Merge 1c9b28968d into 0f9694c90b

Engine was added in #2733 but the API does no longer exists. Related:

- https://github.com/searxng/searxng/issues/4038

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

docs/index.rst

@@ -4,22 +4,27 @@ Welcome to SearXNG
 
   *Search without being tracked.*
 
-SearXNG is a free internet metasearch engine which aggregates results from more
+.. jinja:: searx
-than 70 search services.  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 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.
 
 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:`about 200 search engines <configured engines>`
+      - :ref:`{{engines | length}} search engines <configured engines>`
-   - `about 60 translations <https://translate.codeberg.org/projects/searxng/searxng/>`_
+      - `58 translations <https://translate.codeberg.org/projects/searxng/searxng/>`_
-   - about 100 `well maintained <https://uptime.searxng.org/>`__ instances on searx.space_
+      - about 70 `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/>`_ &

docs/src/searx.botdetection.rst

@@ -53,6 +53,9 @@ Probe HTTP headers
 .. automodule:: searx.botdetection.http_user_agent
   :members:
 
+.. automodule:: searx.botdetection.sec_fetch
+  :members:
+
 .. _botdetection config:
 
 Config

searx/botdetection/_helpers.py

@@ -31,6 +31,9 @@ def dump_request(request: flask.Request):
         + " || Content-Length: %s" % request.headers.get('Content-Length')
         + " || Connection: %s" % request.headers.get('Connection')
         + " || User-Agent: %s" % request.headers.get('User-Agent')
+        + " || Sec-Fetch-Site: %s" % request.headers.get('Sec-Fetch-Site')
+        + " || Sec-Fetch-Mode: %s" % request.headers.get('Sec-Fetch-Mode')
+        + " || Sec-Fetch-Dest: %s" % request.headers.get('Sec-Fetch-Dest')
     )
 
 

searx/botdetection/http_sec_fetch.py

@@ -0,0 +1,59 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""
+Method ``http_sec_fetch``
+-------------------------
+
+The ``http_sec_fetch`` method protect resources from web attacks with `Fetch
+Metadata`_.  A request is filtered out in case of:
+
+- http header Sec-Fetch-Mode_ is invalid
+- http header Sec-Fetch-Dest_ is invalid
+
+.. _Fetch Metadata:
+   https://developer.mozilla.org/en-US/docs/Glossary/Fetch_metadata_request_header
+
+.. Sec-Fetch-Dest:
+   https://developer.mozilla.org/en-US/docs/Web/API/Request/destination
+
+.. Sec-Fetch-Mode:
+   https://developer.mozilla.org/en-US/docs/Web/API/Request/mode
+
+
+"""
+# pylint: disable=unused-argument
+
+from __future__ import annotations
+from ipaddress import (
+    IPv4Network,
+    IPv6Network,
+)
+
+import flask
+import werkzeug
+
+from . import config
+from ._helpers import logger
+
+
+def filter_request(
+    network: IPv4Network | IPv6Network,
+    request: flask.Request,
+    cfg: config.Config,
+) -> werkzeug.Response | None:
+
+    val = request.headers.get("Sec-Fetch-Mode", "")
+    if val != "navigate":
+        logger.debug("invalid Sec-Fetch-Mode '%s'", val)
+        return flask.redirect(flask.url_for('index'), code=302)
+
+    val = request.headers.get("Sec-Fetch-Site", "")
+    if val not in ('same-origin', 'same-site', 'none'):
+        logger.debug("invalid Sec-Fetch-Site '%s'", val)
+        flask.redirect(flask.url_for('index'), code=302)
+
+    val = request.headers.get("Sec-Fetch-Dest", "")
+    if val != "document":
+        logger.debug("invalid Sec-Fetch-Dest '%s'", val)
+        flask.redirect(flask.url_for('index'), code=302)
+
+    return None

searx/engines/internet_archive_scholar.py

@@ -1,71 +0,0 @@
-# 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://loc.gov'
+base_url = 'https://www.loc.gov'
 search_string = "/{endpoint}/?sp={page}&{query}&fo=json"
 
 

searx/limiter.py

@@ -111,6 +111,7 @@ from searx.botdetection import (
     http_accept_encoding,
     http_accept_language,
     http_user_agent,
+    http_sec_fetch,
     ip_limit,
     ip_lists,
     get_network,
@@ -178,16 +179,17 @@ def filter_request(request: flask.Request) -> werkzeug.Response | None:
         logger.error("BLOCK %s: matched BLOCKLIST - %s", network.compressed, msg)
         return flask.make_response(('IP is on BLOCKLIST - %s' % msg, 429))
 
-    # methods applied on /
+    # methods applied on all requests
 
     for func in [
         http_user_agent,
     ]:
         val = func.filter_request(network, request, cfg)
         if val is not None:
+            logger.debug(f"NOT OK ({func.__name__}): {network}: %s", dump_request(flask.request))
             return val
 
-    # methods applied on /search
+    # methods applied on /search requests
 
     if request.path == '/search':
 
@@ -196,12 +198,15 @@ def filter_request(request: flask.Request) -> werkzeug.Response | None:
             http_accept_encoding,
             http_accept_language,
             http_user_agent,
+            http_sec_fetch,
             ip_limit,
         ]:
             val = func.filter_request(network, request, cfg)
             if val is not None:
+                logger.debug(f"NOT OK ({func.__name__}): {network}: %s", dump_request(flask.request))
                 return val
-    logger.debug(f"OK {network}: %s", dump_request(flask.request))
+        logger.debug(f"OK: {network}: %s", dump_request(flask.request))
+
     return None
 
 

searx/network/network.py

@@ -233,8 +233,7 @@ class Network:
             del kwargs['raise_for_httperror']
         return do_raise_for_httperror
 
-    @staticmethod
+    def patch_response(self, response, do_raise_for_httperror):
-    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
@@ -242,8 +241,11 @@ 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):
@@ -269,7 +271,7 @@ class Network:
                 else:
                     response = await client.request(method, url, **kwargs)
                 if self.is_valid_response(response) or retries <= 0:
-                    return Network.patch_response(response, do_raise_for_httperror)
+                    return self.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

@@ -137,9 +137,6 @@ 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

@@ -1622,11 +1622,6 @@ 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