Merge 27aa9c4cb1 into b8f1a329d3

docs/index.rst

@@ -4,27 +4,22 @@ Welcome to SearXNG
 
   *Search without being tracked.*
 
-.. jinja:: searx
-
-   SearXNG is a free internet metasearch engine which aggregates results from up
-   to {{engines | length}} :ref:`search services <configured engines>`.  Users
-   are neither tracked nor profiled.  Additionally, SearXNG can be used over Tor
-   for online anonymity.
+SearXNG is a free internet metasearch engine which aggregates results from more
+than 70 search services.  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
 
    - :ref:`self hosted <installation>`
    - :ref:`no user tracking / no profiling <SearXNG protect privacy>`
    - script & cookies are optional
    - secure, encrypted connections
-      - :ref:`{{engines | length}} search engines <configured engines>`
-      - `58 translations <https://translate.codeberg.org/projects/searxng/searxng/>`_
-      - about 70 `well maintained <https://uptime.searxng.org/>`__ instances on searx.space_
+   - :ref:`about 200 search engines <configured engines>`
+   - `about 60 translations <https://translate.codeberg.org/projects/searxng/searxng/>`_
+   - about 100 `well maintained <https://uptime.searxng.org/>`__ instances on searx.space_
    - :ref:`easy integration of search engines <demo online engine>`
    - professional development: `CI <https://github.com/searxng/searxng/actions>`_,
      `quality assurance <https://dev.searxng.org/>`_ &

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/engines/loc.py

@@ -27,7 +27,7 @@ categories = ['images']
 paging = True
 
 endpoint = 'photos'
-base_url = 'https://www.loc.gov'
+base_url = 'https://loc.gov'
 search_string = "/{endpoint}/?sp={page}&{query}&fo=json"
 
 

searx/network/network.py

@@ -233,7 +233,8 @@ class Network:
             del kwargs['raise_for_httperror']
         return do_raise_for_httperror
 
-    def patch_response(self, response, do_raise_for_httperror):
+    @staticmethod
+    def patch_response(response, do_raise_for_httperror):
         if isinstance(response, httpx.Response):
             # requests compatibility (response is not streamed)
             # see also https://www.python-httpx.org/compatibility/#checking-for-4xx5xx-responses
@@ -241,11 +242,8 @@ class Network:
 
             # raise an exception
             if do_raise_for_httperror:
-                try:
                 raise_for_httperror(response)
-                except:
-                    self._logger.warning(f"HTTP Request failed: {response.request.method} {response.request.url}")
-                    raise
+
         return response
 
     def is_valid_response(self, response):
@@ -271,7 +269,7 @@ class Network:
                 else:
                     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)
+                    return Network.patch_response(response, do_raise_for_httperror)
             except httpx.RemoteProtocolError as e:
                 if not was_disconnected:
                     # the server has closed the connection:

searx/search/processors/online.py

@@ -138,6 +138,9 @@ class OnlineProcessor(EngineProcessor):
         self.engine.request(query, params)
 
         # ignoring empty urls
+        if params['url'] is None:
+            return None
+
         if not params['url']:
             return None
 

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