổi công cụ tìm kiếm sẽ được dùng trong phần tùy chọn:"
+msgstr "Thay đổi công cụ tìm kiếm được dùng trong phần tùy chọn:"
 
 #: searx/templates/simple/messages/no_results.html:22
 msgid "Switch to another instance:"
@@ -1314,7 +1316,7 @@ msgstr "Tìm kiếm bằng truy vấn khác hoặc chọn mục khác."
 
 #: searx/templates/simple/messages/no_results.html:25
 msgid "Go back to the previous page using the previous page button."
-msgstr "Quay lại trang t rước bằng nút bấm trang trước"
+msgstr "Quay lại trang trước bằng nút bấm trang trước"
 
 #: searx/templates/simple/preferences/answerers.html:4
 #: searx/templates/simple/preferences/engines.html:23
@@ -1340,7 +1342,7 @@ msgstr "Danh sách các mô-đun trả lời nhanh của SearXNG."
 
 #: searx/templates/simple/preferences/answerers.html:29
 msgid "This is the list of plugins."
-msgstr "Danh sách các plugins."
+msgstr "Danh sách các plugin."
 
 #: searx/templates/simple/preferences/autocomplete.html:2
 msgid "Autocomplete"
@@ -1356,15 +1358,15 @@ msgstr "Căn giữa"
 
 #: searx/templates/simple/preferences/center_alignment.html:14
 msgid "Display results in the center of the page (Oscar layout)."
-msgstr "Hiển thị kết quả ở giữa trang (Oscar layout)."
+msgstr "Hiển thị kết quả ở giữa trang (bố cục Oscar)."
 
 #: searx/templates/simple/preferences/cookies.html:2
 msgid ""
 "This is the list of cookies and their values SearXNG is storing on your "
 "computer."
 msgstr ""
-"Danh sách tên và giá trị của những cookies mà SearXNG lưu trữ trên máy "
+"Danh sách tên và giá trị của những cookie mà SearXNG lưu trữ trên máy tính "
-"tính của bạn."
+"của bạn."
 
 #: searx/templates/simple/preferences/cookies.html:3
 msgid "With this list, you can assess the transparency of SearXNG."
@@ -1387,15 +1389,12 @@ msgid ""
 "Note: specifying custom settings in the search URL can reduce privacy by "
 "leaking data to the clicked result sites."
 msgstr ""
-"Ghi chú: việc định rõ cài đặt cá nhân trong URL tìm kiếm có thể làm suy "
+"Lưu ý: việc định rõ cài đặt cá nhân trong URL tìm kiếm có thể làm suy giảm "
-"giảm mức độ riêng tư vì nó chuyển dữ liệu đến các trang kết quả được nhấp"
+"mức độ riêng tư vì nó chuyển dữ liệu đến các trang kết quả được nhấp chọn."
-" chọn."
 
 #: searx/templates/simple/preferences/cookies.html:35
 msgid "URL to restore your preferences in another browser"
-msgstr ""
+msgstr "URL dùng để khôi phục những tuỳ chọn của bạn trong một trình duyệt khác"
-"URL dùng để khôi phục những lựa chọn ưu tiên của bạn trong một trình "
-"duyệt khác"
 
 #: searx/templates/simple/preferences/cookies.html:43
 msgid ""
@@ -1407,7 +1406,7 @@ msgstr ""
 
 #: searx/templates/simple/preferences/cookies.html:46
 msgid "Copy preferences hash"
-msgstr "Sao chép những mã băm được ưu tiên"
+msgstr "Sao chép mã băm tuỳ chọn"
 
 #: searx/templates/simple/preferences/cookies.html:57
 msgid "Insert copied preferences hash (without URL) to restore"
@@ -1415,7 +1414,7 @@ msgstr "Nhập mã băm của tùy chọn đã sao chép (không kèm URL) để
 
 #: searx/templates/simple/preferences/cookies.html:59
 msgid "Preferences hash"
-msgstr "Mã băm được ưu tiên"
+msgstr "Mã băm tuỳ chọn"
 
 #: searx/templates/simple/preferences/doi_resolver.html:1
 msgid "Digital Object Identifier (DOI)"
@@ -1502,7 +1501,7 @@ msgstr "Phím tắt"
 
 #: searx/templates/simple/preferences/hotkeys.html:13
 msgid "Vim-like"
-msgstr "Vim-like"
+msgstr "Giống Vim"
 
 #: searx/templates/simple/preferences/hotkeys.html:18
 msgid ""
@@ -1568,7 +1567,7 @@ msgstr "Mở các liên kết của kết quả trong tab trình duyệt mới"
 
 #: searx/templates/simple/preferences/safesearch.html:20
 msgid "Filter content"
-msgstr "Lọc các nội dung"
+msgstr "Lọc nội dung"
 
 #: searx/templates/simple/preferences/search_on_category_select.html:2
 msgid "Search on category select"
@@ -1600,11 +1599,11 @@ msgstr "Chọn tự động để tuân thủ cài đặt của trình duyệt"
 
 #: searx/templates/simple/preferences/tokens.html:2
 msgid "Engine tokens"
-msgstr "Các vé của công cụ tìm kiếm"
+msgstr "Mã truy cập của công cụ tìm kiếm"
 
 #: searx/templates/simple/preferences/tokens.html:9
 msgid "Access tokens for private engines"
-msgstr "Truy cập các vé cho các công cụ tìm kiếm riêng tư"
+msgstr "Mã truy cập cho các công cụ tìm kiếm riêng tư"
 
 #: searx/templates/simple/preferences/ui_locale.html:2
 msgid "Interface language"
@@ -1632,7 +1631,7 @@ msgstr "Máy chủ"
 
 #: searx/templates/simple/preferences/urlformatting.html:23
 msgid "Change result URL formatting"
-msgstr "Thay đổi kết quả định dạng URL"
+msgstr "Thay đổi định dạng URL kết quả"
 
 #: searx/templates/simple/result_templates/code.html:13
 msgid "Repository"
@@ -1652,13 +1651,13 @@ msgstr "ẩn nội dung"
 #: searx/templates/simple/result_templates/default.html:14
 #: searx/templates/simple/result_templates/videos.html:14
 msgid "This site did not provide any description."
-msgstr "Trang web này không cung cấp bất kỳ mô tả."
+msgstr "Trang web này không cung cấp bất kỳ mô tả nào."
 
 #: searx/templates/simple/result_templates/files.html:38
 #: searx/templates/simple/result_templates/images.html:22
 #: searx/templates/simple/result_templates/torrent.html:18
 msgid "Filesize"
-msgstr "Kích thước tập tin"
+msgstr "Kích cỡ tệp"
 
 #: searx/templates/simple/result_templates/files.html:40
 msgid "Date"
@@ -1687,7 +1686,7 @@ msgstr "Xem nguồn"
 
 #: searx/templates/simple/result_templates/map.html:12
 msgid "address"
-msgstr "Địa chỉ"
+msgstr "địa chỉ"
 
 #: searx/templates/simple/result_templates/map.html:43
 msgid "show map"
@@ -1773,7 +1772,7 @@ msgstr "liên kết magnet"
 
 #: searx/templates/simple/result_templates/torrent.html:8
 msgid "torrent file"
-msgstr "tập tin torrent"
+msgstr "tệp torrent"
 
 #: searx/templates/simple/result_templates/torrent.html:13
 msgid "Seeder"
@@ -1785,15 +1784,15 @@ msgstr "Leecher"
 
 #: searx/templates/simple/result_templates/torrent.html:19
 msgid "Number of Files"
-msgstr "Số lượng tập tin"
+msgstr "Số lượng tệp"
 
 #: searx/templates/simple/result_templates/videos.html:6
 msgid "show video"
-msgstr "hiện"
+msgstr "hiện video"
 
 #: searx/templates/simple/result_templates/videos.html:6
 msgid "hide video"
-msgstr "ẩn phim"
+msgstr "ẩn video"
 
 #~ msgid "Engine time (sec)"
 #~ msgstr "Thời gian trình tìm kiếm (giây)"

searx/utils.py

@@ -21,7 +21,8 @@ from datetime import timedelta
 from markdown_it import MarkdownIt
 
 from lxml import html
-from lxml.etree import ElementBase, XPath, XPathError, XPathSyntaxError
+from lxml.etree import XPath, XPathError, XPathSyntaxError
+from lxml.etree import ElementBase, _Element  # pyright: ignore[reportPrivateUsage]
 
 from searx import settings
 from searx.data import USER_AGENTS, data_dir
@@ -40,6 +41,9 @@ XPathSpecType: t.TypeAlias = str | XPath
 """Type alias used by :py:obj:`searx.utils.get_xpath`,
 :py:obj:`searx.utils.eval_xpath` and other XPath selectors."""
 
+ElementType: t.TypeAlias = ElementBase | _Element
+
+
 _BLOCKED_TAGS = ('script', 'style')
 
 _ECMA_UNESCAPE4_RE = re.compile(r'%u([0-9a-fA-F]{4})', re.UNICODE)
@@ -204,15 +208,23 @@ def markdown_to_text(markdown_str: str) -> str:
 
 
 def extract_text(
-    xpath_results: list[ElementBase] | ElementBase | str | Number | bool | None,
+    xpath_results: list[ElementType] | ElementType | str | Number | bool | None,
     allow_none: bool = False,
 ) -> str | None:
     """Extract text from a lxml result
 
-    * if xpath_results is list, extract the text from each result and concat the list
+    - If ``xpath_results`` is a list of :py:obj:`ElementType` objects, extract
-    * if xpath_results is a xml element, extract all the text node from it
+      the text from each result and concatenate the list in a string.
-      ( text_content() method from lxml )
+
-    * if xpath_results is a string element, then it's already done
+    - If ``xpath_results`` is a :py:obj:`ElementType` object, extract all the
+      text node from it ( :py:obj:`lxml.html.tostring`, ``method="text"`` )
+
+    - If ``xpath_results`` is of type :py:obj:`str` or :py:obj:`Number`,
+      :py:obj:`bool` the string value is returned.
+
+    - If ``xpath_results`` is of type ``None`` a :py:obj:`ValueError` is raised,
+      except ``allow_none`` is ``True`` where ``None`` is returned.
+
     """
     if isinstance(xpath_results, list):
         # it's list of result : concat everything using recursive call
@@ -220,7 +232,7 @@ def extract_text(
         for e in xpath_results:
             result = result + (extract_text(e) or '')
         return result.strip()
-    if isinstance(xpath_results, ElementBase):
+    if isinstance(xpath_results, ElementType):
         # it's a element
         text: str = html.tostring(  # type: ignore
             xpath_results,  # pyright: ignore[reportArgumentType]
@@ -289,7 +301,7 @@ def normalize_url(url: str, base_url: str) -> str:
     return url
 
 
-def extract_url(xpath_results: list[ElementBase] | ElementBase | str | Number | bool | None, base_url: str) -> str:
+def extract_url(xpath_results: list[ElementType] | ElementType | str | Number | bool | None, base_url: str) -> str:
     """Extract and normalize URL from lxml Element
 
     Example:
@@ -520,7 +532,7 @@ def get_xpath(xpath_spec: XPathSpecType) -> XPath:
     raise TypeError('xpath_spec must be either a str or a lxml.etree.XPath')  # pyright: ignore[reportUnreachable]
 
 
-def eval_xpath(element: ElementBase, xpath_spec: XPathSpecType) -> t.Any:
+def eval_xpath(element: ElementType, xpath_spec: XPathSpecType) -> t.Any:
     """Equivalent of ``element.xpath(xpath_str)`` but compile ``xpath_str`` into
     a :py:obj:`lxml.etree.XPath` object once for all.  The return value of
     ``xpath(..)`` is complex, read `XPath return values`_ for more details.
@@ -548,12 +560,12 @@ def eval_xpath(element: ElementBase, xpath_spec: XPathSpecType) -> t.Any:
         raise SearxEngineXPathException(xpath_spec, arg) from e
 
 
-def eval_xpath_list(element: ElementBase, xpath_spec: XPathSpecType, min_len: int | None = None) -> list[t.Any]:
+def eval_xpath_list(element: ElementType, xpath_spec: XPathSpecType, min_len: int | None = None) -> list[t.Any]:
     """Same as :py:obj:`searx.utils.eval_xpath`, but additionally ensures the
     return value is a :py:obj:`list`.  The minimum length of the list is also
     checked (if ``min_len`` is set)."""
 
-    result = eval_xpath(element, xpath_spec)
+    result: list[t.Any] = eval_xpath(element, xpath_spec)
     if not isinstance(result, list):
         raise SearxEngineXPathException(xpath_spec, 'the result is not a list')
     if min_len is not None and min_len > len(result):
@@ -562,7 +574,7 @@ def eval_xpath_list(element: ElementBase, xpath_spec: XPathSpecType, min_len: in
 
 
 def eval_xpath_getindex(
-    element: ElementBase,
+    element: ElementType,
     xpath_spec: XPathSpecType,
     index: int,
     default: t.Any = _NOTSET,

searx/weather.py

@@ -27,6 +27,7 @@ import babel
 import babel.numbers
 import babel.dates
 import babel.languages
+import flask_babel
 
 from searx import network
 from searx.cache import ExpireCache, ExpireCacheCfg
@@ -197,6 +198,7 @@ class GeoLocation:
 
 
 DateTimeFormats = typing.Literal["full", "long", "medium", "short"]
+DateTimeLocaleTypes = typing.Literal["UI"]
 
 
 @typing.final
@@ -205,6 +207,13 @@ class DateTime:
     conveniently combines :py:obj:`datetime.datetime` and
     :py:obj:`babel.dates.format_datetime`.  A conversion of time zones is not
     provided (in the current version).
+
+    The localized string representation can be obtained via the
+    :py:obj:`DateTime.l10n` and :py:obj:`DateTime.l10n_date` methods, where the
+    ``locale`` parameter defaults to the search language.  Alternatively, a
+    :py:obj:`GeoLocation` or a :py:obj:`babel.Locale` instance can be passed
+    directly. If the UI language is to be used, the string ``UI`` can be passed
+    as the value for the ``locale``.
     """
 
     def __init__(self, time: datetime.datetime):
@@ -216,15 +225,32 @@ class DateTime:
     def l10n(
         self,
         fmt: DateTimeFormats | str = "medium",
-        locale: babel.Locale | GeoLocation | None = None,
+        locale: DateTimeLocaleTypes | babel.Locale | GeoLocation | None = None,
     ) -> str:
         """Localized representation of date & time."""
-        if isinstance(locale, GeoLocation):
+        if isinstance(locale, str) and locale == "UI":
+            locale = flask_babel.get_locale()
+        elif isinstance(locale, GeoLocation):
             locale = locale.locale()
         elif locale is None:
             locale = babel.Locale.parse(_get_sxng_locale_tag(), sep='-')
         return babel.dates.format_datetime(self.datetime, format=fmt, locale=locale)
 
+    def l10n_date(
+        self,
+        fmt: DateTimeFormats | str = "medium",
+        locale: DateTimeLocaleTypes | babel.Locale | GeoLocation | None = None,
+    ) -> str:
+        """Localized representation of date."""
+
+        if isinstance(locale, str) and locale == "UI":
+            locale = flask_babel.get_locale()
+        elif isinstance(locale, GeoLocation):
+            locale = locale.locale()
+        elif locale is None:
+            locale = babel.Locale.parse(_get_sxng_locale_tag(), sep='-')
+        return babel.dates.format_date(self.datetime, format=fmt, locale=locale)
+
 
 @typing.final
 class Temperature:

utils/lib_sxng_container.sh

@@ -85,9 +85,20 @@ container.build() {
         info_msg "Set \$DOCKER_TAG: $DOCKER_TAG"
         info_msg "Set \$GIT_URL: $GIT_URL"
 
+        # change cmp to lockfile when available
+        timestamp_requirements_main=$(git log -1 --format='%ct' ./requirements.txt)
+        timestamp_requirements_server=$(git log -1 --format='%ct' ./requirements-server.txt)
+        if [[ "$timestamp_requirements_main" -ge "$timestamp_requirements_server" ]]; then
+            timestamp_venv="$timestamp_requirements_main"
+        else
+            timestamp_venv="$timestamp_requirements_server"
+        fi
+
+        timestamp_searx_settings=$(git log -1 --format='%ct' ./searx/settings.yml)
+
         if [ "$container_engine" = "podman" ]; then
-            params_build_builder="build --format=oci --platform=$platform --layers --identity-label=false"
+            params_build_builder="build --format=oci --platform=$platform --layers --identity-label=false --timestamp=$timestamp_venv"
-            params_build=$params_build_builder
+            params_build="build --format=oci --platform=$platform --layers --identity-label=false"
         else
             params_build_builder="build --platform=$platform"
             params_build=$params_build_builder
@@ -102,8 +113,8 @@ container.build() {
 
         # shellcheck disable=SC2086
         "$container_engine" $params_build_builder \
-            --build-arg="TIMESTAMP=$(git log -1 --date=format:'%Y%m%d%H%M.%S' --format='%ad')" \
+            --build-arg="TIMESTAMP_VENV=$timestamp_venv" \
-            --build-arg="TIMESTAMP_SETTINGS=$(git log -1 --date=format:'%Y%m%d%H%M.%S' --format='%ad' ./searx/settings.yml)" \
+            --build-arg="TIMESTAMP_SETTINGS=$timestamp_searx_settings" \
             --tag="localhost/$CONTAINER_IMAGE_ORGANIZATION/$CONTAINER_IMAGE_NAME:builder" \
             --file="./container/builder.dockerfile" \
             .