docs/index.rst

@@ -4,31 +4,26 @@ Welcome to SearXNG
 
   *Search without being tracked.*
 
-.. jinja:: searx
+SearXNG is a free internet metasearch engine which aggregates results from more
-
+than 70 search services.  Users are neither tracked nor profiled.  Additionally,
-   SearXNG is a free internet metasearch engine which aggregates results from up
+SearXNG can be used over Tor for online anonymity.
-   to {{engines | length}} :ref:`search services <configured engines>`.  Users
-   are neither tracked nor profiled.  Additionally, SearXNG can be used over Tor
-   for online anonymity.
 
 Get started with SearXNG by using one of the instances listed at searx.space_.
 If you don't trust anyone, you can set up your own, see :ref:`installation`.
 
-.. jinja:: searx
+.. sidebar::  features
 
-   .. sidebar::  features
+   - :ref:`self hosted <installation>`
-
+   - :ref:`no user tracking / no profiling <SearXNG protect privacy>`
-      - :ref:`self hosted <installation>`
+   - script & cookies are optional
-      - :ref:`no user tracking / no profiling <SearXNG protect privacy>`
+   - secure, encrypted connections
-      - script & cookies are optional
+   - :ref:`about 200 search engines <configured engines>`
-      - secure, encrypted connections
+   - `about 60 translations <https://translate.codeberg.org/projects/searxng/searxng/>`_
-      - :ref:`{{engines | length}} search engines <configured engines>`
+   - about 100 `well maintained <https://uptime.searxng.org/>`__ instances on searx.space_
-      - `58 translations <https://translate.codeberg.org/projects/searxng/searxng/>`_
+   - :ref:`easy integration of search engines <demo online engine>`
-      - about 70 `well maintained <https://uptime.searxng.org/>`__ instances on searx.space_
+   - professional development: `CI <https://github.com/searxng/searxng/actions>`_,
-      - :ref:`easy integration of search engines <demo online engine>`
+     `quality assurance <https://dev.searxng.org/>`_ &
-      - professional development: `CI <https://github.com/searxng/searxng/actions>`_,
+     `automated tested UI <https://dev.searxng.org/screenshots.html>`_
-	`quality assurance <https://dev.searxng.org/>`_ &
-	`automated tested UI <https://dev.searxng.org/screenshots.html>`_
 
 .. sidebar:: be a part
 

searx/engines/internet_archive_scholar.py

@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Internet Archive scholar(science)
+"""
+
+from datetime import datetime
+from urllib.parse import urlencode
+from searx.utils import html_to_text
+
+about = {
+    "website": "https://scholar.archive.org/",
+    "wikidata_id": "Q115667709",
+    "official_api_documentation": "https://scholar.archive.org/api/redoc",
+    "use_official_api": True,
+    "require_api_key": False,
+    "results": "JSON",
+}
+categories = ['science', 'scientific publications']
+paging = True
+
+base_url = "https://scholar.archive.org"
+results_per_page = 15
+
+
+def request(query, params):
+    args = {
+        "q": query,
+        "limit": results_per_page,
+        "offset": (params["pageno"] - 1) * results_per_page,
+    }
+    params["url"] = f"{base_url}/search?{urlencode(args)}"
+    params["headers"]["Accept"] = "application/json"
+    return params
+
+
+def response(resp):
+    results = []
+
+    json = resp.json()
+
+    for result in json["results"]:
+        publishedDate, content, doi = None, '', None
+
+        if result['biblio'].get('release_date'):
+            publishedDate = datetime.strptime(result['biblio']['release_date'], "%Y-%m-%d")
+
+        if len(result['abstracts']) > 0:
+            content = result['abstracts'][0].get('body')
+        elif len(result['_highlights']) > 0:
+            content = result['_highlights'][0]
+
+        if len(result['releases']) > 0:
+            doi = result['releases'][0].get('doi')
+
+        results.append(
+            {
+                'template': 'paper.html',
+                'url': result['fulltext']['access_url'],
+                'title': result['biblio'].get('title') or result['biblio'].get('container_name'),
+                'content': html_to_text(content),
+                'publisher': result['biblio'].get('publisher'),
+                'doi': doi,
+                'journal': result['biblio'].get('container_name'),
+                'authors': result['biblio'].get('contrib_names'),
+                'tags': result['tags'],
+                'publishedDate': publishedDate,
+                'issns': result['biblio'].get('issns'),
+                'pdf_url': result['fulltext'].get('access_url'),
+            }
+        )
+
+    return results

searx/settings.yml

@@ -1622,6 +1622,11 @@ engines:
     api_site: 'askubuntu'
     categories: [it, q&a]
 
+  - name: internetarchivescholar
+    engine: internet_archive_scholar
+    shortcut: ias
+    timeout: 15.0
+
   - name: superuser
     engine: stackexchange
     shortcut: su