OwlBurst/Ponysearch
1
0
Fork 0
forked from Ponysearch/Ponysearch
Code Pull requests Activity

Merge remote-tracking branch 'upstream/master'

Browse source 
# Conflicts:
#	searx/static/themes/simple/css/searxng-rtl.min.css
#	searx/static/themes/simple/css/searxng-rtl.min.css.map
#	searx/static/themes/simple/css/searxng.min.css
#	searx/static/themes/simple/css/searxng.min.css.map
This commit is contained in:
Sky Splash 2024-11-03 01:09:20 +01:00
commit f70f63de09
246 changed files with 14672 additions and 4812 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
.github/workflows/integration.yml vendored
View file

@ -16,7 +16,7 @@ jobs:
strategy:
matrix:
os: [ubuntu-20.04]
python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
python-version: ["3.9", "3.10", "3.11", "3.12",]
steps:
- name: Checkout
uses: actions/checkout@v4
@ -25,7 +25,7 @@ jobs:
sudo ./utils/searxng.sh install packages
sudo apt install firefox
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
architecture: 'x64'
@ -45,14 +45,6 @@ jobs:
make V=1 gecko.driver
- name: Run tests
run: make V=1 ci.test
- name: Test coverage
run: make V=1 test.coverage
- name: Store coverage result
uses: actions/upload-artifact@v3
with:
name: coverage-${{ matrix.python-version }}
path: coverage/
retention-days: 60
themes:
name: Themes
@ -63,9 +55,9 @@ jobs:
- name: Install Ubuntu packages
run: sudo ./utils/searxng.sh install buildhost
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.9'
python-version: '3.12'
architecture: 'x64'
- name: Cache Python dependencies
id: cache-python
@ -75,7 +67,7 @@ jobs:
./local
./.nvm
./node_modules
key: python-ubuntu-20.04-3.9-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
key: python-ubuntu-20.04-3.12-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
- name: Install node dependencies
run: make V=1 node.env
- name: Build themes
@ -95,9 +87,9 @@ jobs:
- name: Install Ubuntu packages
run: sudo ./utils/searxng.sh install buildhost
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.9'
python-version: '3.12'
architecture: 'x64'
- name: Cache Python dependencies
id: cache-python
@ -107,7 +99,7 @@ jobs:
./local
./.nvm
./node_modules
key: python-ubuntu-20.04-3.9-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
key: python-ubuntu-20.04-3.12-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
- name: Build documentation
run: |
make V=1 docs.clean docs.html
@ -139,9 +131,9 @@ jobs:
fetch-depth: '0'
token: ${{ secrets.WEBLATE_GITHUB_TOKEN }}
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.9'
python-version: '3.12'
architecture: 'x64'
- name: Cache Python dependencies
id: cache-python
@ -151,7 +143,7 @@ jobs:
./local
./.nvm
./node_modules
key: python-ubuntu-20.04-3.9-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
key: python-ubuntu-20.04-3.12-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
- name: weblate & git setup
env:
WEBLATE_CONFIG: ${{ secrets.WEBLATE_CONFIG }}
@ -183,9 +175,9 @@ jobs:
# make sure "make docker.push" can get the git history
fetch-depth: '0'
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.9'
python-version: '3.12'
architecture: 'x64'
- name: Cache Python dependencies
id: cache-python
@ -195,7 +187,7 @@ jobs:
./local
./.nvm
./node_modules
key: python-ubuntu-20.04-3.9-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
key: python-ubuntu-20.04-3.12-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
- name: Set up QEMU
if: env.DOCKERHUB_USERNAME != null
uses: docker/setup-qemu-action@v1

6
.github/workflows/translations-update.yml vendored
View file

@ -16,9 +16,9 @@ jobs:
fetch-depth: '0'
token: ${{ secrets.WEBLATE_GITHUB_TOKEN }}
- name: Set up Python
uses: actions/setup-python@v4
uses: actions/setup-python@v5
with:
python-version: '3.9'
python-version: '3.12'
architecture: 'x64'
- name: Cache Python dependencies
id: cache-python
@ -28,7 +28,7 @@ jobs:
./local
./.nvm
./node_modules
key: python-ubuntu-20.04-3.9-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
key: python-ubuntu-20.04-3.12-${{ hashFiles('requirements*.txt', 'setup.py','.nvmrc', 'package.json') }}
- name: weblate & git setup
env:
WEBLATE_CONFIG: ${{ secrets.WEBLATE_CONFIG }}

1
.pylintrc
View file

@ -338,6 +338,7 @@ valid-metaclass-classmethod-first-arg=mcs
# Maximum number of arguments for function / method
max-args=8
max-positional-arguments=14
# Maximum number of attributes for a class (see R0902).
max-attributes=20

2
README.rst
View file

@ -66,7 +66,7 @@ A user_, admin_ and developer_ handbook is available on the homepage_.
Contact
=======
Ask questions or just chat about SearXNG on
Ask questions or chat with the SearXNG community (this not a chatbot) on
IRC
`#searxng on libera.chat <https://web.libera.chat/?channel=#searxng>`_

10
docs/admin/api.rst
View file

@ -84,9 +84,9 @@ HTML of the site. URL of the SearXNG instance and values are customizable.
.. code:: html
<form method="post" action="https://example.org/">
<!-- search --> <input type="text" name="q" />
<!-- categories --> <input type="hidden" name="categories" value="general,social media" />
<!-- language --> <input type="hidden" name="lang" value="all" />
<!-- locale --> <input type="hidden" name="locale" value="en" />
<!-- date filter --> <input type="hidden" name="time_range" value="month" />
<!-- search --> <input type="text" name="q">
<!-- categories --> <input type="hidden" name="categories" value="general,social media">
<!-- language --> <input type="hidden" name="lang" value="all">
<!-- locale --> <input type="hidden" name="locale" value="en">
<!-- date filter --> <input type="hidden" name="time_range" value="month">
</form>

1
docs/admin/index.rst
View file

@ -15,6 +15,7 @@ Administrator documentation
installation-apache
update-searxng
answer-captcha
searx.favicons
searx.limiter
api
architecture

251
docs/admin/searx.favicons.rst Normal file
View file

@ -0,0 +1,251 @@
.. _favicons:
========
Favicons
========
.. sidebar:: warning
Don't activate the favicons before reading the documentation.
.. contents::
:depth: 2
:local:
:backlinks: entry
Activating the favicons in SearXNG is very easy, but this **generates a
significantly higher load** in the client/server communication and increases
resources needed on the server.
To mitigate these disadvantages, various methods have been implemented,
including a *cache*. The cache must be parameterized according to your own
requirements and maintained regularly.
To activate favicons in SearXNG's result list, set a default
``favicon_resolver`` in the :ref:`search <settings search>` settings:
.. code:: yaml
search:
favicon_resolver: "duckduckgo"
By default and without any extensions, SearXNG serves these resolvers:
- ``duckduckgo``
- ``allesedv``
- ``google``
- ``yandex``
With the above setting favicons are displayed, the user has the option to
deactivate this feature in his settings. If the user is to have the option of
selecting from several *resolvers*, a further setting is required / but this
setting will be discussed :ref:`later <register resolvers>` in this article,
first we have to setup the favicons cache.
Infrastructure
==============
The infrastructure for providing the favicons essentially consists of three
parts:
- :py:obj:`Favicons-Proxy <.favicons.proxy>` (aka *proxy*)
- :py:obj:`Favicons-Resolvers <.favicons.resolvers>` (aka *resolver*)
- :py:obj:`Favicons-Cache <.favicons.cache>` (aka *cache*)
To protect the privacy of users, the favicons are provided via a *proxy*. This
*proxy* is automatically activated with the above activation of a *resolver*.
Additional requests are required to provide the favicons: firstly, the *proxy*
must process the incoming requests and secondly, the *resolver* must make
outgoing requests to obtain the favicons from external sources.
A *cache* has been developed to massively reduce both, incoming and outgoing
requests. This *cache* is also activated automatically with the above
activation of a *resolver*. In its defaults, however, the *cache* is minimal
and not well suitable for a production environment!
.. _favicon cache setup:
Setting up the cache
====================
To parameterize the *cache* and more settings of the favicons infrastructure, a
TOML_ configuration is created in the file ``/etc/searxng/favicons.toml``.
.. code:: toml
[favicons]
cfg_schema = 1 # config's schema version no.
[favicons.cache]
db_url = "/var/cache/searxng/faviconcache.db" # default: "/tmp/faviconcache.db"
LIMIT_TOTAL_BYTES = 2147483648 # 2 GB / default: 50 MB
# HOLD_TIME = 5184000 # 60 days / default: 30 days
# BLOB_MAX_BYTES = 40960 # 40 KB / default 20 KB
# MAINTENANCE_MODE = "off" # default: "auto"
# MAINTENANCE_PERIOD = 600 # 10min / default: 1h
:py:obj:`cfg_schema <.FaviconConfig.cfg_schema>`:
Is required to trigger any processes required for future upgrades / don't
change it.
:py:obj:`cache.db_url <.FaviconCacheConfig.db_url>`:
The path to the (SQLite_) database file. The default path is in the `/tmp`_
folder, which is deleted on every reboot and is therefore unsuitable for a
production environment. The FHS_ provides the folder for the
application cache
The FHS_ provides the folder `/var/cache`_ for the cache of applications, so a
suitable storage location of SearXNG's caches is folder ``/var/cache/searxng``.
In container systems, a volume should be mounted for this folder and in a
standard installation (compare :ref:`create searxng user`), the folder must be
created and the user under which the SearXNG process is running must be given
write permission to this folder.
.. code:: bash
$ sudo mkdir /var/cache/searxng
$ sudo chown root:searxng /var/cache/searxng/
$ sudo chmod g+w /var/cache/searxng/
:py:obj:`cache.LIMIT_TOTAL_BYTES <.FaviconCacheConfig.LIMIT_TOTAL_BYTES>`:
Maximum of bytes stored in the cache of all blobs. The limit is only reached
at each maintenance interval after which the oldest BLOBs are deleted; the
limit is exceeded during the maintenance period.
.. attention::
If the maintenance period is too long or maintenance is switched
off completely, the cache grows uncontrollably.
SearXNG hosters can change other parameters of the cache as required:
- :py:obj:`cache.HOLD_TIME <.FaviconCacheConfig.HOLD_TIME>`
- :py:obj:`cache.BLOB_MAX_BYTES <.FaviconCacheConfig.BLOB_MAX_BYTES>`
Maintenance of the cache
------------------------
Regular maintenance of the cache is required! By default, regular maintenance
is triggered automatically as part of the client requests:
- :py:obj:`cache.MAINTENANCE_MODE <.FaviconCacheConfig.MAINTENANCE_MODE>` (default ``auto``)
- :py:obj:`cache.MAINTENANCE_PERIOD <.FaviconCacheConfig.MAINTENANCE_PERIOD>` (default ``6000`` / 1h)
As an alternative to maintenance as part of the client request process, it is
also possible to carry out maintenance using an external process. For example,
by creating a :man:`crontab` entry for maintenance:
.. code:: bash
$ python -m searx.favicons cache maintenance
The following command can be used to display the state of the cache:
.. code:: bash
$ python -m searx.favicons cache state
.. _favicon proxy setup:
Proxy configuration
===================
Most of the options of the :py:obj:`Favicons-Proxy <.favicons.proxy>` are
already set sensibly with settings from the :ref:`settings.yml <searxng
settings.yml>` and should not normally be adjusted.
.. code:: toml
[favicons.proxy]
max_age = 5184000 # 60 days / default: 7 days (604800 sec)
:py:obj:`max_age <.FaviconProxyConfig.max_age>`:
The `HTTP Cache-Control max-age`_ response directive indicates that the
response remains fresh until N seconds after the response is generated. This
setting therefore determines how long a favicon remains in the client's cache.
As a rule, in the favicons infrastructure of SearXNG's this setting only
affects favicons whose byte size exceeds :ref:`BLOB_MAX_BYTES <favicon cache
setup>` (the other favicons that are already in the cache are embedded as
`data URL`_ in the :py:obj:`generated HTML <.favicons.proxy.favicon_url>`,
which can greatly reduce the number of additional requests).
.. _register resolvers:
Register resolvers
------------------
A :py:obj:`resolver <.favicon.resolvers>` is a function that obtains the favicon
from an external source. The resolver functions available to the user are
registered with their fully qualified name (FQN_) in a ``resolver_map``.
If no ``resolver_map`` is defined in the ``favicon.toml``, the favicon
infrastructure of SearXNG generates this ``resolver_map`` automatically
depending on the ``settings.yml``. SearXNG would automatically generate the
following TOML configuration from the following YAML configuration:
.. code:: yaml
search:
favicon_resolver: "duckduckgo"
.. code:: toml
[favicons.proxy.resolver_map]
"duckduckgo" = "searx.favicons.resolvers.duckduckgo"
If this automatism is not desired, then (and only then) a separate
``resolver_map`` must be created. For example, to give the user two resolvers to
choose from, the following configuration could be used:
.. code:: toml
[favicons.proxy.resolver_map]
"duckduckgo" = "searx.favicons.resolvers.duckduckgo"
"allesedv" = "searx.favicons.resolvers.allesedv"
# "google" = "searx.favicons.resolvers.google"
# "yandex" = "searx.favicons.resolvers.yandex"
.. note::
With each resolver, the resource requirement increases significantly.
The number of resolvers increases:
- the number of incoming/outgoing requests and
- the number of favicons to be stored in the cache.
In the following we list the resolvers available in the core of SearXNG, but via
the FQN_ it is also possible to implement your own resolvers and integrate them
into the *proxy*:
- :py:obj:`searx.favicons.resolvers.duckduckgo`
- :py:obj:`searx.favicons.resolvers.allesedv`
- :py:obj:`searx.favicons.resolvers.google`
- :py:obj:`searx.favicons.resolvers.yandex`
.. _SQLite:
https://www.sqlite.org/
.. _FHS:
https://refspecs.linuxfoundation.org/FHS_3.0/fhs/index.html
.. _`/var/cache`:
https://refspecs.linuxfoundation.org/FHS_3.0/fhs/ch05s05.html
.. _`/tmp`:
https://refspecs.linuxfoundation.org/FHS_3.0/fhs/ch03s18.html
.. _TOML:
https://toml.io/en/
.. _HTTP Cache-Control max-age:
https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Cache-Control#response_directives
.. _data URL:
https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs
.. _FQN: https://en.wikipedia.org/wiki/Fully_qualified_name

6
docs/admin/settings/settings_search.rst
View file

@ -9,6 +9,7 @@
search:
safe_search: 0
autocomplete: ""
favicon_resolver: ""
default_lang: ""
ban_time_on_fail: 5
max_ban_time_on_fail: 120
@ -41,6 +42,11 @@
- ``qwant``
- ``wikipedia``
``favicon_resolver``:
To activate favicons in SearXNG's result list select a default
favicon-resolver, leave blank to turn off the feature. Don't activate the
favicons before reading the :ref:`Favicons documentation <favicons>`.
``default_lang``:
Default search language - leave blank to detect from browser information or
use codes from :origin:`searx/languages.py`.

2
docs/admin/settings/settings_ui.rst
View file

@ -58,7 +58,7 @@
Name of the theme you want to use by default on your SearXNG instance.
``theme_args.simple_style``:
Style of simple theme: ``auto``, ``light``, ``dark``
Style of simple theme: ``auto``, ``light``, ``dark``, ``black``
``results_on_new_tab``:
Open result links in a new tab by default.

2
docs/build-templates/searxng.rst
View file

@ -113,7 +113,7 @@ ${fedora_build}
(${SERVICE_USER})$ command -v python && python --version
$SEARXNG_PYENV/bin/python
Python 3.8.1
Python 3.11.10
# update pip's boilerplate ..
pip install -U pip

1
docs/conf.py
View file

@ -127,6 +127,7 @@ extensions = [
"sphinx_tabs.tabs", # https://github.com/djungelorm/sphinx-tabs
'myst_parser', # https://www.sphinx-doc.org/en/master/usage/markdown.html
'notfound.extension', # https://github.com/readthedocs/sphinx-notfound-page
'sphinxcontrib.autodoc_pydantic', # https://github.com/mansenfranzen/autodoc_pydantic
]
autodoc_default_options = {

15
docs/dev/engines/offline/sql-engines.rst
View file

@ -25,7 +25,7 @@ Relational Database Management System (RDBMS) are supported:
- :ref:`engine sqlite`
- :ref:`engine postgresql`
- :ref:`engine mysql_server`
- :ref:`engine mysql_server` & :ref:`engine mariadb_server`
All of the engines above are just commented out in the :origin:`settings.yml
<searx/settings.yml>`, as you have to set the required attributes for the
@ -119,3 +119,16 @@ MySQL
.. automodule:: searx.engines.mysql_server
:members:
.. _engine mariadb_server:
MariaDB
--------
.. sidebar:: info
- :origin:`mariadb_server.py <searx/engines/mariadb_server.py>`
- ``pip install`` :pypi:`mariadb <mariadb>`
.. automodule:: searx.engines.mariadb_server
:members:

8
docs/dev/engines/online/gitlab.rst Normal file
View file

@ -0,0 +1,8 @@
.. _gitlab engine:
======
GitLab
======
.. automodule:: searx.engines.gitlab
:members:

54
docs/own-instance.rst
View file

@ -2,9 +2,9 @@
Why use a private instance?
===========================
.. sidebar:: Is it worth to run my own instance?
.. sidebar:: Is running my own instance worth it?
\.\. is a common question among SearXNG users. Before answering this
\.\.\.is a common question among SearXNG users. Before answering this
question, see what options a SearXNG user has.
.. contents::
@ -12,13 +12,13 @@ Why use a private instance?
:local:
:backlinks: entry
Public instances are open to everyone who has access to its URL. Usually, these
Public instances are open to everyone who has access to their URL. Usually, they
are operated by unknown parties (from the users' point of view). Private
instances can be used by a select group of people. It is for example a SearXNG of
group of friends or a company which can be accessed through VPN. Also it can be
single user one which runs on the user's laptop.
instances can be used by a select group of people, such as a SearXNG instance for a
group of friends, or a company which can be accessed through a VPN. Instances can also be
single-user instances, which run locally on the user's machine.
To gain more insight on how these instances work let's dive into how SearXNG
To gain more insight on how these instances work, let's dive into how SearXNG
protects its users.
.. _SearXNG protect privacy:
@ -26,26 +26,26 @@ protects its users.
How does SearXNG protect privacy?
=================================
SearXNG protects the privacy of its users in multiple ways regardless of the type
of the instance (private, public). Removal of private data from search requests
SearXNG protects the privacy of its users in multiple ways, regardless of the type
of the instance (private or public). Removal of private data from search requests
comes in three forms:
1. removal of private data from requests going to search services
2. not forwarding anything from a third party services through search services
1. Removing private data from requests going to search services
2. Not forwarding anything from third party services through search services
(e.g. advertisement)
3. removal of private data from requests going to the result pages
3. Removing private data from requests going to the results pages
Removing private data means not sending cookies to external search engines and
generating a random browser profile for every request. Thus, it does not matter
if a public or private instance handles the request, because it is anonymized in
both cases. IP addresses will be the IP of the instance. But SearXNG can be
both cases. The IP address used will be the IP of the instance, but SearXNG can also be
configured to use proxy or Tor. `Result proxy
<https://github.com/asciimoo/morty>`__ is supported, too.
SearXNG does not serve ads or tracking content unlike most search services. So
SearXNG does not serve ads or tracking content, unlike most search services. Therefore,
private data is not forwarded to third parties who might monetize it. Besides
protecting users from search services, both referring page and search query are
hidden from visited result pages.
protecting users from search services, both the referring page and search query are
hidden from the results pages being visited.
What are the consequences of using public instances?
@ -53,11 +53,11 @@ What are the consequences of using public instances?
If someone uses a public instance, they have to trust the administrator of that
instance. This means that the user of the public instance does not know whether
their requests are logged, aggregated and sent or sold to a third party.
their requests are logged, aggregated, and sent or sold to a third party.
Also, public instances without proper protection are more vulnerable to abusing
the search service, In this case the external service in exchange returns
CAPTCHAs or bans the IP of the instance. Thus, search requests return less
Also, public instances without proper protection are more vulnerable to abuse of
the search service, which may cause the external service to enforce
CAPTCHAs or to ban the IP address of the instance. Thus, search requests would return less
results.
I see. What about private instances?
@ -67,10 +67,10 @@ If users run their :ref:`own instances <installation>`, everything is in their
control: the source code, logging settings and private data. Unknown instance
administrators do not have to be trusted.
Furthermore, as the default settings of their instance is editable, there is no
need to use cookies to tailor SearXNG to their needs. So preferences will not be
Furthermore, as the default settings of their instance are editable, there is no
need to use cookies to tailor SearXNG to their needs and preferences will not
reset to defaults when clearing browser cookies. As settings are stored on
their computer, it will not be accessible to others as long as their computer is
the user's computer, they will not be accessible to others as long as their computer is
not compromised.
Conclusion
@ -80,7 +80,7 @@ Always use an instance which is operated by people you trust. The privacy
features of SearXNG are available to users no matter what kind of instance they
use.
If someone is on the go or just wants to try SearXNG for the first time public
instances are the best choices. Additionally, public instance are making a
world a better place, because those who cannot or do not want to run an
instance, have access to a privacy respecting search service.
For those on the go, or just wanting to try SearXNG for the first time, public
instances are the best choice. Public instances are also making the
world a better place by giving those who cannot, or do not want to, run an
instance access to a privacy-respecting search service.

48
docs/src/searx.favicons.rst Normal file
View file

@ -0,0 +1,48 @@
.. _favicons source:
=================
Favicons (source)
=================
.. contents::
:depth: 2
:local:
:backlinks: entry
.. automodule:: searx.favicons
:members:
.. _favicons.config:
Favicons Config
===============
.. automodule:: searx.favicons.config
:members:
.. _favicons.proxy:
Favicons Proxy
==============
.. automodule:: searx.favicons.proxy
:members:
.. _favicons.resolver:
Favicons Resolver
=================
.. automodule:: searx.favicons.resolvers
:members:
.. _favicons.cache:
Favicons Cache
==============
.. automodule:: searx.favicons.cache
:members:

8
docs/src/searx.sqlitedb.rst Normal file
View file

@ -0,0 +1,8 @@
.. _sqlite db:
=========
SQLite DB
=========
.. automodule:: searx.sqlitedb
:members:

25
requirements-dev.txt
View file

@ -2,24 +2,23 @@ mock==5.1.0
nose2[coverage_plugin]==0.15.1
cov-core==1.15.0
black==24.3.0
pylint==3.2.6
pylint==3.3.1
splinter==0.21.0
selenium==4.23.1
Pallets-Sphinx-Themes==2.1.3
Sphinx<=7.1.2; python_version == '3.8'
Sphinx==7.4.7; python_version > '3.8'
sphinx-issues==4.1.0
selenium==4.25.0
Pallets-Sphinx-Themes==2.3.0
Sphinx==7.4.7
sphinx-issues==5.0.0
sphinx-jinja==2.0.2
sphinx-tabs==3.4.5
sphinx-tabs==3.4.7
sphinxcontrib-programoutput==0.17
sphinx-autobuild==2021.3.14
sphinx-autobuild==2024.10.3
sphinx-notfound-page==1.0.4
myst-parser==3.0.1
linuxdoc==20240509
linuxdoc==20240924
aiounittest==1.4.2
yamllint==1.35.1
wlc==1.14
wlc==1.15
coloredlogs==15.0.1
docutils<=0.21; python_version == '3.8'
docutils>=0.21.2; python_version > '3.8'
docutils>=0.21.2
parameterized==0.9.0
autodoc_pydantic==2.2.0

9
requirements.txt
View file

@ -1,4 +1,4 @@
certifi==2024.7.4
certifi==2024.8.30
babel==2.16.0
flask-babel==4.0.0
flask==3.0.3
@ -9,10 +9,13 @@ python-dateutil==2.9.0.post0
pyyaml==6.0.2
httpx[http2]==0.24.1
Brotli==1.1.0
uvloop==0.20.0
uvloop==0.21.0
httpx-socks[asyncio]==0.7.7
setproctitle==1.3.3
redis==5.0.8
markdown-it-py==3.0.0
fasttext-predict==0.9.2.2
pytomlpp==1.0.13; python_version < '3.11'
tomli==2.0.2; python_version < '3.11'
msgspec==0.18.6
eval_type_backport; python_version < '3.9'
typer-slim==0.12.5

27
searx/botdetection/config.py
View file

@ -14,17 +14,7 @@ import typing
import logging
import pathlib
try:
import tomllib
pytomlpp = None
USE_TOMLLIB = True
except ImportError:
import pytomlpp
tomllib = None
USE_TOMLLIB = False
from ..compat import tomllib
__all__ = ['Config', 'UNSET', 'SchemaIssue']
@ -183,19 +173,10 @@ class Config:
def toml_load(file_name):
if USE_TOMLLIB:
# Python >= 3.11
try:
with open(file_name, "rb") as f:
return tomllib.load(f)
except tomllib.TOMLDecodeError as exc:
msg = str(exc).replace('\t', '').replace('\n', ' ')
log.error("%s: %s", file_name, msg)
raise
# fallback to pytomlpp for Python < 3.11
try:
return pytomlpp.load(file_name)
except pytomlpp.DecodeError as exc:
with open(file_name, "rb") as f:
return tomllib.load(f)
except tomllib.TOMLDecodeError as exc:
msg = str(exc).replace('\t', '').replace('\n', ' ')
log.error("%s: %s", file_name, msg)
raise

6
searx/botdetection/ip_limit.py
View file

@ -76,11 +76,11 @@ LONG_MAX = 150
LONG_MAX_SUSPICIOUS = 10
"""Maximum suspicious requests from one IP in the :py:obj:`LONG_WINDOW`"""
API_WONDOW = 3600
API_WINDOW = 3600
"""Time (sec) before sliding window for API requests (format != html) expires."""
API_MAX = 4
"""Maximum requests from one IP in the :py:obj:`API_WONDOW`"""
"""Maximum requests from one IP in the :py:obj:`API_WINDOW`"""
SUSPICIOUS_IP_WINDOW = 3600 * 24 * 30
"""Time (sec) before sliding window for one suspicious IP expires."""
@ -103,7 +103,7 @@ def filter_request(
return None
if request.args.get('format', 'html') != 'html':
c = incr_sliding_window(redis_client, 'ip_limit.API_WONDOW:' + network.compressed, API_WONDOW)
c = incr_sliding_window(redis_client, 'ip_limit.API_WINDOW:' + network.compressed, API_WINDOW)
if c > API_MAX:
return too_many_requests(network, "too many request in API_WINDOW")

2
searx/botdetection/link_token.py
View file

@ -28,7 +28,7 @@ And in the HTML template from flask a stylesheet link is needed (the value of
<link rel="stylesheet"
href="{{ url_for('client_token', token=link_token) }}"
type="text/css" />
type="text/css" >
.. _X-Forwarded-For:
https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Forwarded-For

18
searx/compat.py Normal file
View file

@ -0,0 +1,18 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Compatibility with older versions"""
# pylint: disable=unused-import
__all__ = [
"tomllib",
]
import sys
# TOML (lib) compatibility
# ------------------------
if sys.version_info >= (3, 11):
import tomllib
else:
import tomli as tomllib

4473
searx/data/ahmia_blacklist.txt
View file

File diff suppressed because it is too large Load diff

135
searx/data/currencies.json
View file

@ -7,6 +7,7 @@
"bn": "সংযুক্ত আরব আমিরাতের দিরহাম",
"ca": "dírham dels Emirats Àrabs Units",
"cs": "dirham Spojených arabských emirátů",
"cy": "dirham yr Emiradau Arabaidd Unedig",
"da": "Emiratisk dirham",
"de": "VAE-Dirham",
"en": "United Arab Emirates dirham",
@ -23,7 +24,7 @@
"ja": "UAEディルハム",
"ko": "아랍에미리트 디르함",
"lt": "Jungtinių Arabų Emyratų dirhamas",
"ml": "യുണൈറ്റഡ് അറബ് എമിരേറ്റ്സ് ദിർഹം",
"ml": "AE92 0530 0000 1514 1185 002",
"ms": "Dirham Emiriah Arab Bersatu",
"nl": "VAE-Dirham",
"oc": "Diram emirati",
@ -81,7 +82,7 @@
"af": "Albanese lek",
"ar": "ليك ألباني",
"bg": "Албански лек",
"ca": "lek",
"ca": "Lek (moneda)",
"cs": "Albánský lek",
"cy": "Lek",
"da": "Lek",
@ -277,6 +278,7 @@
"bg": "Австралийски долар",
"ca": "dòlar australià",
"cs": "australský dolar",
"cy": "Doler Awstralia",
"da": "australsk dollar",
"de": "Australischer Dollar",
"en": "Australian dollar",
@ -353,6 +355,7 @@
"af": "Azerbeidjanse manat",
"ar": "مانات أذربيجاني",
"bg": "Азербайджански манат",
"bn": "আজারবাইজানি মানাত",
"ca": "manat azerbaidjanès",
"cs": "Ázerbájdžánský manat",
"cy": "Manat Aserbaijan",
@ -380,6 +383,7 @@
"nl": "Azerbeidzjaanse manat",
"oc": "Manat",
"pa": "ਅਜ਼ਰਬਾਈਜਾਨੀ ਮਨਾਤ",
"pap": "Manat Azerbaijano",
"pl": "Manat azerski",
"pt": "Manat azeri",
"ro": "Manat azer",
@ -389,6 +393,7 @@
"sr": "азербејџански манат",
"sv": "Azerbajdzjansk manat",
"ta": "அசர்பைச்சானிய மனாத்து",
"th": "มานัตอาเซอร์ไบจาน",
"tr": "Azerbaycan manatı",
"uk": "Азербайджанський манат",
"vi": "Manat Azerbaijan"
@ -602,6 +607,7 @@
"pt": "Franco do Burúndi",
"ro": "franc burundez",
"ru": "бурундийский франк",
"sk": "Burundský frank",
"sl": "burundijski frank",
"sr": "бурундски франак",
"sv": "Burundisk franc",
@ -1323,6 +1329,7 @@
"pl": "escudo Zielonego Przylądka",
"pt": "escudo cabo-verdiano",
"ru": "Эскудо Кабо-Верде",
"sk": "Kapverdské escudo",
"sl": "zelenortski eskudo",
"sr": "зеленортски ескудо",
"sv": "Kapverdisk escudo",
@ -1401,6 +1408,7 @@
"pl": "frank Dżibuti",
"pt": "franco do Jibuti",
"ru": "Франк Джибути",
"sk": "Džibutský frank",
"sr": "џибутски франак",
"sv": "Djiboutisk franc",
"tr": "Cibuti frangı",
@ -1479,6 +1487,7 @@
"pt": "peso dominicano",
"ro": "peso dominican",
"ru": "доминиканское песо",
"sl": "dominikanski peso",
"sr": "доминикански пезос",
"sv": "Dominikansk peso",
"tr": "Dominik pesosu",
@ -1513,6 +1522,7 @@
"pt": "dinar argelino",
"ro": "Dinar algerian",
"ru": "алжирский динар",
"sk": "Alžírský dinár",
"sl": "alžirski dinar",
"sr": "алжирски динар",
"sv": "Algerisk dinar",
@ -1964,6 +1974,7 @@
"pl": "frank gwinejski",
"pt": "Franco da Guiné",
"ru": "Гвинейский франк",
"sk": "Guinejský frank",
"sl": "gvinejski frank",
"sr": "гвинејски франак",
"sv": "Guinesisk franc",
@ -2684,6 +2695,7 @@
"pt": "Franco comoriano",
"ro": "Franc comorian",
"ru": "Франк Комор",
"sk": "Komorský frank",
"sr": "коморски франак",
"sv": "Komoransk franc",
"tr": "Komor frangı",
@ -2981,6 +2993,7 @@
"pt": "rúpia do Sri Lanka",
"ru": "ланкийская рупия",
"si": "ශ්රී ලංකා රුපියල",
"sk": "Srílanská rupia",
"sl": "šrilanška rupija",
"sr": "шриланчанска рупија",
"sv": "Lankesisk rupie",
@ -3054,7 +3067,7 @@
"uk": "Лоті"
},
"LYD": {
"ar": "دينار ليبي",
"ar": "دينار ذهبي",
"bg": "Либийски динар",
"ca": "dinar libi",
"cs": "Libyjský dinár",
@ -3116,6 +3129,7 @@
"pt": "Dirham marroquino",
"ro": "Dirham marocan",
"ru": "марокканский дирхам",
"sk": "Marocký dirham",
"sl": "maroški dirham",
"sr": "марокански дирхам",
"sv": "Marockansk dirham",
@ -3127,6 +3141,7 @@
"bg": "Молдовска лея",
"ca": "leu moldau",
"cs": "moldavský lei",
"cy": "leu Moldofa",
"de": "moldauischer Leu",
"en": "Moldovan leu",
"eo": "moldava leo",
@ -3134,6 +3149,7 @@
"et": "Moldova leu",
"fi": "Moldovan leu",
"fr": "leu moldave",
"gl": "leu moldovo",
"he": "לאו מולדובני",
"hr": "moldavski lej",
"hu": "moldován lej",
@ -3342,6 +3358,7 @@
"bg": "Мавританска угия",
"ca": "ouguiya",
"cs": "Mauritánská ukíjá",
"cy": "ouguiya Mawritania",
"da": "Ouguiya",
"de": "Ouguiya",
"en": "Mauritanian ouguiya",
@ -3364,6 +3381,7 @@
"pl": "Ugija",
"pt": "Uguia",
"ru": "Мавританская угия",
"sk": "Mauritánska ukíjá",
"sr": "мауританска огија",
"sv": "Mauretansk ouguiya",
"tr": "Ugiya",
@ -3519,6 +3537,7 @@
"bg": "Малайзийски рингит",
"ca": "ringgit",
"cs": "Malajsijský ringgit",
"cy": "ringgit Maleisia",
"de": "Ringgit",
"en": "Malaysian ringgit",
"eo": "malajzia ringito",
@ -3736,6 +3755,7 @@
"bn": "নেপালি রুপি",
"ca": "rupia nepalesa",
"cs": "Nepálská rupie",
"cy": "Rupee Nepal",
"da": "Nepalesiske rupee",
"de": "Nepalesische Rupie",
"en": "Nepalese rupee",
@ -3807,6 +3827,7 @@
"sl": "novozelandski dolar",
"sr": "новозеландски долар",
"sv": "Nyzeeländsk dollar",
"th": "ดอลลาร์นิวซีแลนด์",
"tr": "Yeni Zelanda doları",
"uk": "новозеландський долар",
"vi": "Đô la New Zealand"
@ -3849,6 +3870,7 @@
"bg": "Панамска балбоа",
"ca": "balboa",
"cs": "Panamská balboa",
"cy": "Balboa Panama",
"de": "Panamaischer Balboa",
"en": "Panamanian balboa",
"eo": "panama balboo",
@ -3989,6 +4011,7 @@
"bn": "পাকিস্তানি রুপি",
"ca": "rupia pakistanesa",
"cs": "Pákistánská rupie",
"cy": "Rupee Pacistan",
"da": "Pakistanske rupee",
"de": "pakistanische Rupie",
"dv": "ޕާކިސްތާނީ ރުޕީ",
@ -4114,6 +4137,7 @@
"ar": "غواراني باراغواي",
"ca": "guaraní",
"cs": "paraguayský guaraní",
"cy": "Gwarani Paragwâi",
"de": "Paraguayischer Guaraní",
"en": "Paraguayan guaraní",
"eo": "paragvaja gvaranio",
@ -4163,6 +4187,7 @@
"lt": "Kataro rialas",
"ms": "Riyal Qatar",
"nl": "Qatarese rial",
"oc": "Riyal qatarita",
"pa": "ਕਤਰੀ ਰਿਆਲ",
"pl": "Rial Kataru",
"pt": "Rial catarense",
@ -4310,6 +4335,7 @@
"bg": "Руандийски франк",
"ca": "franc ruandès",
"cs": "Rwandský frank",
"cy": "Ffranc Rwanda",
"da": "Rwandisk franc",
"de": "Ruanda-Franc",
"en": "Rwandan franc",
@ -4655,6 +4681,7 @@
"bg": "Сомалийски шилинг",
"ca": "xíling somali",
"cs": "Somálský šilink",
"cy": "Swllt Somali",
"da": "Somalisk shilling",
"de": "Somalia-Schilling",
"en": "Somali shilling",
@ -4717,6 +4744,7 @@
"bg": "Южносудански паунд",
"ca": "lliura sud-sudanesa",
"cs": "jihosúdánská libra",
"cy": "Punt De Swdan",
"da": "Sydsudanesiske pund",
"de": "südsudanesisches Pfund",
"en": "South Sudanese pound",
@ -4753,6 +4781,7 @@
"ar": "دوبرا ساو تومي وبرينسيب",
"ca": "dobra",
"cs": "Svatotomášská dobra",
"cy": "Dobra São Tomé a Príncipe",
"da": "Dobra",
"de": "São-toméischer Dobra",
"en": "São Tomé and Príncipe dobra",
@ -4788,6 +4817,7 @@
"bn": "সিরীয় পাউন্ড",
"ca": "lliura siriana",
"cs": "syrská libra",
"cy": "Punt Syria",
"de": "syrische Lira",
"en": "Syrian pound",
"eo": "siria pundo",
@ -4881,6 +4911,7 @@
"pt": "baht",
"ru": "тайский бат",
"sk": "Thajský baht",
"sl": "tajski baht",
"sr": "тајландски бат",
"sv": "Baht",
"ta": "தாய்லாந்தின் பாட்",
@ -4931,6 +4962,7 @@
"bg": "Туркменски манат",
"ca": "manat turcman",
"cs": "Turkmenský manat",
"cy": "Manat newydd Tyrcmenestan",
"de": "Turkmenistan-Manat",
"en": "Turkmenistan new manat",
"eo": "turkmena manato",
@ -4985,6 +5017,7 @@
"lt": "Tuniso dinaras",
"ms": "Dinar Tunisia",
"nl": "tunesische dinar",
"oc": "dinar tunisian",
"pl": "Dinar tunezyjski",
"pt": "dinar tunisiano",
"ru": "тунисский динар",
@ -5077,6 +5110,7 @@
"bg": "Тринидадски и тобагски долар",
"ca": "dòlar de Trinitat i Tobago",
"cs": "Dolar Trinidadu a Tobaga",
"cy": "doler Trinidad a Thobago",
"de": "Trinidad-und-Tobago-Dollar",
"en": "Trinidad and Tobago dollar",
"eo": "trinidada dolaro",
@ -5182,41 +5216,41 @@
"cs": "ukrajinská hřivna",
"da": "hryvnia",
"de": "Hrywnja",
"en": "Hryvnia",
"en": "hryvnia",
"eo": "ukraina hrivno",
"es": "grivna",
"et": "Ukraina grivna",
"eu": "hryvnia",
"fi": "Ukrainan hryvnia",
"fr": "hryvnia",
"gl": "Hrivna",
"gl": "hrivna",
"he": "הריבניה",
"hr": "Grivnja",
"hr": "grivnja",
"hu": "ukrán hrivnya",
"ia": "hryvnja ukrainian",
"id": "Hryvnia Ukraina",
"id": "hryvnia Ukraina",
"it": "grivnia ucraina",
"ja": "フリヴニャ",
"ko": "우크라이나 흐리우냐",
"lt": "Grivina",
"lv": "Ukrainas hrivna",
"ms": "Hryvnia",
"ms": "hryvnia",
"nl": "Oekraïense hryvnja",
"oc": "Hryvnia",
"oc": "hryvnia",
"pa": "ਯੂਕਰੇਨੀ ਹਰੀਵਨਾ",
"pl": "hrywna",
"pt": "hryvnia",
"ro": "Grivnă",
"ro": "grivnă",
"ru": "украинская гривна",
"sk": "Ukrajinská hrivna",
"sk": "ukrajinská hrivna",
"sl": "ukrajinska grivna",
"sr": "украјинска хривња",
"sv": "hryvnja",
"ta": "ஹிருன்யா",
"th": "ฮรึวญา",
"tr": "Grivna",
"tr": "grivna",
"uk": "гривня",
"vi": "Hryvnia Ukraina"
"vi": "hryvnia Ukraina"
},
"UGX": {
"af": "Ugandiese shilling",
@ -5224,6 +5258,7 @@
"bg": "Угандийски шилинг",
"ca": "xíling ugandès",
"cs": "Ugandský šilink",
"cy": "Swllt Wganda",
"de": "Uganda-Schilling",
"en": "Ugandan shilling",
"eo": "uganda ŝilingo",
@ -5363,12 +5398,14 @@
"ja": "スム",
"ko": "우즈베키스탄 숨",
"lt": "Uzbekijos sumas",
"lv": "Uzbekistānas soms",
"nl": "Oezbeekse sum",
"pa": "ਉਜ਼ਬੇਕਿਸਤਾਨੀ ਸੋਮ",
"pl": "Sum",
"pt": "som usbeque",
"ro": "Som uzbec",
"ru": "узбекский сум",
"sk": "Uzbecký som",
"sr": "узбекистански сом",
"sv": "Uzbekistansk som",
"tr": "Özbekistan somu",
@ -5382,6 +5419,7 @@
"VES": {
"ar": "بوليفار السيادي",
"ca": "bolívar sobirà",
"cy": "sofren bolifar",
"en": "sovereign bolivar",
"es": "bolívar soberano",
"fr": "bolivar souverain",
@ -5397,6 +5435,7 @@
"bg": "виетнамски донг",
"ca": "dong",
"cs": "Vietnamský dong",
"cy": "đồng Fietnam",
"da": "Dong",
"de": "vietnamesischer Đồng",
"en": "Vietnamese đồng",
@ -5505,6 +5544,7 @@
"es": "franco CFA de África Central",
"fi": "Keski-Afrikan CFA-frangi",
"fr": "franc CFA d'Afrique centrale",
"gl": "franco CFA de África Central",
"he": "פרנק CFA מרכז אפריקני",
"hr": "Srednjoafrički CFA franak",
"ia": "CFA",
@ -5516,6 +5556,7 @@
"ms": "Franc CFA Afrika Tengah",
"nl": "Central African CFA franc",
"oc": "Franc CFA d'Africa Centrala",
"pl": "środkowoafrykański frank CFA",
"pt": "franco",
"ro": "Franc CFA BEAC",
"ru": "франк КФА BEAC",
@ -5618,7 +5659,7 @@
"eo": "specialaj rajtoj de enspezo",
"es": "Derechos Especiales de Giro",
"eu": "igorpen eskubide bereziak",
"fi": "Erityisnosto-oikeus",
"fi": "erityisnosto-oikeus",
"fr": "droits de tirage spéciaux",
"hr": "Posebna prava vučenja",
"hu": "különleges lehívási jog",
@ -5628,9 +5669,10 @@
"ko": "특별인출권",
"lt": "Specialiosios skolinimosi teisės",
"lv": "Speciālās aizņēmuma tiesības",
"ms": "hak pengeluaran khas",
"nl": "speciale trekkingsrechten",
"oc": "Drechs de tiratge Especials",
"pl": "Specjalne prawa ciągnienia",
"pl": "specjalne prawa ciągnienia",
"pt": "direitos especiais de saque",
"ro": "Drepturi speciale de tragere",
"ru": "специальные права заимствования",
@ -5648,7 +5690,7 @@
"bg": "Западноафрикански CFA франк",
"ca": "franc CFA de l'Àfrica Occidental",
"cs": "západoafrický CFA frank",
"cy": "franc CFA Gorllein ffrica",
"cy": "franc CFA Gorllein Affrica",
"de": "CFA-Franc BCEAO",
"en": "West African CFA franc",
"eo": "okcident-afrika franko",
@ -5750,12 +5792,13 @@
"en": "No currency"
},
"YER": {
"ar": "ريال عربي",
"ar": "ريال يمني",
"bg": "Йеменски риал",
"ca": "rial iemenita",
"cs": "Jemenský rijál",
"cy": "Rial Iemen",
"de": "Jemen-Rial",
"en": "rial",
"en": "Yemeni Rial",
"eo": "jemena rialo",
"es": "rial yemení",
"fi": "Jemenin rial",
@ -5809,7 +5852,7 @@
"lt": "Randas",
"lv": "Dienvidāfrikas rands",
"ml": "സൗത്ത് ആഫ്രിക്കൻ റാൻഡ്",
"ms": "Rand",
"ms": "Rand Afrika Selatan",
"nl": "Zuid-Afrikaanse rand",
"oc": "Rand sudafrican",
"pl": "Rand",
@ -5827,6 +5870,7 @@
"ar": "كواشا زامبي",
"ca": "kwacha zambià",
"cs": "Zambijská kwacha",
"cy": "Kwacha Sambia",
"da": "Zambianske kwacha",
"de": "sambischer Kwacha",
"en": "Zambian Kwacha",
@ -5866,10 +5910,12 @@
"es": "Oro de Zimbabue",
"fr": "or du Zimbabwe",
"id": "Zimbabwe Gold",
"it": "Zimbabwe Gold",
"ja": "ジンバブエ・ゴールド",
"ko": "짐바브웨 골드",
"nl": "Zimbabwe Gold",
"pl": "Złoto Zimbabwe",
"pt": "Ouro do Zimbábue",
"ru": "зимбабвийский золотой",
"sk": "zimbabwiansky zlatý",
"sl": "zimbabvejski gold",
@ -6069,11 +6115,13 @@
"Ush": "UGX",
"VT": "VUV",
"WS$": "WST",
"XDR": "XDR",
"Z$": "ZWL",
"ZK": "ZMW",
"a$": "AUD",
"abd doları": "USD",
"adb unit of account": "XUA",
"ae92 0530 0000 1514 1185 002": "AED",
"aed": "AED",
"af": "AFN",
"afegane": "AFN",
@ -7087,6 +7135,7 @@
"dinar tunezyjski": "TND",
"dinar tunisia": "TND",
"dinar tunisiaidd": "TND",
"dinar tunisian": "TND",
"dinar tunisiano": "TND",
"dinar tunisià": "TND",
"dinar tunisien": "TND",
@ -7165,6 +7214,7 @@
"dirham uae": "AED",
"dirham uea": "AED",
"dirham uni emirat arab": "AED",
"dirham yr emiradau arabaidd unedig": "AED",
"dirham zjednoczonych emiratów arabskich": "AED",
"diritti speciali di prelievo": "XDR",
"dirrã dos emirados árabes unidos": "AED",
@ -7190,6 +7240,7 @@
"dobra santotomense": "STN",
"dobra saotomejska": "STN",
"dobra são tomense": "STN",
"dobra são tomé a príncipe": "STN",
"dobra são tomé dan príncipe": "STN",
"dobra svetog tome i principa": "STN",
"dobra svetog tome i prinsipa": "STN",
@ -7373,10 +7424,12 @@
"CAD",
"BZD"
],
"doler awstralia": "AUD",
"doler dwyrain y caribî": "XCD",
"doler hong cong": "HKD",
"doler hong kong": "HKD",
"doler newydd taiwan": "TWD",
"doler trinidad a thobago": "TTD",
"doler yr unol daleithiau": "USD",
"dollar": [
"USD",
@ -7780,6 +7833,7 @@
"eritrese nakfa": "ERN",
"erityinen nosto oikeus": "XDR",
"erityiset nosto oikeudet": "XDR",
"erityisnosto oikeudet": "XDR",
"erityisnosto oikeus": "XDR",
"ermeni dramı": "AMD",
"ermenistan dramı": "AMD",
@ -7879,6 +7933,7 @@
"fen": "CNY",
"feninga": "BAM",
"ffranc canol affrica": "XAF",
"ffranc rwanda": "RWF",
"ffranc y congo": "CDF",
"fidschi dollar": "FJD",
"fidzhin dollari": "FJD",
@ -7998,7 +8053,7 @@
"franc cfa d'afrique centrale": "XAF",
"franc cfa de l'àfrica central": "XAF",
"franc cfa de l'àfrica occidental": "XOF",
"franc cfa gorllein ffrica": "XOF",
"franc cfa gorllein affrica": "XOF",
"franc cfa tây phi": "XOF",
"franc cfa trung phi": "XAF",
"franc cfa vest african": "XOF",
@ -8318,6 +8373,7 @@
"gvinejski franak": "GNF",
"gvinejski frank": "GNF",
"gvinėjos frankas": "GNF",
"gwarani paragwâi": "PYG",
"gy$": "GYD",
"gyd": "GYD",
"ĝibraltara pundo": "GIP",
@ -8333,6 +8389,8 @@
"haitský gourde": "HTG",
"haïtiaanse gourde": "HTG",
"hak penarikan khusus": "XDR",
"hak pengeluaran khas": "XDR",
"hak pengeluaran khusus": "XDR",
"halalas": "SAR",
"hegoafrikar rand": "ZAR",
"heller": "CZK",
@ -8917,6 +8975,7 @@
"kwacha malawien": "MWK",
"kwacha malawijska": "MWK",
"kwacha malawite": "MWK",
"kwacha sambia": "ZMW",
"kwacha zambese": "ZMW",
"kwacha zambia": "ZMW",
"kwacha zambian": "ZMW",
@ -9075,12 +9134,15 @@
"leu da roménia": "RON",
"leu da romênia": "RON",
"leu de moldàvia": "MDL",
"leu de moldova": "MDL",
"leu moldau": "MDL",
"leu moldave": "MDL",
"leu moldavo": "MDL",
"leu moldávio": "MDL",
"leu moldofa": "MDL",
"leu moldova": "MDL",
"leu moldovenesc": "MDL",
"leu moldovo": "MDL",
"leu romanès": "RON",
"leu romanés": "RON",
"leu romanian": "RON",
@ -9396,6 +9458,7 @@
"manat azerbaijandar": "AZN",
"manat azerbaijanês": "AZN",
"manat azerbaijano": "AZN",
"manat azerbaitjanés": "AZN",
"manat azerbaiyano": "AZN",
"manat azerbaïdjanais": "AZN",
"manat azerbejdżański": "AZN",
@ -9412,6 +9475,7 @@
"manat de turkmenistán": "TMT",
"manat del turkmenistan": "TMT",
"manat do azerbaijão": "AZN",
"manat newydd tyrcmenestan": "TMT",
"manat turcman": "TMT",
"manat turcmèn": "TMT",
"manat turcomano": "TMT",
@ -9478,6 +9542,7 @@
"mauritanijska ouguja": "MRU",
"mauritanijska uguija": "MRU",
"mauritániai ouguiya": "MRU",
"mauritánska ukíjá": "MRU",
"mauritánská ukíjá": "MRU",
"mauritānijas oguja": "MRU",
"mauritiaanse roepee": "MUR",
@ -9942,6 +10007,8 @@
"ouguiya della mauritana": "MRU",
"ouguiya mauritana": "MRU",
"ouguiya mauritanien": "MRU",
"ouguiya mawritania": "MRU",
"ouro do zimbábue": "ZWG",
"örmény dram": "AMD",
"östkaribisk dollar": "XCD",
"özbekistan somu": "UZS",
@ -10304,10 +10371,12 @@
"pula, unitate monetară": "BWP",
"pund sterling": "GBP",
"punt": "GBP",
"punt de swdan": "SSP",
"punt gibraltar": "GIP",
"punt libanus": "LBP",
"punt sterling": "GBP",
"punt swdan": "SDG",
"punt syria": "SYP",
"punt yr aifft": "EGP",
"puolan zloty": [
"PLZ",
@ -10411,6 +10480,7 @@
"rial do irão": "IRR",
"rial do omã": "OMR",
"rial do omão": "OMR",
"rial iemen": "YER",
"rial iemenita": "YER",
"rial iemení": "YER",
"rial iémenita": "YER",
@ -10460,6 +10530,7 @@
"ringgit malaio": "MYR",
"ringgit malaysia": "MYR",
"ringgit malaysiano": "MYR",
"ringgit maleisia": "MYR",
"ringgit malese": "MYR",
"ringgit singapore": "SGD",
"ringgit singapura": "SGD",
@ -10479,6 +10550,7 @@
"riyal qatari": "QAR",
"riyal qatarien": "QAR",
"riyal qatariota": "QAR",
"riyal qatarita": "QAR",
"riyal saoudien": "SAR",
"riyal saudi": "SAR",
"riyal saudita": "SAR",
@ -10597,6 +10669,7 @@
"rupee mauritus": "MUR",
"rupee nepal": "NPR",
"rupee nepali": "NPR",
"rupee pacistan": "PKR",
"rupee pakistan": "PKR",
"rupee seychelles": "SCR",
"rupee sri lanca": "LKR",
@ -10747,6 +10820,7 @@
"salomona dolaro": "SBD",
"salomondollar": "SBD",
"salomonen dollar": "SBD",
"salomoninsaarten dollari": "SBD",
"salomonsaarten dollari": "SBD",
"salomonskootočni dolar": "SBD",
"salüng": "THB",
@ -10992,6 +11066,7 @@
"so'm": "UZS",
"soedanees pond": "SDG",
"soedanese pond": "SDG",
"sofren bolifar": "VES",
"sol": "PEN",
"sol d'or": "PEN",
"sol de oro": "PEN",
@ -11102,6 +11177,7 @@
"srilankansk rupee": "LKR",
"srilankanske rupee": "LKR",
"srí lanka i rúpia": "LKR",
"srílanská rupia": "LKR",
"srílanská rupie": "LKR",
"srpski dinar": "RSD",
"ssp": "SSP",
@ -11214,8 +11290,10 @@
"swiss franken": "CHF",
"switserse frank": "CHF",
"swllt cenia": "KES",
"swllt somali": "SOS",
"swllt tansanïa": "TZS",
"swllt tanzania": "TZS",
"swllt wganda": "UGX",
"sydafrikansk rand": "ZAR",
"sydkoreansk won": "KRW",
"sydkoreanske won": "KRW",
@ -11249,6 +11327,7 @@
"szyling tanzański": "TZS",
"szyling ugandyjski": "UGX",
"sırp dinarı": "RSD",
"środkowoafrykański frank cfa": "XAF",
"šalamounský dolar": "SBD",
"šalomounský dolar": "SBD",
"šekel chadaš": "ILS",
@ -11297,6 +11376,7 @@
"tajikistani somoni": "TJS",
"tajlanda bahto": "THB",
"tajlandski baht": "THB",
"tajski baht": "THB",
"tajvana dolaro": "TWD",
"tajvani új dollár": "TWD",
"taka": [
@ -11361,6 +11441,7 @@
"tengue": "KZT",
"tengue cazaque": "KZT",
"teňňe": "TMT",
"tetri": "GEL",
"thai baht": "THB",
"thai bát": "THB",
"thailandiar baht": "THB",
@ -11485,10 +11566,10 @@
"turkisk lira": "TRY",
"turkiska lira": "TRY",
"turkmeense manat": "TMT",
"turkmen manat": "TMT",
"turkmena manato": "TMT",
"turkmenistan manat": "TMT",
"turkmenistan new manat": "TMT",
"turkmenistani manat": "TMT",
"turkmenistani new manat": "TMT",
"turkmenistanin manat": "TMT",
"turkmenistansk manat": "TMT",
@ -11654,6 +11735,7 @@
"uzbekistano sumas": "UZS",
"uzbekistansk som": "UZS",
"uzbekistanski som": "UZS",
"uzbekistānas soms": "UZS",
"uzs": "UZS",
"új zélandi dollár": "NZD",
"ürdün dinarı": "JOD",
@ -11807,6 +11889,7 @@
"yuan cinese": "CNY",
"yuan renmimbi": "CNY",
"yuan renminbi": "CNY",
"yuan rmb": "CNY",
"yuans": "CNY",
"yuán chino": "CNY",
"z$": "ZWL",
@ -12032,6 +12115,7 @@
"đồng bảng anh": "GBP",
"đồng bạc mĩ": "USD",
"đồng bạc mỹ": "USD",
"đồng fietnam": "VND",
"đồng forint": "HUF",
"đồng tiền": "VND",
"đồng vietnam": "VND",
@ -13679,6 +13763,7 @@
"دينار بحريني": "BHD",
"دينار تونسي": "TND",
"دينار جزائري": "DZD",
"دينار ذهبي": "LYD",
"دينار سوداني": "SDG",
"دينار صربي": "RSD",
"دينار عراقي": "IQD",
@ -13719,7 +13804,6 @@
"ريال إيراني": "IRR",
"ريال برازيلي": "BRL",
"ريال سعودي": "SAR",
"ريال عربي": "YER",
"ريال عماني": "OMR",
"ريال عُماني": "OMR",
"ريال قطري": "QAR",
@ -13889,6 +13973,7 @@
"रू.": "INR",
"অ্যাঙ্গোলীয় কুয়াঞ্জা": "AOA",
"আইসল্যান্ডীয় ক্রোনা": "ISK",
"আজারবাইজানি মানাত": "AZN",
"ই রুপি": "INR",
"ইউরো": "EUR",
"ইরানি রিয়াল": "IRR",
@ -13936,6 +14021,7 @@
"ਅਲਬਾਨੀਆਈ ਲੇਕ": "ALL",
"ਅੰਗੋਲਨ ਕਵਾਂਜ਼ਾ": "AOA",
"ਆਈਸਲੈਂਡੀ ਕਰੋਨਾ": "ISK",
"ਆਜ਼ਰਬਾਈਜਾਨੀ ਮਨਾਤ": "AZN",
"ਆਸਟ੍ਰੇਲੀਆਈ ਡਾਲਰ": "AUD",
"ਇਜ਼ਰਾਇਲੀ ਨਵਾਂ ਸ਼ੇਕਲ": "ILS",
"ਇਰਾਕੀ ਦਿਨਾਰ": "IQD",
@ -14227,7 +14313,6 @@
"ബർമ്മീസ് ക്യാറ്റ്": "MMK",
"ബൾഗേറിയൻ ലെവ്": "BGN",
"മൊറോക്കൻ ദിർഹം": "MAD",
"യു.എ.ഇ. ദിർഹം": "AED",
"യുണൈറ്റഡ് അറബ് എമിരേറ്റ്സ് ദിർഹം": "AED",
"യുണൈറ്റഡ് സ്റ്റേറ്റ്സ് ഡോളർ": "USD",
"യൂറോ": "EUR",
@ -14271,6 +14356,7 @@
"USD",
"TWD"
],
"ดอลลาร์นิวซีแลนด์": "NZD",
"ดอลลาร์บรูไน": "BND",
"ดอลลาร์สหรัฐ": "USD",
"ดอลลาร์สิงคโปร์": "SGD",
@ -14294,6 +14380,7 @@
"ปาอางา": "TOP",
"พาแองกา": "TOP",
"ฟรังก์สวิส": "CHF",
"มานัตอาเซอร์ไบจาน": "AZN",
"มานัตเติร์กเมนิสถาน": "TMT",
"ยูโร": "EUR",
"ริงกิต": "MYR",
@ -14942,6 +15029,7 @@
"ボツワナ・プラ": "BWP",
"ボリバル・ソベラノ": "VES",
"ボリビアーノ": "BOB",
"ポンド・スターリング": "GBP",
"ポーランド・ズウォティ": [
"PLZ",
"PLN"
@ -15007,7 +15095,6 @@
"中華人民共和国の通貨": "CNY",
"中部アフリカcfaフラン": "XAF",
"人民元": "CNY",
"人民币": "CNY",
"人民幣": "CNY",
"元": [
"HKD",

604
searx/data/engine_descriptions.json
View file

File diff suppressed because one or more lines are too long

1047
searx/data/engine_traits.json
View file

File diff suppressed because it is too large Load diff

4
searx/data/useragents.json
View file

@ -5,7 +5,7 @@
],
"ua": "Mozilla/5.0 ({os}; rv:{version}) Gecko/20100101 Firefox/{version}",
"versions": [
"129.0",
"128.0"
"132.0",
"131.0"
]
}

13
searx/data/wikidata_units.json
View file

@ -832,7 +832,7 @@
"Q104907390": {
"si_name": "Q182429",
"symbol": "nmi/h",
"to_si_factor": 0.514444
"to_si_factor": 0.5144444444444445
},
"Q104907398": {
"si_name": "Q215571",
@ -1336,7 +1336,7 @@
},
"Q106636307": {
"si_name": "Q80842107",
"symbol": "μS/cm",
"symbol": "μS/cm-1",
"to_si_factor": 0.0001
},
"Q106639711": {
@ -3594,11 +3594,6 @@
"symbol": "mm²",
"to_si_factor": 1e-06
},
"Q190951": {
"si_name": null,
"symbol": "S$",
"to_si_factor": null
},
"Q191118": {
"si_name": "Q11570",
"symbol": "t",
@ -4147,7 +4142,7 @@
"Q23931103": {
"si_name": "Q25343",
"symbol": "nmi²",
"to_si_factor": 3434290.0120544
"to_si_factor": 3429904.0
},
"Q239830": {
"si_name": "Q3395194",
@ -6516,7 +6511,7 @@
},
"Q68343206": {
"si_name": "Q68343206",
"symbol": "C/m²",
"symbol": "C²/m",
"to_si_factor": 1.0
},
"Q685662": {

28
searx/engines/annas_archive.py
View file

@ -34,10 +34,10 @@ Implementations
"""
from typing import List, Dict, Any, Optional
from urllib.parse import quote
from urllib.parse import urlencode
from lxml import html
from searx.utils import extract_text, eval_xpath, eval_xpath_list
from searx.utils import extract_text, eval_xpath, eval_xpath_getindex, eval_xpath_list
from searx.enginelib.traits import EngineTraits
from searx.data import ENGINE_TRAITS
@ -53,7 +53,7 @@ about: Dict[str, Any] = {
# engine dependent config
categories: List[str] = ["files"]
paging: bool = False
paging: bool = True
# search-url
base_url: str = "https://annas-archive.org"
@ -99,9 +99,18 @@ def init(engine_settings=None): # pylint: disable=unused-argument
def request(query, params: Dict[str, Any]) -> Dict[str, Any]:
q = quote(query)
lang = traits.get_language(params["language"], traits.all_locale) # type: ignore
params["url"] = base_url + f"/search?lang={lang or ''}&content={aa_content}&ext={aa_ext}&sort={aa_sort}&q={q}"
args = {
'lang': lang,
'content': aa_content,
'ext': aa_ext,
'sort': aa_sort,
'q': query,
'page': params['pageno'],
}
# filter out None and empty values
filtered_args = dict((k, v) for k, v in args.items() if v)
params["url"] = f"{base_url}/search?{urlencode(filtered_args)}"
return params
@ -128,12 +137,12 @@ def response(resp) -> List[Dict[str, Optional[str]]]:
def _get_result(item):
return {
'template': 'paper.html',
'url': base_url + item.xpath('./@href')[0],
'url': base_url + extract_text(eval_xpath_getindex(item, './@href', 0)),
'title': extract_text(eval_xpath(item, './/h3/text()[1]')),
'publisher': extract_text(eval_xpath(item, './/div[contains(@class, "text-sm")]')),
'authors': [extract_text(eval_xpath(item, './/div[contains(@class, "italic")]'))],
'content': extract_text(eval_xpath(item, './/div[contains(@class, "text-xs")]')),
'thumbnail': item.xpath('.//img/@src')[0],
'thumbnail': extract_text(eval_xpath_getindex(item, './/img/@src', 0, default=None), allow_none=True),
}
@ -184,3 +193,8 @@ def fetch_traits(engine_traits: EngineTraits):
for x in eval_xpath_list(dom, "//form//select[@name='sort']//option"):
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['ext'].sort()
engine_traits.custom['sort'].sort()

6
searx/engines/bilibili.py
View file

@ -9,6 +9,8 @@ import string
from urllib.parse import urlencode
from datetime import datetime, timedelta
from searx import utils
# Engine metadata
about = {
"website": "https://www.bilibili.com",
@ -56,6 +58,8 @@ def request(query, params):
# Format the video duration
def format_duration(duration):
if not ":" in duration:
return None
minutes, seconds = map(int, duration.split(":"))
total_seconds = minutes * 60 + seconds
@ -70,7 +74,7 @@ def response(resp):
results = []
for item in search_res.get("data", {}).get("result", []):
title = item["title"]
title = utils.html_to_text(item["title"])
url = item["arcurl"]
thumbnail = item["pic"]
description = item["description"]

2
searx/engines/bing_images.py
View file

@ -99,7 +99,7 @@ def response(resp):
'url': metadata['purl'],
'thumbnail_src': metadata['turl'],
'img_src': metadata['murl'],
'content': metadata['desc'],
'content': metadata.get('desc'),
'title': title,
'source': source,
'resolution': img_format[0],

20
searx/engines/brave.py
View file

@ -123,7 +123,6 @@ from typing import Any, TYPE_CHECKING
from urllib.parse import (
urlencode,
urlparse,
parse_qs,
)
from dateutil import parser
@ -137,6 +136,7 @@ from searx.utils import (
eval_xpath_list,
eval_xpath_getindex,
js_variable_to_python,
get_embeded_stream_url,
)
from searx.enginelib.traits import EngineTraits
@ -311,7 +311,7 @@ def _parse_search(resp):
# In my tests a video tag in the WEB search was most often not a
# video, except the ones from youtube ..
iframe_src = _get_iframe_src(url)
iframe_src = get_embeded_stream_url(url)
if iframe_src:
item['iframe_src'] = iframe_src
item['template'] = 'videos.html'
@ -328,15 +328,6 @@ def _parse_search(resp):
return result_list
def _get_iframe_src(url):
parsed_url = urlparse(url)
if parsed_url.path == '/watch' and parsed_url.query:
video_id = parse_qs(parsed_url.query).get('v', []) # type: ignore
if video_id:
return 'https://www.youtube-nocookie.com/embed/' + video_id[0] # type: ignore
return None
def _parse_news(json_resp):
result_list = []
@ -392,7 +383,7 @@ def _parse_videos(json_resp):
if result['thumbnail'] is not None:
item['thumbnail'] = result['thumbnail']['src']
iframe_src = _get_iframe_src(url)
iframe_src = get_embeded_stream_url(url)
if iframe_src:
item['iframe_src'] = iframe_src
@ -430,7 +421,8 @@ def fetch_traits(engine_traits: EngineTraits):
ui_lang = option.get('value')
try:
if '-' in ui_lang and not ui_lang.startswith("zh-"):
l = babel.Locale.parse(ui_lang, sep='-')
if l.territory:
sxng_tag = region_tag(babel.Locale.parse(ui_lang, sep='-'))
else:
sxng_tag = language_tag(babel.Locale.parse(ui_lang, sep='-'))
@ -453,7 +445,7 @@ def fetch_traits(engine_traits: EngineTraits):
if not resp.ok: # type: ignore
print("ERROR: response from Brave is not OK.")
country_js = resp.text[resp.text.index("options:{all") + len('options:') :]
country_js = resp.text[resp.text.index("options:{all") + len('options:') :] # type: ignore
country_js = country_js[: country_js.index("},k={default")]
country_tags = js_variable_to_python(country_js)

1
searx/engines/btdigg.py
View file

@ -54,7 +54,6 @@ def response(resp):
excerpt = result.xpath('.//div[@class="torrent_excerpt"]')[0]
content = html.tostring(excerpt, encoding='unicode', method='text', with_tail=False)
# it is better to emit <br/> instead of |, but html tags are verboten
content = content.strip().replace('\n', ' | ')
content = ' '.join(content.split())

68
searx/engines/cloudflareai.py Normal file
View file

@ -0,0 +1,68 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Cloudflare AI engine"""
from json import loads, dumps
from searx.exceptions import SearxEngineAPIException
about = {
"website": 'https://ai.cloudflare.com',
"wikidata_id": None,
"official_api_documentation": 'https://developers.cloudflare.com/workers-ai',
"use_official_api": True,
"require_api_key": True,
"results": 'JSON',
}
cf_account_id = ''
cf_ai_api = ''
cf_ai_gateway = ''
cf_ai_model = ''
cf_ai_model_display_name = 'Cloudflare AI'
# Assistant messages hint to the AI about the desired output format. Not all models support this role.
cf_ai_model_assistant = 'Keep your answers as short and effective as possible.'
# System messages define the AI's personality. You can use them to set rules and how you expect the AI to behave.
cf_ai_model_system = 'You are a self-aware language model who is honest and direct about any question from the user.'
def request(query, params):
params['query'] = query
params['url'] = f'https://gateway.ai.cloudflare.com/v1/{cf_account_id}/{cf_ai_gateway}/workers-ai/{cf_ai_model}'
params['method'] = 'POST'
params['headers']['Authorization'] = f'Bearer {cf_ai_api}'
params['headers']['Content-Type'] = 'application/json'
params['data'] = dumps(
{
'messages': [
{'role': 'assistant', 'content': cf_ai_model_assistant},
{'role': 'system', 'content': cf_ai_model_system},
{'role': 'user', 'content': params['query']},
]
}
).encode('utf-8')
return params
def response(resp):
results = []
json = loads(resp.text)
if 'error' in json:
raise SearxEngineAPIException('Cloudflare AI error: ' + json['error'])
if 'result' in json:
results.append(
{
'content': json['result']['response'],
'infobox': cf_ai_model_display_name,
}
)
return results

217
searx/engines/duckduckgo.py
View file

@ -18,13 +18,13 @@ from searx import (
)
from searx.utils import (
eval_xpath,
eval_xpath_getindex,
extract_text,
)
from searx.network import get # see https://github.com/searxng/searxng/issues/762
from searx import redisdb
from searx.enginelib.traits import EngineTraits
from searx.utils import extr
from searx.exceptions import SearxEngineCaptchaException
if TYPE_CHECKING:
import logging
@ -53,31 +53,33 @@ paging = True
time_range_support = True
safesearch = True # user can't select but the results are filtered
url = 'https://lite.duckduckgo.com/lite/'
# url_ping = 'https://duckduckgo.com/t/sl_l'
url = "https://html.duckduckgo.com/html"
time_range_dict = {'day': 'd', 'week': 'w', 'month': 'm', 'year': 'y'}
form_data = {'v': 'l', 'api': 'd.js', 'o': 'json'}
__CACHE = []
def cache_vqd(query, value):
def _cache_key(data: dict):
return 'SearXNG_ddg_web_vqd' + redislib.secret_hash(f"{data['q']}//{data['kl']}")
def cache_vqd(data: dict, value):
"""Caches a ``vqd`` value from a query."""
c = redisdb.client()
if c:
logger.debug("cache vqd value: %s", value)
key = 'SearXNG_ddg_web_vqd' + redislib.secret_hash(query)
c.set(key, value, ex=600)
c.set(_cache_key(data), value, ex=600)
else:
logger.debug("MEM cache vqd value: %s", value)
if len(__CACHE) > 100: # cache vqd from last 100 queries
__CACHE.pop(0)
__CACHE.append((_cache_key(data), value))
def get_vqd(query):
"""Returns the ``vqd`` that fits to the *query*. If there is no ``vqd`` cached
(:py:obj:`cache_vqd`) the query is sent to DDG to get a vqd value from the
response.
.. hint::
If an empty string is returned there are no results for the ``query`` and
therefore no ``vqd`` value.
def get_vqd(data):
"""Returns the ``vqd`` that fits to the *query* (``data`` from HTTP POST).
DDG's bot detection is sensitive to the ``vqd`` value. For some search terms
(such as extremely long search terms that are often sent by bots), no ``vqd``
@ -105,28 +107,23 @@ def get_vqd(query):
- DuckDuckGo News: ``https://duckduckgo.com/news.js??q=...&vqd=...``
"""
key = _cache_key(data)
value = None
c = redisdb.client()
if c:
key = 'SearXNG_ddg_web_vqd' + redislib.secret_hash(query)
value = c.get(key)
if value or value == b'':
value = value.decode('utf-8')
logger.debug("re-use cached vqd value: %s", value)
logger.debug("re-use CACHED vqd value: %s", value)
return value
query_url = 'https://duckduckgo.com/?' + urlencode({'q': query})
res = get(query_url)
doc = lxml.html.fromstring(res.text)
for script in doc.xpath("//script[@type='text/javascript']"):
script = script.text
if 'vqd="' in script:
value = extr(script, 'vqd="', '"')
break
logger.debug("new vqd value: '%s'", value)
if value is not None:
cache_vqd(query, value)
return value
else:
for k, value in __CACHE:
if k == key:
logger.debug("MEM re-use CACHED vqd value: %s", value)
return value
return None
def get_ddg_lang(eng_traits: EngineTraits, sxng_locale, default='en_US'):
@ -154,9 +151,10 @@ def get_ddg_lang(eng_traits: EngineTraits, sxng_locale, default='en_US'):
.. hint::
`DDG-lite <https://lite.duckduckgo.com/lite>`__ does not offer a language
selection to the user, only a region can be selected by the user
(``eng_region`` from the example above). DDG-lite stores the selected
`DDG-lite <https://lite.duckduckgo.com/lite>`__ and the *no Javascript*
page https://html.duckduckgo.com/html do not offer a language selection
to the user, only a region can be selected by the user (``eng_region``
from the example above). DDG-lite and *no Javascript* store the selected
region in a cookie::
params['cookies']['kl'] = eng_region # 'ar-es'
@ -240,10 +238,25 @@ def request(query, params):
query = quote_ddg_bangs(query)
# request needs a vqd argument
vqd = get_vqd(query)
if len(query) >= 500:
# DDG does not accept queries with more than 499 chars
params["url"] = None
return
# Advanced search syntax ends in CAPTCHA
# https://duckduckgo.com/duckduckgo-help-pages/results/syntax/
query = [
x.removeprefix("site:").removeprefix("intitle:").removeprefix("inurl:").removeprefix("filetype:")
for x in query.split()
]
eng_region = traits.get_region(params['searxng_locale'], traits.all_locale)
if eng_region == "wt-wt":
# https://html.duckduckgo.com/html sets an empty value for "all".
eng_region = ""
params['data']['kl'] = eng_region
params['cookies']['kl'] = eng_region
# eng_lang = get_ddg_lang(traits, params['searxng_locale'])
params['url'] = url
@ -251,45 +264,82 @@ def request(query, params):
params['data']['q'] = query
# The API is not documented, so we do some reverse engineering and emulate
# what https://lite.duckduckgo.com/lite/ does when you press "next Page"
# link again and again ..
# what https://html.duckduckgo.com/html does when you press "next Page" link
# again and again ..
params['headers']['Content-Type'] = 'application/x-www-form-urlencoded'
params['data']['vqd'] = vqd
# initial page does not have an offset
params['headers']['Sec-Fetch-Dest'] = "document"
params['headers']['Sec-Fetch-Mode'] = "navigate" # at least this one is used by ddg's bot detection
params['headers']['Sec-Fetch-Site'] = "same-origin"
params['headers']['Sec-Fetch-User'] = "?1"
# Form of the initial search page does have empty values in the form
if params['pageno'] == 1:
params['data']['b'] = ""
params['data']['df'] = ''
if params['time_range'] in time_range_dict:
params['data']['df'] = time_range_dict[params['time_range']]
params['cookies']['df'] = time_range_dict[params['time_range']]
if params['pageno'] == 2:
# second page does have an offset of 20
offset = (params['pageno'] - 1) * 20
params['data']['s'] = offset
params['data']['dc'] = offset + 1
elif params['pageno'] > 2:
# third and following pages do have an offset of 20 + n*50
offset = 20 + (params['pageno'] - 2) * 50
params['data']['s'] = offset
params['data']['dc'] = offset + 1
# initial page does not have additional data in the input form
if params['pageno'] > 1:
# initial page does not have these additional data in the input form
params['data']['o'] = form_data.get('o', 'json')
params['data']['api'] = form_data.get('api', 'd.js')
params['data']['nextParams'] = form_data.get('nextParams', '')
params['data']['v'] = form_data.get('v', 'l')
params['headers']['Referer'] = 'https://lite.duckduckgo.com/'
params['headers']['Referer'] = url
params['data']['kl'] = eng_region
params['cookies']['kl'] = eng_region
# from here on no more params['data'] shuld be set, since this dict is
# needed to get a vqd value from the cache ..
params['data']['df'] = ''
if params['time_range'] in time_range_dict:
params['data']['df'] = time_range_dict[params['time_range']]
params['cookies']['df'] = time_range_dict[params['time_range']]
vqd = get_vqd(params['data'])
# Certain conditions must be met in order to call up one of the
# following pages ...
if vqd:
params['data']['vqd'] = vqd # follow up pages / requests needs a vqd argument
else:
# Don't try to call follow up pages without a vqd value. DDG
# recognizes this as a request from a bot. This lowers the
# reputation of the SearXNG IP and DDG starts to activate CAPTCHAs.
params["url"] = None
return
if params['searxng_locale'].startswith("zh"):
# Some locales (at least China) do not have a "next page" button and ddg
# will return a HTTP/2 403 Forbidden for a request of such a page.
params["url"] = None
return
logger.debug("param data: %s", params['data'])
logger.debug("param cookies: %s", params['cookies'])
return params
def is_ddg_captcha(dom):
"""In case of CAPTCHA ddg response its own *not a Robot* dialog and is not
redirected to a CAPTCHA page."""
return bool(eval_xpath(dom, "//form[@id='challenge-form']"))
def response(resp):
@ -300,35 +350,33 @@ def response(resp):
results = []
doc = lxml.html.fromstring(resp.text)
result_table = eval_xpath(doc, '//html/body/form/div[@class="filters"]/table')
if is_ddg_captcha(doc):
# set suspend time to zero is OK --> ddg does not block the IP
raise SearxEngineCaptchaException(suspended_time=0, message=f"CAPTCHA ({resp.search_params['data'].get('kl')})")
if len(result_table) == 2:
# some locales (at least China) does not have a "next page" button and
# the layout of the HTML tables is different.
result_table = result_table[1]
elif not len(result_table) >= 3:
# no more results
return []
else:
result_table = result_table[2]
# update form data from response
form = eval_xpath(doc, '//html/body/form/div[@class="filters"]/table//input/..')
if len(form):
form = eval_xpath(doc, '//input[@name="vqd"]/..')
if len(form):
# some locales (at least China) does not have a "next page" button
form = form[0]
form_vqd = eval_xpath(form, '//input[@name="vqd"]/@value')[0]
form = form[0]
form_data['v'] = eval_xpath(form, '//input[@name="v"]/@value')[0]
form_data['api'] = eval_xpath(form, '//input[@name="api"]/@value')[0]
form_data['o'] = eval_xpath(form, '//input[@name="o"]/@value')[0]
logger.debug('form_data: %s', form_data)
cache_vqd(resp.search_params["data"], form_vqd)
tr_rows = eval_xpath(result_table, './/tr')
# In the last <tr> is the form of the 'previous/next page' links
tr_rows = tr_rows[:-1]
# just select "web-result" and ignore results of class "result--ad result--ad--small"
for div_result in eval_xpath(doc, '//div[@id="links"]/div[contains(@class, "web-result")]'):
len_tr_rows = len(tr_rows)
offset = 0
item = {}
title = eval_xpath(div_result, './/h2/a')
if not title:
# this is the "No results." item in the result list
continue
item["title"] = extract_text(title)
item["url"] = eval_xpath(div_result, './/h2/a/@href')[0]
item["content"] = extract_text(eval_xpath(div_result, './/a[contains(@class, "result__snippet")]')[0])
zero_click_info_xpath = '//html/body/form/div/table[2]/tr[2]/td/text()'
results.append(item)
zero_click_info_xpath = '//div[@id="zero_click_abstract"]'
zero_click = extract_text(eval_xpath(doc, zero_click_info_xpath)).strip()
if zero_click and "Your IP address is" not in zero_click and "Your user agent:" not in zero_click:
@ -341,33 +389,6 @@ def response(resp):
}
)
while len_tr_rows >= offset + 4:
# assemble table rows we need to scrap
tr_title = tr_rows[offset]
tr_content = tr_rows[offset + 1]
offset += 4
# ignore sponsored Adds <tr class="result-sponsored">
if tr_content.get('class') == 'result-sponsored':
continue
a_tag = eval_xpath_getindex(tr_title, './/td//a[@class="result-link"]', 0, None)
if a_tag is None:
continue
td_content = eval_xpath_getindex(tr_content, './/td[@class="result-snippet"]', 0, None)
if td_content is None:
continue
results.append(
{
'title': a_tag.text_content(),
'content': extract_text(td_content),
'url': a_tag.get('href'),
}
)
return results

3
searx/engines/duckduckgo_extra.py
View file

@ -7,6 +7,7 @@ DuckDuckGo Extra (images, videos, news)
from datetime import datetime
from typing import TYPE_CHECKING
from urllib.parse import urlencode
from searx.utils import get_embeded_stream_url
from searx.engines.duckduckgo import fetch_traits # pylint: disable=unused-import
from searx.engines.duckduckgo import (
@ -108,7 +109,7 @@ def _video_result(result):
'title': result['title'],
'content': result['description'],
'thumbnail': result['images'].get('small') or result['images'].get('medium'),
'iframe_src': result['embed_url'],
'iframe_src': get_embeded_stream_url(result['content']),
'source': result['provider'],
'length': result['duration'],
'metadata': result.get('uploader'),

17
searx/engines/gitea.py
View file

@ -1,7 +1,8 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Engine to search in collaborative software platforms based on Gitea_.
"""Engine to search in collaborative software platforms based on Gitea_ or Forgejo_.
.. _Gitea: https://about.gitea.com/
.. _Forgejo: https://forgejo.org/
Configuration
=============
@ -23,6 +24,11 @@ Optional settings are:
base_url: https://gitea.com
shortcut: gitea
- name: forgejo.com
engine: gitea
base_url: https://code.forgejo.org
shortcut: forgejo
If you would like to use additional instances, just configure new engines in the
:ref:`settings <settings engine>` and set the ``base_url``.
@ -95,13 +101,14 @@ def response(resp):
'url': item.get('html_url'),
'title': item.get('full_name'),
'content': ' / '.join(content),
'img_src': item.get('owner', {}).get('avatar_url'),
# Use Repository Avatar and fall back to Owner Avatar if not set.
'thumbnail': item.get('avatar_url') or item.get('owner', {}).get('avatar_url'),
'package_name': item.get('name'),
'maintainer': item.get('owner', {}).get('login'),
'maintainer': item.get('owner', {}).get('username'),
'publishedDate': parser.parse(item.get("updated_at") or item.get("created_at")),
'tags': item.get('topics', []),
'popularity': item.get('stargazers_count'),
'homepage': item.get('homepage'),
'popularity': item.get('stars_count'),
'homepage': item.get('website'),
'source_code_url': item.get('clone_url'),
}
)

95
searx/engines/gitlab.py Normal file
View file

@ -0,0 +1,95 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Engine to search in collaborative software platforms based on GitLab_ with
the `GitLab REST API`_.
.. _GitLab: https://about.gitlab.com/install/
.. _GitLab REST API: https://docs.gitlab.com/ee/api/
Configuration
=============
The engine has the following mandatory setting:
- :py:obj:`base_url`
Optional settings are:
- :py:obj:`api_path`
.. code:: yaml
- name: gitlab
engine: gitlab
base_url: https://gitlab.com
shortcut: gl
about:
website: https://gitlab.com/
wikidata_id: Q16639197
- name: gnome
engine: gitlab
base_url: https://gitlab.gnome.org
shortcut: gn
about:
website: https://gitlab.gnome.org
wikidata_id: Q44316
Implementations
===============
"""
from urllib.parse import urlencode
from dateutil import parser
about = {
"website": None,
"wikidata_id": None,
"official_api_documentation": "https://docs.gitlab.com/ee/api/",
"use_official_api": True,
"require_api_key": False,
"results": "JSON",
}
categories = ['it', 'repos']
paging = True
base_url: str = ""
"""Base URL of the GitLab host."""
api_path: str = 'api/v4/projects'
"""The path the `project API <https://docs.gitlab.com/ee/api/projects.html>`_.
The default path should work fine usually.
"""
def request(query, params):
args = {'search': query, 'page': params['pageno']}
params['url'] = f"{base_url}/{api_path}?{urlencode(args)}"
return params
def response(resp):
results = []
for item in resp.json():
results.append(
{
'template': 'packages.html',
'url': item.get('web_url'),
'title': item.get('name'),
'content': item.get('description'),
'thumbnail': item.get('avatar_url'),
'package_name': item.get('name'),
'maintainer': item.get('namespace', {}).get('name'),
'publishedDate': parser.parse(item.get('last_activity_at') or item.get("created_at")),
'tags': item.get('tag_list', []),
'popularity': item.get('star_count'),
'homepage': item.get('readme_url'),
'source_code_url': item.get('http_url_to_repo'),
}
)
return results

4
searx/engines/google.py
View file

@ -62,7 +62,7 @@ filter_mapping = {0: 'off', 1: 'medium', 2: 'high'}
results_xpath = './/div[contains(@jscontroller, "SC7lYd")]'
title_xpath = './/a/h3[1]'
href_xpath = './/a[h3]/@href'
content_xpath = './/div[@data-sncf="1"]'
content_xpath = './/div[contains(@data-sncf, "1")]'
# Suggestions are links placed in a *card-section*, we extract only the text
# from the links not the links itself.
@ -441,7 +441,7 @@ def fetch_traits(engine_traits: EngineTraits, add_domains: bool = True):
try:
locale = babel.Locale.parse(lang_map.get(eng_lang, eng_lang), sep='-')
except babel.UnknownLocaleError:
print("ERROR: %s -> %s is unknown by babel" % (x.get("data-name"), eng_lang))
print("INFO: google UI language %s (%s) is unknown by babel" % (eng_lang, x.text.split("(")[0].strip()))
continue
sxng_lang = language_tag(locale)

2
searx/engines/google_videos.py
View file

@ -34,6 +34,7 @@ from searx.engines.google import (
detect_google_sorry,
)
from searx.enginelib.traits import EngineTraits
from searx.utils import get_embeded_stream_url
if TYPE_CHECKING:
import logging
@ -125,6 +126,7 @@ def response(resp):
'content': content,
'author': pub_info,
'thumbnail': thumbnail,
'iframe_src': get_embeded_stream_url(url),
'template': 'videos.html',
}
)

6
searx/engines/hackernews.py
View file

@ -57,7 +57,11 @@ def request(query, params):
if params['time_range']:
search_type = 'search_by_date'
timestamp = (datetime.now() - relativedelta(**{f"{params['time_range']}s": 1})).timestamp()
timestamp = (
# pylint: disable=unexpected-keyword-arg
datetime.now()
- relativedelta(**{f"{params['time_range']}s": 1}) # type: ignore
).timestamp()
query_params["numericFilters"] = f"created_at_i>{timestamp}"
params["url"] = f"{base_url}/{search_type}?{urlencode(query_params)}"

6
searx/engines/json_engine.py
View file

@ -146,7 +146,11 @@ def response(resp):
}
)
else:
for url, title, content in zip(query(json, url_query), query(json, title_query), query(json, content_query)):
for result in json:
url = query(result, url_query)[0]
title = query(result, title_query)[0]
content = query(result, content_query)[0]
results.append(
{
'url': url_prefix + to_string(url),

95
searx/engines/mariadb_server.py Normal file
View file

@ -0,0 +1,95 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""MariaDB is a community driven fork of MySQL. Before enabling MariaDB engine,
you must the install the pip package ``mariadb`` along with the necessary
prerequities.
`See the following documentation for more details
<https://mariadb.com/docs/server/connect/programming-languages/c/install/>`_
Example
=======
This is an example configuration for querying a MariaDB server:
.. code:: yaml
- name: my_database
engine: mariadb_server
database: my_database
username: searxng
password: password
limit: 5
query_str: 'SELECT * from my_table WHERE my_column=%(query)s'
Implementations
===============
"""
from typing import TYPE_CHECKING
try:
import mariadb
except ImportError:
# import error is ignored because the admin has to install mysql manually to use
# the engine
pass
if TYPE_CHECKING:
import logging
logger = logging.getLogger()
engine_type = 'offline'
host = "127.0.0.1"
"""Hostname of the DB connector"""
port = 3306
"""Port of the DB connector"""
database = ""
"""Name of the database."""
username = ""
"""Username for the DB connection."""
password = ""
"""Password for the DB connection."""
query_str = ""
"""SQL query that returns the result items."""
limit = 10
paging = True
result_template = 'key-value.html'
_connection = None
def init(engine_settings):
global _connection # pylint: disable=global-statement
if 'query_str' not in engine_settings:
raise ValueError('query_str cannot be empty')
if not engine_settings['query_str'].lower().startswith('select '):
raise ValueError('only SELECT query is supported')
_connection = mariadb.connect(database=database, user=username, password=password, host=host, port=port)
def search(query, params):
query_params = {'query': query}
query_to_run = query_str + ' LIMIT {0} OFFSET {1}'.format(limit, (params['pageno'] - 1) * limit)
logger.debug("SQL Query: %s", query_to_run)
with _connection.cursor() as cur:
cur.execute(query_to_run, query_params)
results = []
col_names = [i[0] for i in cur.description]
for res in cur:
result = dict(zip(col_names, map(str, res)))
result['template'] = result_template
results.append(result)
return results

50
searx/engines/mojeek.py
View file

@ -1,12 +1,15 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Mojeek (general, images, news)"""
from typing import TYPE_CHECKING
from datetime import datetime
from urllib.parse import urlencode
from lxml import html
from dateutil.relativedelta import relativedelta
from searx.utils import eval_xpath, eval_xpath_list, extract_text
from searx.enginelib.traits import EngineTraits
about = {
'website': 'https://mojeek.com',
@ -42,6 +45,18 @@ news_url_xpath = './/h2/a/@href'
news_title_xpath = './/h2/a'
news_content_xpath = './/p[@class="s"]'
language_param = 'lb'
region_param = 'arc'
_delta_kwargs = {'day': 'days', 'week': 'weeks', 'month': 'months', 'year': 'years'}
if TYPE_CHECKING:
import logging
logger = logging.getLogger()
traits: EngineTraits
def init(_):
if search_type not in ('', 'images', 'news'):
@ -53,13 +68,16 @@ def request(query, params):
'q': query,
'safe': min(params['safesearch'], 1),
'fmt': search_type,
language_param: traits.get_language(params['searxng_locale'], traits.custom['language_all']),
region_param: traits.get_region(params['searxng_locale'], traits.custom['region_all']),
}
if search_type == '':
args['s'] = 10 * (params['pageno'] - 1)
if params['time_range'] and search_type != 'images':
args["since"] = (datetime.now() - relativedelta(**{f"{params['time_range']}s": 1})).strftime("%Y%m%d")
kwargs = {_delta_kwargs[params['time_range']]: 1}
args["since"] = (datetime.now() - relativedelta(**kwargs)).strftime("%Y%m%d") # type: ignore
logger.debug(args["since"])
params['url'] = f"{base_url}/search?{urlencode(args)}"
@ -94,7 +112,7 @@ def _image_results(dom):
'template': 'images.html',
'url': extract_text(eval_xpath(result, image_url_xpath)),
'title': extract_text(eval_xpath(result, image_title_xpath)),
'img_src': base_url + extract_text(eval_xpath(result, image_img_src_xpath)),
'img_src': base_url + extract_text(eval_xpath(result, image_img_src_xpath)), # type: ignore
'content': '',
}
)
@ -130,3 +148,31 @@ def response(resp):
return _news_results(dom)
raise ValueError(f"Invalid search type {search_type}")
def fetch_traits(engine_traits: EngineTraits):
# pylint: disable=import-outside-toplevel
from searx import network
from searx.locales import get_official_locales, region_tag
from babel import Locale, UnknownLocaleError
import contextlib
resp = network.get(base_url + "/preferences", headers={'Accept-Language': 'en-US,en;q=0.5'})
dom = html.fromstring(resp.text) # type: ignore
languages = eval_xpath_list(dom, f'//select[@name="{language_param}"]/option/@value')
engine_traits.custom['language_all'] = languages[0]
for code in languages[1:]:
with contextlib.suppress(UnknownLocaleError):
locale = Locale(code)
engine_traits.languages[locale.language] = code
regions = eval_xpath_list(dom, f'//select[@name="{region_param}"]/option/@value')
engine_traits.custom['region_all'] = regions[1]
for code in regions[2:]:
for locale in get_official_locales(code, engine_traits.languages):
engine_traits.regions[region_tag(locale)] = code

13
searx/engines/mysql_server.py
View file

@ -34,12 +34,25 @@ except ImportError:
engine_type = 'offline'
auth_plugin = 'caching_sha2_password'
host = "127.0.0.1"
"""Hostname of the DB connector"""
port = 3306
"""Port of the DB connector"""
database = ""
"""Name of the database."""
username = ""
"""Username for the DB connection."""
password = ""
"""Password for the DB connection."""
query_str = ""
"""SQL query that returns the result items."""
limit = 10
paging = True
result_template = 'key-value.html'

71
searx/engines/openlibrary.py Normal file
View file

@ -0,0 +1,71 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Open library (books)
"""
from urllib.parse import urlencode
import re
from dateutil import parser
about = {
'website': 'https://openlibrary.org',
'wikidata_id': 'Q1201876',
'require_api_key': False,
'use_official_api': False,
'official_api_documentation': 'https://openlibrary.org/developers/api',
}
paging = True
categories = []
base_url = "https://openlibrary.org"
results_per_page = 10
def request(query, params):
args = {
'q': query,
'page': params['pageno'],
'limit': results_per_page,
}
params['url'] = f"{base_url}/search.json?{urlencode(args)}"
return params
def _parse_date(date):
try:
return parser.parse(date)
except parser.ParserError:
return None
def response(resp):
results = []
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')
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')))
result = {
'template': 'paper.html',
'url': f"{base_url}{item['key']}",
'title': item['title'],
'content': re.sub(r"\{|\}", "", item['first_sentence'][0]) if item.get('first_sentence') else '',
'isbn': item.get('isbn', [])[:5],
'authors': item.get('author_name', []),
'thumbnail': cover,
'publishedDate': published,
'tags': item.get('subject', [])[:10] + item.get('place', [])[:10],
}
results.append(result)
return results

13
searx/engines/postgresql.py
View file

@ -29,12 +29,25 @@ except ImportError:
pass
engine_type = 'offline'
host = "127.0.0.1"
"""Hostname of the DB connector"""
port = "5432"
"""Port of the DB connector"""
database = ""
"""Name of the database."""
username = ""
"""Username for the DB connection."""
password = ""
"""Password for the DB connection."""
query_str = ""
"""SQL query that returns the result items."""
limit = 10
paging = True
result_template = 'key-value.html'

10
searx/engines/qwant.py
View file

@ -49,7 +49,11 @@ from flask_babel import gettext
import babel
import lxml
from searx.exceptions import SearxEngineAPIException, SearxEngineTooManyRequestsException
from searx.exceptions import (
SearxEngineAPIException,
SearxEngineTooManyRequestsException,
SearxEngineCaptchaException,
)
from searx.network import raise_for_httperror
from searx.enginelib.traits import EngineTraits
@ -57,6 +61,7 @@ from searx.utils import (
eval_xpath,
eval_xpath_list,
extract_text,
get_embeded_stream_url,
)
traits: EngineTraits
@ -187,6 +192,8 @@ def parse_web_api(resp):
error_code = data.get('error_code')
if error_code == 24:
raise SearxEngineTooManyRequestsException()
if search_results.get("data", {}).get("error_data", {}).get("captchaUrl") is not None:
raise SearxEngineCaptchaException()
msg = ",".join(data.get('message', ['unknown']))
raise SearxEngineAPIException(f"{msg} ({error_code})")
@ -297,6 +304,7 @@ def parse_web_api(resp):
'title': title,
'url': res_url,
'content': content,
'iframe_src': get_embeded_stream_url(res_url),
'publishedDate': pub_date,
'thumbnail': thumbnail,
'template': 'videos.html',

6
searx/engines/radio_browser.py
View file

@ -165,10 +165,12 @@ def fetch_traits(engine_traits: EngineTraits):
countrycodes = set()
for region in country_list:
if region['iso_3166_1'] not in babel_reg_list:
# country_list contains duplicates that differ only in upper/lower case
_reg = region['iso_3166_1'].upper()
if _reg not in babel_reg_list:
print(f"ERROR: region tag {region['iso_3166_1']} is unknown by babel")
continue
countrycodes.add(region['iso_3166_1'])
countrycodes.add(_reg)
countrycodes = list(countrycodes)
countrycodes.sort()

5
searx/engines/sqlite.py
View file

@ -41,8 +41,13 @@ import sqlite3
import contextlib
engine_type = 'offline'
database = ""
"""Filename of the SQLite DB."""
query_str = ""
"""SQL query that returns the result items."""
limit = 10
paging = True
result_template = 'key-value.html'

36
searx/engines/stract.py
View file

@ -7,6 +7,7 @@ ends.
from json import dumps
from searx.utils import searx_useragent
from searx.enginelib.traits import EngineTraits
about = {
"website": "https://stract.com/",
@ -18,7 +19,10 @@ about = {
categories = ['general']
paging = True
search_url = "https://stract.com/beta/api/search"
base_url = "https://stract.com/beta/api"
search_url = base_url + "/search"
traits: EngineTraits
def request(query, params):
@ -29,7 +33,14 @@ def request(query, params):
'Content-Type': 'application/json',
'User-Agent': searx_useragent(),
}
params['data'] = dumps({'query': query, 'page': params['pageno'] - 1})
region = traits.get_region(params["searxng_locale"], default=traits.all_locale)
params['data'] = dumps(
{
'query': query,
'page': params['pageno'] - 1,
'selectedRegion': region,
}
)
return params
@ -47,3 +58,24 @@ def response(resp):
)
return results
def fetch_traits(engine_traits: EngineTraits):
# pylint: disable=import-outside-toplevel
from searx import network
from babel import Locale, languages
from searx.locales import region_tag
territories = Locale("en").territories
json = network.get(base_url + "/docs/openapi.json").json()
regions = json['components']['schemas']['Region']['enum']
engine_traits.all_locale = regions[0]
for region in regions[1:]:
for code, name in territories.items():
if region not in (code, name):
continue
for lang in languages.get_official_languages(code, de_facto=True):
engine_traits.regions[region_tag(Locale(lang, code))] = region

15
searx/engines/yahoo.py
View file

@ -16,6 +16,7 @@ from searx.utils import (
eval_xpath_getindex,
eval_xpath_list,
extract_text,
html_to_text,
)
from searx.enginelib.traits import EngineTraits
@ -133,12 +134,20 @@ def response(resp):
url = parse_url(url)
title = eval_xpath_getindex(result, './/h3//a/@aria-label', 0, default='')
title = extract_text(title)
title: str = extract_text(title)
content = eval_xpath_getindex(result, './/div[contains(@class, "compText")]', 0, default='')
content = extract_text(content, allow_none=True)
content: str = extract_text(content, allow_none=True)
# append result
results.append({'url': url, 'title': title, 'content': content})
results.append(
{
'url': url,
# title sometimes contains HTML tags / see
# https://github.com/searxng/searxng/issues/3790
'title': " ".join(html_to_text(title).strip().split()),
'content': " ".join(html_to_text(content).strip().split()),
}
)
for suggestion in eval_xpath_list(dom, '//div[contains(@class, "AlsoTry")]//table//a'):
# append suggestion

2
searx/engines/yep.py
View file

@ -67,6 +67,8 @@ def response(resp):
for result in resp.json()[1]['results']:
if search_type == "web":
if result['type'] != 'Organic':
continue
results.append(_web_result(result))
elif search_type == "images":
results.append(_images_result(result))

12
searx/exceptions.py
View file

@ -1,6 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Exception types raised by SearXNG modules.
"""
from __future__ import annotations
from typing import Optional, Union
@ -61,7 +62,7 @@ class SearxEngineAccessDeniedException(SearxEngineResponseException):
"""This settings contains the default suspended time (default 86400 sec / 1
day)."""
def __init__(self, suspended_time: int = None, message: str = 'Access denied'):
def __init__(self, suspended_time: int | None = None, message: str = 'Access denied'):
"""Generic exception to raise when an engine denies access to the results.
:param suspended_time: How long the engine is going to be suspended in
@ -70,12 +71,13 @@ class SearxEngineAccessDeniedException(SearxEngineResponseException):
:param message: Internal message. Defaults to ``Access denied``
:type message: str
"""
suspended_time = suspended_time or self._get_default_suspended_time()
if suspended_time is None:
suspended_time = self._get_default_suspended_time()
super().__init__(message + ', suspended_time=' + str(suspended_time))
self.suspended_time = suspended_time
self.message = message
def _get_default_suspended_time(self):
def _get_default_suspended_time(self) -> int:
from searx import get_setting # pylint: disable=C0415
return get_setting(self.SUSPEND_TIME_SETTING)
@ -88,7 +90,7 @@ class SearxEngineCaptchaException(SearxEngineAccessDeniedException):
"""This settings contains the default suspended time (default 86400 sec / 1
day)."""
def __init__(self, suspended_time=None, message='CAPTCHA'):
def __init__(self, suspended_time: int | None = None, message='CAPTCHA'):
super().__init__(message=message, suspended_time=suspended_time)
@ -102,7 +104,7 @@ class SearxEngineTooManyRequestsException(SearxEngineAccessDeniedException):
"""This settings contains the default suspended time (default 3660 sec / 1
hour)."""
def __init__(self, suspended_time=None, message='Too many request'):
def __init__(self, suspended_time: int | None = None, message='Too many request'):
super().__init__(message=message, suspended_time=suspended_time)

38
searx/favicons/__init__.py Normal file
View file

@ -0,0 +1,38 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementations for providing the favicons in SearXNG"""
from __future__ import annotations
__all__ = ["init", "favicon_url", "favicon_proxy"]
import pathlib
from searx import logger
from searx import get_setting
from .proxy import favicon_url, favicon_proxy
logger = logger.getChild('favicons')
def is_active():
return bool(get_setting("search.favicon_resolver", False))
def init():
# pylint: disable=import-outside-toplevel
from . import config, cache, proxy
from .. import settings_loader
cfg_file = (settings_loader.get_user_cfg_folder() or pathlib.Path("/etc/searxng")) / "favicons.toml"
if not cfg_file.exists():
if is_active():
logger.error(f"missing favicon config: {cfg_file}")
cfg_file = config.DEFAULT_CFG_TOML_PATH
logger.debug(f"load favicon config: {cfg_file}")
cfg = config.FaviconConfig.from_toml_file(cfg_file, use_cache=True)
cache.init(cfg.cache)
proxy.init(cfg.proxy)
del cache, config, proxy, cfg, settings_loader

12
searx/favicons/__main__.py Normal file
View file

@ -0,0 +1,12 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Command line implementation"""
import typer
from . import cache
from . import init
init()
app = typer.Typer()
app.add_typer(cache.app, name="cache", help="commands related to the cache")
app()

476
searx/favicons/cache.py Normal file
View file

@ -0,0 +1,476 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementations for caching favicons.
:py:obj:`FaviconCacheConfig`:
Configuration of the favicon cache
:py:obj:`FaviconCache`:
Abstract base class for the implementation of a favicon cache.
:py:obj:`FaviconCacheSQLite`:
Favicon cache that manages the favicon BLOBs in a SQLite DB.
:py:obj:`FaviconCacheNull`:
Fallback solution if the configured cache cannot be used for system reasons.
----
"""
from __future__ import annotations
from typing import Literal
import os
import abc
import dataclasses
import hashlib
import logging
import sqlite3
import tempfile
import time
import typer
import msgspec
from searx import sqlitedb
from searx import logger
from searx.utils import humanize_bytes, humanize_number
CACHE: "FaviconCache"
FALLBACK_ICON = b"FALLBACK_ICON"
logger = logger.getChild('favicons.cache')
app = typer.Typer()
@app.command()
def state():
"""show state of the cache"""
print(CACHE.state().report())
@app.command()
def maintenance(force: bool = True, debug: bool = False):
"""perform maintenance of the cache"""
root_log = logging.getLogger()
if debug:
root_log.setLevel(logging.DEBUG)
else:
root_log.handlers = []
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter("%(message)s"))
logger.addHandler(handler)
logger.setLevel(logging.DEBUG)
state_t0 = CACHE.state()
CACHE.maintenance(force=force)
state_t1 = CACHE.state()
state_delta = state_t0 - state_t1
print("The cache has been reduced by:")
print(state_delta.report("\n- {descr}: {val}").lstrip("\n"))
def init(cfg: "FaviconCacheConfig"):
"""Initialization of a global ``CACHE``"""
global CACHE # pylint: disable=global-statement
if cfg.db_type == "sqlite":
if sqlite3.sqlite_version_info <= (3, 35):
logger.critical(
"Disable favicon caching completely: SQLite library (%s) is too old! (require >= 3.35)",
sqlite3.sqlite_version,
)
CACHE = FaviconCacheNull(cfg)
else:
CACHE = FaviconCacheSQLite(cfg)
elif cfg.db_type == "mem":
logger.error("Favicons are cached in memory, don't use this in production!")
CACHE = FaviconCacheMEM(cfg)
else:
raise NotImplementedError(f"favicons db_type '{cfg.db_type}' is unknown")
class FaviconCacheConfig(msgspec.Struct): # pylint: disable=too-few-public-methods
"""Configuration of the favicon cache."""
db_type: Literal["sqlite", "mem"] = "sqlite"
"""Type of the database:
``sqlite``:
:py:obj:`.cache.FaviconCacheSQLite`
``mem``:
:py:obj:`.cache.FaviconCacheMEM` (not recommended)
"""
db_url: str = tempfile.gettempdir() + os.sep + "faviconcache.db"
"""URL of the SQLite DB, the path to the database file."""
HOLD_TIME: int = 60 * 60 * 24 * 30 # 30 days
"""Hold time (default in sec.), after which a BLOB is removed from the cache."""
LIMIT_TOTAL_BYTES: int = 1024 * 1024 * 50 # 50 MB
"""Maximum of bytes (default) stored in the cache of all blobs. Note: The
limit is only reached at each maintenance interval after which the oldest
BLOBs are deleted; the limit is exceeded during the maintenance period. If
the maintenance period is *too long* or maintenance is switched off
completely, the cache grows uncontrollably."""
BLOB_MAX_BYTES: int = 1024 * 20 # 20 KB
"""The maximum BLOB size in bytes that a favicon may have so that it can be
saved in the cache. If the favicon is larger, it is not saved in the cache
and must be requested by the client via the proxy."""
MAINTENANCE_PERIOD: int = 60 * 60
"""Maintenance period in seconds / when :py:obj:`MAINTENANCE_MODE` is set to
``auto``."""
MAINTENANCE_MODE: Literal["auto", "off"] = "auto"
"""Type of maintenance mode
``auto``:
Maintenance is carried out automatically as part of the maintenance
intervals (:py:obj:`MAINTENANCE_PERIOD`); no external process is required.
``off``:
Maintenance is switched off and must be carried out by an external process
if required.
"""
@dataclasses.dataclass
class FaviconCacheStats:
"""Dataclass wich provides information on the status of the cache."""
favicons: int | None = None
bytes: int | None = None
domains: int | None = None
resolvers: int | None = None
field_descr = (
("favicons", "number of favicons in cache", humanize_number),
("bytes", "total size (approx. bytes) of cache", humanize_bytes),
("domains", "total number of domains in cache", humanize_number),
("resolvers", "number of resolvers", str),
)
def __sub__(self, other) -> FaviconCacheStats:
if not isinstance(other, self.__class__):
raise TypeError(f"unsupported operand type(s) for +: '{self.__class__}' and '{type(other)}'")
kwargs = {}
for field, _, _ in self.field_descr:
self_val, other_val = getattr(self, field), getattr(other, field)
if None in (self_val, other_val):
continue
if isinstance(self_val, int):
kwargs[field] = self_val - other_val
else:
kwargs[field] = self_val
return self.__class__(**kwargs)
def report(self, fmt: str = "{descr}: {val}\n"):
s = []
for field, descr, cast in self.field_descr:
val = getattr(self, field)
if val is None:
val = "--"
else:
val = cast(val)
s.append(fmt.format(descr=descr, val=val))
return "".join(s)
class FaviconCache(abc.ABC):
"""Abstract base class for the implementation of a favicon cache."""
@abc.abstractmethod
def __init__(self, cfg: FaviconCacheConfig):
"""An instance of the favicon cache is build up from the configuration."""
@abc.abstractmethod
def __call__(self, resolver: str, authority: str) -> None | tuple[None | bytes, None | str]:
"""Returns ``None`` or the tuple of ``(data, mime)`` that has been
registered in the cache. The ``None`` indicates that there was no entry
in the cache."""
@abc.abstractmethod
def set(self, resolver: str, authority: str, mime: str | None, data: bytes | None) -> bool:
"""Set data and mime-type in the cache. If data is None, the
:py:obj:`FALLBACK_ICON` is registered. in the cache."""
@abc.abstractmethod
def state(self) -> FaviconCacheStats:
"""Returns a :py:obj:`FaviconCacheStats` (key/values) with information
on the state of the cache."""
@abc.abstractmethod
def maintenance(self, force=False):
"""Performs maintenance on the cache"""
class FaviconCacheNull(FaviconCache):
"""A dummy favicon cache that caches nothing / a fallback solution. The
NullCache is used when more efficient caches such as the
:py:obj:`FaviconCacheSQLite` cannot be used because, for example, the SQLite
library is only available in an old version and does not meet the
requirements."""
def __init__(self, cfg: FaviconCacheConfig):
return None
def __call__(self, resolver: str, authority: str) -> None | tuple[None | bytes, None | str]:
return None
def set(self, resolver: str, authority: str, mime: str | None, data: bytes | None) -> bool:
return False
def state(self):
return FaviconCacheStats(favicons=0)
def maintenance(self, force=False):
pass
class FaviconCacheSQLite(sqlitedb.SQLiteAppl, FaviconCache):
"""Favicon cache that manages the favicon BLOBs in a SQLite DB. The DB
model in the SQLite DB is implemented using the abstract class
:py:obj:`sqlitedb.SQLiteAppl`.
The following configurations are required / supported:
- :py:obj:`FaviconCacheConfig.db_url`
- :py:obj:`FaviconCacheConfig.HOLD_TIME`
- :py:obj:`FaviconCacheConfig.LIMIT_TOTAL_BYTES`
- :py:obj:`FaviconCacheConfig.BLOB_MAX_BYTES`
- :py:obj:`MAINTENANCE_PERIOD`
- :py:obj:`MAINTENANCE_MODE`
"""
DB_SCHEMA = 1
DDL_BLOBS = """\
CREATE TABLE IF NOT EXISTS blobs (
sha256 TEXT,
bytes_c INTEGER,
mime TEXT NOT NULL,
data BLOB NOT NULL,
PRIMARY KEY (sha256))"""
"""Table to store BLOB objects by their sha256 hash values."""
DDL_BLOB_MAP = """\
CREATE TABLE IF NOT EXISTS blob_map (
m_time INTEGER DEFAULT (strftime('%s', 'now')), -- last modified (unix epoch) time in sec.
sha256 TEXT,
resolver TEXT,
authority TEXT,
PRIMARY KEY (resolver, authority))"""
"""Table to map from (resolver, authority) to sha256 hash values."""
DDL_CREATE_TABLES = {
"blobs": DDL_BLOBS,
"blob_map": DDL_BLOB_MAP,
}
SQL_DROP_LEFTOVER_BLOBS = (
"DELETE FROM blobs WHERE sha256 IN ("
" SELECT b.sha256"
" FROM blobs b"
" LEFT JOIN blob_map bm"
" ON b.sha256 = bm.sha256"
" WHERE bm.sha256 IS NULL)"
)
"""Delete blobs.sha256 (BLOBs) no longer in blob_map.sha256."""
SQL_ITER_BLOBS_SHA256_BYTES_C = (
"SELECT b.sha256, b.bytes_c FROM blobs b"
" JOIN blob_map bm "
" ON b.sha256 = bm.sha256"
" ORDER BY bm.m_time ASC"
)
SQL_INSERT_BLOBS = (
"INSERT INTO blobs (sha256, bytes_c, mime, data) VALUES (?, ?, ?, ?)"
" ON CONFLICT (sha256) DO NOTHING"
) # fmt: skip
SQL_INSERT_BLOB_MAP = (
"INSERT INTO blob_map (sha256, resolver, authority) VALUES (?, ?, ?)"
" ON CONFLICT DO UPDATE "
" SET sha256=excluded.sha256, m_time=strftime('%s', 'now')"
)
def __init__(self, cfg: FaviconCacheConfig):
"""An instance of the favicon cache is build up from the configuration.""" #
if cfg.db_url == ":memory:":
logger.critical("don't use SQLite DB in :memory: in production!!")
super().__init__(cfg.db_url)
self.cfg = cfg
def __call__(self, resolver: str, authority: str) -> None | tuple[None | bytes, None | str]:
sql = "SELECT sha256 FROM blob_map WHERE resolver = ? AND authority = ?"
res = self.DB.execute(sql, (resolver, authority)).fetchone()
if res is None:
return None
data, mime = (None, None)
sha256 = res[0]
if sha256 == FALLBACK_ICON:
return data, mime
sql = "SELECT data, mime FROM blobs WHERE sha256 = ?"
res = self.DB.execute(sql, (sha256,)).fetchone()
if res is not None:
data, mime = res
return data, mime
def set(self, resolver: str, authority: str, mime: str | None, data: bytes | None) -> bool:
if self.cfg.MAINTENANCE_MODE == "auto" and int(time.time()) > self.next_maintenance_time:
# Should automatic maintenance be moved to a new thread?
self.maintenance()
if data is not None and mime is None:
logger.error(
"favicon resolver %s tries to cache mime-type None for authority %s",
resolver,
authority,
)
return False
bytes_c = len(data or b"")
if bytes_c > self.cfg.BLOB_MAX_BYTES:
logger.info(
"favicon of resolver: %s / authority: %s to big to cache (bytes: %s) " % (resolver, authority, bytes_c)
)
return False
if data is None:
sha256 = FALLBACK_ICON
else:
sha256 = hashlib.sha256(data).hexdigest()
with self.connect() as conn:
if sha256 != FALLBACK_ICON:
conn.execute(self.SQL_INSERT_BLOBS, (sha256, bytes_c, mime, data))
conn.execute(self.SQL_INSERT_BLOB_MAP, (sha256, resolver, authority))
return True
@property
def next_maintenance_time(self) -> int:
"""Returns (unix epoch) time of the next maintenance."""
return self.cfg.MAINTENANCE_PERIOD + self.properties.m_time("LAST_MAINTENANCE")
def maintenance(self, force=False):
# Prevent parallel DB maintenance cycles from other DB connections
# (e.g. in multi thread or process environments).
if not force and int(time.time()) < self.next_maintenance_time:
logger.debug("no maintenance required yet, next maintenance interval is in the future")
return
self.properties.set("LAST_MAINTENANCE", "") # hint: this (also) sets the m_time of the property!
# do maintenance tasks
with self.connect() as conn:
# drop items not in HOLD time
res = conn.execute(
f"DELETE FROM blob_map"
f" WHERE cast(m_time as integer) < cast(strftime('%s', 'now') as integer) - {self.cfg.HOLD_TIME}"
)
logger.debug("dropped %s obsolete blob_map items from db", res.rowcount)
res = conn.execute(self.SQL_DROP_LEFTOVER_BLOBS)
logger.debug("dropped %s obsolete BLOBS from db", res.rowcount)
# drop old items to be in LIMIT_TOTAL_BYTES
total_bytes = conn.execute("SELECT SUM(bytes_c) FROM blobs").fetchone()[0] or 0
if total_bytes > self.cfg.LIMIT_TOTAL_BYTES:
x = total_bytes - self.cfg.LIMIT_TOTAL_BYTES
c = 0
sha_list = []
for row in conn.execute(self.SQL_ITER_BLOBS_SHA256_BYTES_C):
sha256, bytes_c = row
sha_list.append(sha256)
c += bytes_c
if c > x:
break
if sha_list:
conn.execute("DELETE FROM blobs WHERE sha256 IN ('%s')" % "','".join(sha_list))
conn.execute("DELETE FROM blob_map WHERE sha256 IN ('%s')" % "','".join(sha_list))
logger.debug("dropped %s blobs with total size of %s bytes", len(sha_list), c)
def _query_val(self, sql, default=None):
val = self.DB.execute(sql).fetchone()
if val is not None:
val = val[0]
if val is None:
val = default
return val
def state(self) -> FaviconCacheStats:
return FaviconCacheStats(
favicons=self._query_val("SELECT count(*) FROM blobs", 0),
bytes=self._query_val("SELECT SUM(bytes_c) FROM blobs", 0),
domains=self._query_val("SELECT count(*) FROM (SELECT authority FROM blob_map GROUP BY authority)", 0),
resolvers=self._query_val("SELECT count(*) FROM (SELECT resolver FROM blob_map GROUP BY resolver)", 0),
)
class FaviconCacheMEM(FaviconCache):
"""Favicon cache in process' memory. Its just a POC that stores the
favicons in the memory of the process.
.. attention::
Don't use it in production, it will blow up your memory!!
"""
def __init__(self, cfg):
self.cfg = cfg
self._data = {}
self._sha_mime = {}
def __call__(self, resolver: str, authority: str) -> None | tuple[bytes | None, str | None]:
sha, mime = self._sha_mime.get(f"{resolver}:{authority}", (None, None))
if sha is None:
return None
data = self._data.get(sha)
if data == FALLBACK_ICON:
data = None
return data, mime
def set(self, resolver: str, authority: str, mime: str | None, data: bytes | None) -> bool:
if data is None:
data = FALLBACK_ICON
mime = None
elif mime is None:
logger.error(
"favicon resolver %s tries to cache mime-type None for authority %s",
resolver,
authority,
)
return False
digest = hashlib.sha256(data).hexdigest()
self._data[digest] = data
self._sha_mime[f"{resolver}:{authority}"] = (digest, mime)
return True
def state(self):
return FaviconCacheStats(favicons=len(self._data.keys()))
def maintenance(self, force=False):
pass

65
searx/favicons/config.py Normal file
View file

@ -0,0 +1,65 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# pylint: disable=missing-module-docstring
from __future__ import annotations
import pathlib
import msgspec
from .cache import FaviconCacheConfig
from .proxy import FaviconProxyConfig
CONFIG_SCHEMA: int = 1
"""Version of the configuration schema."""
TOML_CACHE_CFG: dict[str, "FaviconConfig"] = {}
"""Cache config objects by TOML's filename."""
DEFAULT_CFG_TOML_PATH = pathlib.Path(__file__).parent / "favicons.toml"
class FaviconConfig(msgspec.Struct): # pylint: disable=too-few-public-methods
"""The class aggregates configurations of the favicon tools"""
cfg_schema: int
"""Config's schema version. The specification of the version of the schema
is mandatory, currently only version :py:obj:`CONFIG_SCHEMA` is supported.
By specifying a version, it is possible to ensure downward compatibility in
the event of future changes to the configuration schema"""
cache: FaviconCacheConfig = msgspec.field(default_factory=FaviconCacheConfig)
"""Setup of the :py:obj:`.cache.FaviconCacheConfig`."""
proxy: FaviconProxyConfig = msgspec.field(default_factory=FaviconProxyConfig)
"""Setup of the :py:obj:`.proxy.FaviconProxyConfig`."""
@classmethod
def from_toml_file(cls, cfg_file: pathlib.Path, use_cache: bool) -> "FaviconConfig":
"""Create a config object from a TOML file, the ``use_cache`` argument
specifies whether a cache should be used.
"""
cached = TOML_CACHE_CFG.get(str(cfg_file))
if use_cache and cached:
return cached
with cfg_file.open("rb") as f:
data = f.read()
cfg = msgspec.toml.decode(data, type=_FaviconConfig)
schema = cfg.favicons.cfg_schema
if schema != CONFIG_SCHEMA:
raise ValueError(
f"config schema version {CONFIG_SCHEMA} is needed, version {schema} is given in {cfg_file}"
)
cfg = cfg.favicons
if use_cache and cached:
TOML_CACHE_CFG[str(cfg_file.resolve())] = cfg
return cfg
class _FaviconConfig(msgspec.Struct): # pylint: disable=too-few-public-methods
# wrapper struct for root object "favicons."
favicons: FaviconConfig

25
searx/favicons/favicons.toml Normal file
View file

@ -0,0 +1,25 @@
[favicons]
cfg_schema = 1 # config's schema version no.
[favicons.proxy]
# max_age = 5184000 # 60 days / default: 7 days (604800 sec)
# [favicons.proxy.resolver_map]
#
# The available favicon resolvers are registered here.
#
# "duckduckgo" = "searx.favicons.resolvers.duckduckgo"
# "allesedv" = "searx.favicons.resolvers.allesedv"
# "google" = "searx.favicons.resolvers.google"
# "yandex" = "searx.favicons.resolvers.yandex"
[favicons.cache]
# db_url = "/var/cache/searxng/faviconcache.db" # default: "/tmp/faviconcache.db"
# HOLD_TIME = 5184000 # 60 days / default: 30 days
# LIMIT_TOTAL_BYTES = 2147483648 # 2 GB / default: 50 MB
# BLOB_MAX_BYTES = 40960 # 40 KB / default 20 KB
# MAINTENANCE_MODE = "off" # default: "auto"
# MAINTENANCE_PERIOD = 600 # 10min / default: 1h

237
searx/favicons/proxy.py Normal file
View file

@ -0,0 +1,237 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementations for a favicon proxy"""
from __future__ import annotations
from typing import Callable
import importlib
import base64
import pathlib
import urllib.parse
import flask
from httpx import HTTPError
import msgspec
from searx import get_setting
from searx.webutils import new_hmac, is_hmac_of
from searx.exceptions import SearxEngineResponseException
from .resolvers import DEFAULT_RESOLVER_MAP
from . import cache
DEFAULT_FAVICON_URL = {}
CFG: FaviconProxyConfig = None # type: ignore
def init(cfg: FaviconProxyConfig):
global CFG # pylint: disable=global-statement
CFG = cfg
def _initial_resolver_map():
d = {}
name: str = get_setting("search.favicon_resolver", None) # type: ignore
if name:
func = DEFAULT_RESOLVER_MAP.get(name)
if func:
d = {name: f"searx.favicons.resolvers.{func.__name__}"}
return d
class FaviconProxyConfig(msgspec.Struct):
"""Configuration of the favicon proxy."""
max_age: int = 60 * 60 * 24 * 7 # seven days
"""HTTP header Cache-Control_ ``max-age``
.. _Cache-Control: https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Cache-Control
"""
secret_key: str = get_setting("server.secret_key") # type: ignore
"""By default, the value from :ref:`server.secret_key <settings server>`
setting is used."""
resolver_timeout: int = get_setting("outgoing.request_timeout") # type: ignore
"""Timeout which the resolvers should not exceed, is usually passed to the
outgoing request of the resolver. By default, the value from
:ref:`outgoing.request_timeout <settings outgoing>` setting is used."""
resolver_map: dict[str, str] = msgspec.field(default_factory=_initial_resolver_map)
"""The resolver_map is a key / value dictionary where the key is the name of
the resolver and the value is the fully qualifying name (fqn) of resolver's
function (the callable). The resolvers from the python module
:py:obj:`searx.favicons.resolver` are available by default."""
def get_resolver(self, name: str) -> Callable | None:
"""Returns the callable object (function) of the resolver with the
``name``. If no resolver is registered for the ``name``, ``None`` is
returned.
"""
fqn = self.resolver_map.get(name)
if fqn is None:
return None
mod_name, _, func_name = fqn.rpartition('.')
mod = importlib.import_module(mod_name)
func = getattr(mod, func_name)
if func is None:
raise ValueError(f"resolver {fqn} is not implemented")
return func
favicon_path: str = get_setting("ui.static_path") + "/themes/{theme}/img/empty_favicon.svg" # type: ignore
favicon_mime_type: str = "image/svg+xml"
def favicon(self, **replacements):
"""Returns pathname and mimetype of the default favicon."""
return (
pathlib.Path(self.favicon_path.format(**replacements)),
self.favicon_mime_type,
)
def favicon_data_url(self, **replacements):
"""Returns data image URL of the default favicon."""
cache_key = ", ".join(f"{x}:{replacements[x]}" for x in sorted(list(replacements.keys()), key=str))
data_url = DEFAULT_FAVICON_URL.get(cache_key)
if data_url is not None:
return data_url
fav, mimetype = CFG.favicon(**replacements)
# hint: encoding utf-8 limits favicons to be a SVG image
with fav.open("r", encoding="utf-8") as f:
data_url = f.read()
data_url = urllib.parse.quote(data_url)
data_url = f"data:{mimetype};utf8,{data_url}"
DEFAULT_FAVICON_URL[cache_key] = data_url
return data_url
def favicon_proxy():
"""REST API of SearXNG's favicon proxy service
::
/favicon_proxy?authority=<...>&h=<...>
``authority``:
Domain name :rfc:`3986` / see :py:obj:`favicon_url`
``h``:
HMAC :rfc:`2104`, build up from the :ref:`server.secret_key <settings
server>` setting.
"""
authority = flask.request.args.get('authority')
# malformed request or RFC 3986 authority
if not authority or "/" in authority:
return '', 400
# malformed request / does not have authorisation
if not is_hmac_of(
CFG.secret_key,
authority.encode(),
flask.request.args.get('h', ''),
):
return '', 400
resolver = flask.request.preferences.get_value('favicon_resolver') # type: ignore
# if resolver is empty or not valid, just return HTTP 400.
if not resolver or resolver not in CFG.resolver_map.keys():
return "", 400
data, mime = search_favicon(resolver, authority)
if data is not None and mime is not None:
resp = flask.Response(data, mimetype=mime) # type: ignore
resp.headers['Cache-Control'] = f"max-age={CFG.max_age}"
return resp
# return default favicon from static path
theme = flask.request.preferences.get_value("theme") # type: ignore
fav, mimetype = CFG.favicon(theme=theme)
return flask.send_from_directory(fav.parent, fav.name, mimetype=mimetype)
def search_favicon(resolver: str, authority: str) -> tuple[None | bytes, None | str]:
"""Sends the request to the favicon resolver and returns a tuple for the
favicon. The tuple consists of ``(data, mime)``, if the resolver has not
determined a favicon, both values are ``None``.
``data``:
Binary data of the favicon.
``mime``:
Mime type of the favicon.
"""
data, mime = (None, None)
func = CFG.get_resolver(resolver)
if func is None:
return data, mime
# to avoid superfluous requests to the resolver, first look in the cache
data_mime = cache.CACHE(resolver, authority)
if data_mime is not None:
return data_mime
try:
data, mime = func(authority, timeout=CFG.resolver_timeout)
if data is None or mime is None:
data, mime = (None, None)
except (HTTPError, SearxEngineResponseException):
pass
cache.CACHE.set(resolver, authority, mime, data)
return data, mime
def favicon_url(authority: str) -> str:
"""Function to generate the image URL used for favicons in SearXNG's result
lists. The ``authority`` argument (aka netloc / :rfc:`3986`) is usually a
(sub-) domain name. This function is used in the HTML (jinja) templates.
.. code:: html
<div class="favicon">
<img src="{{ favicon_url(result.parsed_url.netloc) }}">
</div>
The returned URL is a route to :py:obj:`favicon_proxy` REST API.
If the favicon is already in the cache, the returned URL is a `data URL`_
(something like ``data:image/png;base64,...``). By generating a data url from
the :py:obj:`.cache.FaviconCache`, additional HTTP roundtripps via the
:py:obj:`favicon_proxy` are saved. However, it must also be borne in mind
that data urls are not cached in the client (web browser).
.. _data URL: https://developer.mozilla.org/en-US/docs/Web/HTTP/Basics_of_HTTP/Data_URLs
"""
resolver = flask.request.preferences.get_value('favicon_resolver') # type: ignore
# if resolver is empty or not valid, just return nothing.
if not resolver or resolver not in CFG.resolver_map.keys():
return ""
data_mime = cache.CACHE(resolver, authority)
if data_mime == (None, None):
# we have already checked, the resolver does not have a favicon
theme = flask.request.preferences.get_value("theme") # type: ignore
return CFG.favicon_data_url(theme=theme)
if data_mime is not None:
data, mime = data_mime
return f"data:{mime};base64,{str(base64.b64encode(data), 'utf-8')}" # type: ignore
h = new_hmac(CFG.secret_key, authority.encode())
proxy_url = flask.url_for('favicon_proxy')
query = urllib.parse.urlencode({"authority": authority, "h": h})
return f"{proxy_url}?{query}"

100
searx/favicons/resolvers.py Normal file
View file

@ -0,0 +1,100 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementations of the favicon *resolvers* that are available in the favicon
proxy by default. A *resolver* is a function that obtains the favicon from an
external source. The *resolver* function receives two arguments (``domain,
timeout``) and returns a tuple ``(data, mime)``.
"""
from __future__ import annotations
__all__ = ["DEFAULT_RESOLVER_MAP", "allesedv", "duckduckgo", "google", "yandex"]
from typing import Callable
from searx import network
from searx import logger
DEFAULT_RESOLVER_MAP: dict[str, Callable]
logger = logger.getChild('favicons.resolvers')
def _req_args(**kwargs):
# add the request arguments from the searx.network
d = {"raise_for_httperror": False}
d.update(kwargs)
return d
def allesedv(domain: str, timeout: int) -> tuple[None | bytes, None | str]:
"""Favicon Resolver from allesedv.com / https://favicon.allesedv.com/"""
data, mime = (None, None)
url = f"https://f1.allesedv.com/32/{domain}"
logger.debug("fetch favicon from: %s", url)
# will just return a 200 regardless of the favicon existing or not
# sometimes will be correct size, sometimes not
response = network.get(url, **_req_args(timeout=timeout))
if response and response.status_code == 200:
mime = response.headers['Content-Type']
if mime != 'image/gif':
data = response.content
return data, mime
def duckduckgo(domain: str, timeout: int) -> tuple[None | bytes, None | str]:
"""Favicon Resolver from duckduckgo.com / https://blog.jim-nielsen.com/2021/displaying-favicons-for-any-domain/"""
data, mime = (None, None)
url = f"https://icons.duckduckgo.com/ip2/{domain}.ico"
logger.debug("fetch favicon from: %s", url)
# will return a 404 if the favicon does not exist and a 200 if it does,
response = network.get(url, **_req_args(timeout=timeout))
if response and response.status_code == 200:
# api will respond with a 32x32 png image
mime = response.headers['Content-Type']
data = response.content
return data, mime
def google(domain: str, timeout: int) -> tuple[None | bytes, None | str]:
"""Favicon Resolver from google.com"""
data, mime = (None, None)
# URL https://www.google.com/s2/favicons?sz=32&domain={domain}" will be
# redirected (HTTP 301 Moved Permanently) to t1.gstatic.com/faviconV2:
url = (
f"https://t1.gstatic.com/faviconV2?client=SOCIAL&type=FAVICON&fallback_opts=TYPE,SIZE,URL"
f"&url=https://{domain}&size=32"
)
logger.debug("fetch favicon from: %s", url)
# will return a 404 if the favicon does not exist and a 200 if it does,
response = network.get(url, **_req_args(timeout=timeout))
if response and response.status_code == 200:
# api will respond with a 32x32 png image
mime = response.headers['Content-Type']
data = response.content
return data, mime
def yandex(domain: str, timeout: int) -> tuple[None | bytes, None | str]:
"""Favicon Resolver from yandex.com"""
data, mime = (None, None)
url = f"https://favicon.yandex.net/favicon/{domain}"
logger.debug("fetch favicon from: %s", url)
# api will respond with a 16x16 png image, if it doesn't exist, it will be a
# 1x1 png image (70 bytes)
response = network.get(url, **_req_args(timeout=timeout))
if response and response.status_code == 200 and len(response.content) > 70:
mime = response.headers['Content-Type']
data = response.content
return data, mime
DEFAULT_RESOLVER_MAP = {
"allesedv": allesedv,
"duckduckgo": duckduckgo,
"google": google,
"yandex": yandex,
}

9
searx/limiter.py
View file

@ -128,9 +128,6 @@ _INSTALLED = False
LIMITER_CFG_SCHEMA = Path(__file__).parent / "limiter.toml"
"""Base configuration (schema) of the botdetection."""
LIMITER_CFG = Path('/etc/searxng/limiter.toml')
"""Local Limiter configuration."""
CFG_DEPRECATED = {
# "dummy.old.foo": "config 'dummy.old.foo' exists only for tests. Don't use it in your real project config."
}
@ -138,8 +135,12 @@ CFG_DEPRECATED = {
def get_cfg() -> config.Config:
global CFG # pylint: disable=global-statement
if CFG is None:
CFG = config.Config.from_toml(LIMITER_CFG_SCHEMA, LIMITER_CFG, CFG_DEPRECATED)
from . import settings_loader # pylint: disable=import-outside-toplevel
cfg_file = (settings_loader.get_user_cfg_folder() or Path("/etc/searxng")) / "limiter.toml"
CFG = config.Config.from_toml(LIMITER_CFG_SCHEMA, cfg_file, CFG_DEPRECATED)
return CFG

2
searx/locales.py
View file

@ -152,7 +152,7 @@ def locales_initialize():
def region_tag(locale: babel.Locale) -> str:
"""Returns SearXNG's region tag from the locale (e.g. zh-TW , en-US)."""
if not locale.territory:
raise ValueError('%s missed a territory')
raise ValueError('babel.Locale %s: missed a territory' % locale)
return locale.language + '-' + locale.territory

78
searx/plugins/calculator.py
View file

@ -3,19 +3,27 @@
"""
import ast
import re
import operator
from multiprocessing import Process, Queue
from typing import Callable
import flask
import babel
from flask_babel import gettext
from searx import settings
from searx.plugins import logger
name = "Basic Calculator"
description = gettext("Calculate mathematical expressions via the search bar")
default_on = False
default_on = True
preference_section = 'general'
plugin_id = 'calculator'
operators = {
logger = logger.getChild(plugin_id)
operators: dict[type, Callable] = {
ast.Add: operator.add,
ast.Sub: operator.sub,
ast.Mult: operator.mul,
@ -35,11 +43,15 @@ def _eval_expr(expr):
>>> _eval_expr('1 + 2*3**(4^5) / (6 + -7)')
-5.0
"""
return _eval(ast.parse(expr, mode='eval').body)
try:
return _eval(ast.parse(expr, mode='eval').body)
except ZeroDivisionError:
# This is undefined
return ""
def _eval(node):
if isinstance(node, ast.Constant) and isinstance(node.value, int):
if isinstance(node, ast.Constant) and isinstance(node.value, (int, float)):
return node.value
if isinstance(node, ast.BinOp):
@ -51,10 +63,31 @@ def _eval(node):
raise TypeError(node)
def timeout_func(timeout, func, *args, **kwargs):
def handler(q: Queue, func, args, **kwargs): # pylint:disable=invalid-name
try:
q.put(func(*args, **kwargs))
except:
q.put(None)
raise
que = Queue()
p = Process(target=handler, args=(que, func, args), kwargs=kwargs)
p.start()
p.join(timeout=timeout)
ret_val = None
if not p.is_alive():
ret_val = que.get()
else:
logger.debug("terminate function after timeout is exceeded")
p.terminate()
p.join()
p.close()
return ret_val
def post_search(_request, search):
# don't run on public instances due to possible attack surfaces
if settings['server']['public_instance']:
return True
# only show the result of the expression on the first page
if search.search_query.pageno > 1:
@ -68,21 +101,30 @@ def post_search(_request, search):
# replace commonly used math operators with their proper Python operator
query = query.replace("x", "*").replace(":", "/")
# use UI language
ui_locale = babel.Locale.parse(flask.request.preferences.get_value('locale'), sep='-')
# parse the number system in a localized way
def _decimal(match: re.Match) -> str:
val = match.string[match.start() : match.end()]
val = babel.numbers.parse_decimal(val, ui_locale, numbering_system="latn")
return str(val)
decimal = ui_locale.number_symbols["latn"]["decimal"]
group = ui_locale.number_symbols["latn"]["group"]
query = re.sub(f"[0-9]+[{decimal}|{group}][0-9]+[{decimal}|{group}]?[0-9]?", _decimal, query)
# only numbers and math operators are accepted
if any(str.isalpha(c) for c in query):
return True
# in python, powers are calculated via **
query_py_formatted = query.replace("^", "**")
try:
result = str(_eval_expr(query_py_formatted))
if result != query:
search.result_container.answers['calculate'] = {'answer': f"{query} = {result}"}
except (TypeError, SyntaxError, ArithmeticError):
pass
# Prevent the runtime from being longer than 50 ms
result = timeout_func(0.05, _eval_expr, query_py_formatted)
if result is None or result == "":
return True
result = babel.numbers.format_decimal(result, locale=ui_locale)
search.result_container.answers['calculate'] = {'answer': f"{search.search_query.query} = {result}"}
return True
def is_allowed():
return not settings['server']['public_instance']

9
searx/preferences.py
View file

@ -13,7 +13,7 @@ from collections import OrderedDict
import flask
import babel
from searx import settings, autocomplete
from searx import settings, autocomplete, favicons
from searx.enginelib import Engine
from searx.plugins import Plugin
from searx.locales import LOCALE_NAMES
@ -406,6 +406,11 @@ class Preferences:
locked=is_locked('autocomplete'),
choices=list(autocomplete.backends.keys()) + ['']
),
'favicon_resolver': EnumStringSetting(
settings['search']['favicon_resolver'],
locked=is_locked('favicon_resolver'),
choices=list(favicons.proxy.CFG.resolver_map.keys()) + ['']
),
'image_proxy': BooleanSetting(
settings['server']['image_proxy'],
locked=is_locked('image_proxy')
@ -441,7 +446,7 @@ class Preferences:
'simple_style': EnumStringSetting(
settings['ui']['theme_args']['simple_style'],
locked=is_locked('simple_style'),
choices=['', 'auto', 'light', 'dark']
choices=['', 'auto', 'light', 'dark', 'black']
),
'center_alignment': BooleanSetting(
settings['ui']['center_alignment'],

3
searx/query.py
View file

@ -1,6 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# pylint: disable=invalid-name, missing-module-docstring, missing-class-docstring
from __future__ import annotations
from abc import abstractmethod, ABC
import re
@ -258,7 +259,7 @@ class RawTextQuery:
FeelingLuckyParser, # redirect to the first link in the results list
]
def __init__(self, query, disabled_engines):
def __init__(self, query: str, disabled_engines: list):
assert isinstance(query, str)
# input parameters
self.query = query

5
searx/results.py
View file

@ -9,7 +9,6 @@ from typing import List, NamedTuple, Set
from urllib.parse import urlparse, unquote
from searx import logger
from searx import utils
from searx.engines import engines
from searx.metrics import histogram_observe, counter_add, count_error
@ -366,9 +365,9 @@ class ResultContainer:
result['score'] = result_score(result, result.get('priority'))
# removing html content and whitespace duplications
if result.get('content'):
result['content'] = utils.html_to_text(result['content']).strip()
result['content'] = result['content'].strip()
if result.get('title'):
result['title'] = ' '.join(utils.html_to_text(result['title']).strip().split())
result['title'] = ' '.join(result['title'].strip().split())
for result_engine in result['engines']:
counter_add(result['score'], 'engine', result_engine, 'score')

2
searx/search/processors/online_currency.py
View file

@ -23,7 +23,7 @@ def name_to_iso4217(name):
currency = CURRENCIES['names'].get(name, [name])
if isinstance(currency, str):
return currency
return currency[0]
return currency[-1]
def iso4217_to_name(iso4217, language):

1
searx/searxng.msg
View file

@ -55,6 +55,7 @@ STYLE_NAMES = {
'AUTO': 'auto',
'LIGHT': 'light',
'DARK': 'dark',
'BLACK': 'black',
}
BRAND_CUSTOM_LINKS = {

147
searx/settings.yml
View file

@ -35,6 +35,9 @@ search:
autocomplete: ""
# minimun characters to type before autocompleter starts
autocomplete_min: 4
# backend for the favicon near URL in search results.
# Available resolvers: "allesedv", "duckduckgo", "google", "yandex" - leave blank to turn it off by default.
favicon_resolver: ""
# Default search language - leave blank to detect from browser information or
# use codes from 'languages.py'
default_lang: "auto"
@ -219,13 +222,13 @@ outgoing:
#
# enabled_plugins:
# # these plugins are enabled if nothing is configured ..
# - 'Basic Calculator'
# - 'Hash plugin'
# - 'Self Information'
# - 'Tracker URL remover'
# - 'Ahmia blacklist' # activation depends on outgoing.using_tor_proxy
# # these plugins are disabled if nothing is configured ..
# - 'Hostnames plugin' # see 'hostnames' configuration below
# - 'Basic Calculator'
# - 'Open Access DOI rewrite'
# - 'Tor check plugin'
# # Read the docs before activate: auto-detection of the language could be
@ -482,6 +485,23 @@ engines:
# to show premium or plus results too:
# skip_premium: false
- name: cloudflareai
engine: cloudflareai
shortcut: cfai
# get api token and accont id from https://developers.cloudflare.com/workers-ai/get-started/rest-api/
cf_account_id: 'your_cf_accout_id'
cf_ai_api: 'your_cf_api'
# create your ai gateway by https://developers.cloudflare.com/ai-gateway/get-started/creating-gateway/
cf_ai_gateway: 'your_cf_ai_gateway_name'
# find the model name from https://developers.cloudflare.com/workers-ai/models/#text-generation
cf_ai_model: 'ai_model_name'
# custom your preferences
# cf_ai_model_display_name: 'Cloudflare AI'
# cf_ai_model_assistant: 'prompts_for_assistant_role'
# cf_ai_model_system: 'prompts_for_system_role'
timeout: 30
disabled: true
# - name: core.ac.uk
# engine: core
# categories: science
@ -562,33 +582,6 @@ engines:
categories: general
shortcut: cc
- name: bahnhof
engine: json_engine
search_url: https://www.bahnhof.de/api/stations/search/{query}
url_prefix: https://www.bahnhof.de/
url_query: slug
title_query: name
content_query: state
shortcut: bf
disabled: true
about:
website: https://www.bahn.de
wikidata_id: Q22811603
use_official_api: false
require_api_key: false
results: JSON
language: de
tests:
bahnhof:
matrix:
query: berlin
lang: en
result_container:
- not_empty
- ['one_title_contains', 'Berlin Hauptbahnhof']
test:
- unique_results
- name: deezer
engine: deezer
shortcut: dz
@ -834,24 +827,21 @@ engines:
timeout: 10
- name: gitlab
engine: json_engine
paging: true
search_url: https://gitlab.com/api/v4/projects?search={query}&page={pageno}
url_query: web_url
title_query: name_with_namespace
content_query: description
page_size: 20
categories: [it, repos]
engine: gitlab
base_url: https://gitlab.com
shortcut: gl
timeout: 10.0
disabled: true
about:
website: https://about.gitlab.com/
website: https://gitlab.com/
wikidata_id: Q16639197
official_api_documentation: https://docs.gitlab.com/ee/api/
use_official_api: false
require_api_key: false
results: JSON
# - name: gnome
# engine: gitlab
# base_url: https://gitlab.gnome.org
# shortcut: gn
# about:
# website: https://gitlab.gnome.org
# wikidata_id: Q44316
- name: github
engine: github
@ -930,26 +920,6 @@ engines:
shortcut: mi
disabled: true
- name: gpodder
engine: json_engine
shortcut: gpod
timeout: 4.0
paging: false
search_url: https://gpodder.net/search.json?q={query}
url_query: url
title_query: title
content_query: description
page_size: 19
categories: music
disabled: true
about:
website: https://gpodder.net
wikidata_id: Q3093354
official_api_documentation: https://gpoddernet.readthedocs.io/en/latest/api/
use_official_api: false
requires_api_key: false
results: JSON
- name: habrahabr
engine: xpath
paging: true
@ -1313,6 +1283,12 @@ engines:
require_api_key: false
results: JSON
- name: openlibrary
engine: openlibrary
shortcut: ol
timeout: 5
disabled: true
- name: openmeteo
engine: open_meteo
shortcut: om
@ -1575,6 +1551,24 @@ engines:
page_size: 25
disabled: true
- name: right dao
engine: xpath
paging: true
page_size: 12
search_url: https://rightdao.com/search?q={query}&start={pageno}
results_xpath: //div[contains(@class, "description")]
url_xpath: ../div[contains(@class, "title")]/a/@href
title_xpath: ../div[contains(@class, "title")]
content_xpath: .
categories: general
shortcut: rd
disabled: true
about:
website: https://rightdao.com/
use_official_api: false
require_api_key: false
results: HTML
- name: rottentomatoes
engine: rottentomatoes
shortcut: rt
@ -1882,25 +1876,6 @@ engines:
about:
website: https://wiby.me/
- name: alexandria
engine: json_engine
shortcut: alx
categories: general
paging: true
search_url: https://api.alexandria.org/?a=1&q={query}&p={pageno}
results_query: results
title_query: title
url_query: url
content_query: snippet
timeout: 1.5
disabled: true
about:
website: https://alexandria.org/
official_api_documentation: https://github.com/alexandria-org/alexandria-api/raw/master/README.md
use_official_api: true
require_api_key: false
results: JSON
- name: wikibooks
engine: mediawiki
weight: 0.5
@ -2069,6 +2044,16 @@ engines:
# query_str: 'SELECT * from mytable WHERE fieldname=%(query)s'
# shortcut: mysql
# Required dependency: mariadb
# - name: mariadb
# engine: mariadb_server
# database: mydatabase
# username: user
# password: pass
# limit: 10
# query_str: 'SELECT * from mytable WHERE fieldname=%(query)s'
# shortcut: mdb
- name: 1337x
engine: 1337x
shortcut: 1337x

3
searx/settings_defaults.py
View file

@ -18,7 +18,7 @@ searx_dir = abspath(dirname(__file__))
logger = logging.getLogger('searx')
OUTPUT_FORMATS = ['html', 'csv', 'json', 'rss']
SXNG_LOCALE_TAGS = ['all', 'auto'] + list(l[0] for l in sxng_locales)
SIMPLE_STYLE = ('auto', 'light', 'dark')
SIMPLE_STYLE = ('auto', 'light', 'dark', 'black')
CATEGORIES_AS_TABS = {
'general': {},
'images': {},
@ -156,6 +156,7 @@ SCHEMA = {
'safe_search': SettingsValue((0, 1, 2), 0),
'autocomplete': SettingsValue(str, ''),
'autocomplete_min': SettingsValue(int, 4),
'favicon_resolver': SettingsValue(str, ''),
'default_lang': SettingsValue(tuple(SXNG_LOCALE_TAGS + ['']), ''),
'languages': SettingSublistValue(SXNG_LOCALE_TAGS, SXNG_LOCALE_TAGS),
'ban_time_on_fail': SettingsValue(numbers.Real, 5),

323
searx/sqlitedb.py Normal file
View file

@ -0,0 +1,323 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementations to make access to SQLite databases a little more convenient.
:py:obj:`SQLiteAppl`
Abstract class with which DB applications can be implemented.
:py:obj:`SQLiteProperties`:
Class to manage properties stored in a database.
----
"""
from __future__ import annotations
import sys
import re
import sqlite3
import threading
import abc
from searx import logger
logger = logger.getChild('sqlitedb')
class SQLiteAppl(abc.ABC):
"""Abstract base class for implementing convenient DB access in SQLite
applications. In the constructor, a :py:obj:`SQLiteProperties` instance is
already aggregated under ``self.properties``."""
DDL_CREATE_TABLES: dict[str, str] = {}
DB_SCHEMA: int = 1
"""As soon as changes are made to the DB schema, the version number must be
increased. Changes to the version number require the DB to be recreated (or
migrated / if an migration path exists and is implemented)."""
SQLITE_THREADING_MODE = {
0: "single-thread",
1: "multi-thread",
3: "serialized"}[sqlite3.threadsafety] # fmt:skip
"""Threading mode of the SQLite library. Depends on the options used at
compile time and is different for different distributions and architectures.
Possible values are 0:``single-thread``, 1:``multi-thread``,
3:``serialized`` (see :py:obj:`sqlite3.threadsafety`). Pre- Python 3.11
this value was hard coded to 1.
Depending on this value, optimizations are made, e.g. in “serialized” mode
it is not necessary to create a separate DB connector for each thread.
"""
SQLITE_JOURNAL_MODE = "WAL"
SQLITE_CONNECT_ARGS = {
# "timeout": 5.0,
# "detect_types": 0,
"check_same_thread": bool(SQLITE_THREADING_MODE != "serialized"),
"cached_statements": 0, # https://github.com/python/cpython/issues/118172
# "uri": False,
"autocommit": False,
} # fmt:skip
"""Connection arguments (:py:obj:`sqlite3.connect`)
``check_same_thread``:
Is disabled by default when :py:obj:`SQLITE_THREADING_MODE` is
``serialized``. The check is more of a hindrance in this case because it
would prevent a DB connector from being used in multiple threads.
``autocommit``:
Is disabled by default. Note: autocommit option has been added in Python
3.12.
``cached_statements``:
Is set to ``0`` by default. Note: Python 3.12+ fetch result are not
consistent in multi-threading application and causing an API misuse error.
The multithreading use in SQLiteAppl is intended and supported if
threadsafety is set to 3 (aka "serialized"). CPython supports “serialized”
from version 3.12 on, but unfortunately only with errors:
- https://github.com/python/cpython/issues/118172
- https://github.com/python/cpython/issues/123873
The workaround for SQLite3 multithreading cache inconsistency ist to set
option ``cached_statements`` to ``0`` by default.
"""
def __init__(self, db_url):
self.db_url = db_url
self.properties = SQLiteProperties(db_url)
self.thread_local = threading.local()
self._init_done = False
self._compatibility()
def _compatibility(self):
if self.SQLITE_THREADING_MODE == "serialized":
self._DB = None
else:
msg = (
f"SQLite library is compiled with {self.SQLITE_THREADING_MODE} mode,"
" read https://docs.python.org/3/library/sqlite3.html#sqlite3.threadsafety"
)
if threading.active_count() > 1:
logger.error(msg)
else:
logger.warning(msg)
if sqlite3.sqlite_version_info <= (3, 35):
# See "Generalize UPSERT:" in https://sqlite.org/releaselog/3_35_0.html
logger.critical(
"SQLite runtime library version %s is not supported (require >= 3.35)", sqlite3.sqlite_version
)
def connect(self) -> sqlite3.Connection:
"""Creates a new DB connection (:py:obj:`SQLITE_CONNECT_ARGS`). If not
already done, the DB schema is set up
"""
if sys.version_info < (3, 12):
# Prior Python 3.12 there is no "autocommit" option
self.SQLITE_CONNECT_ARGS.pop("autocommit", None)
self.init()
logger.debug("%s: connect to DB: %s // %s", self.__class__.__name__, self.db_url, self.SQLITE_CONNECT_ARGS)
conn = sqlite3.Connection(self.db_url, **self.SQLITE_CONNECT_ARGS) # type: ignore
conn.execute(f"PRAGMA journal_mode={self.SQLITE_JOURNAL_MODE}")
self.register_functions(conn)
return conn
def register_functions(self, conn):
"""Create user-defined_ SQL functions.
``REGEXP(<pattern>, <field>)`` : 0 | 1
`re.search`_ returns (int) 1 for a match and 0 for none match of
``<pattern>`` in ``<field>``.
.. code:: sql
SELECT '12' AS field WHERE REGEXP('^[0-9][0-9]$', field)
-- 12
SELECT REGEXP('[0-9][0-9]', 'X12Y')
-- 1
SELECT REGEXP('[0-9][0-9]', 'X1Y')
-- 0
.. _user-defined: https://docs.python.org/3/library/sqlite3.html#sqlite3.Connection.create_function
.. _deterministic: https://sqlite.org/deterministic.html
.. _re.search: https://docs.python.org/3/library/re.html#re.search
"""
conn.create_function('regexp', 2, lambda x, y: 1 if re.search(x, y) else 0, deterministic=True)
@property
def DB(self) -> sqlite3.Connection:
"""Provides a DB connection. The connection is a *singleton* and
therefore well suited for read access. If
:py:obj:`SQLITE_THREADING_MODE` is ``serialized`` only one DB connection
is created for all threads.
.. note::
For dedicated `transaction control`_, it is recommended to create a
new connection (:py:obj:`SQLiteAppl.connect`).
.. _transaction control:
https://docs.python.org/3/library/sqlite3.html#sqlite3-controlling-transactions
"""
if getattr(self.thread_local, 'DB', None) is None:
self.thread_local.DB = self.connect()
# Theoretically it is possible to reuse the DB cursor across threads as
# of Python 3.12, in practice the threading of the cursor seems to me to
# be so faulty that I prefer to establish one connection per thread
self.thread_local.DB.commit()
return self.thread_local.DB
# In "serialized" mode, SQLite can be safely used by multiple threads
# with no restriction.
#
# if self.SQLITE_THREADING_MODE != "serialized":
# if getattr(self.thread_local, 'DB', None) is None:
# self.thread_local.DB = self.connect()
# return self.thread_local.DB
#
# if self._DB is None:
# self._DB = self.connect() # pylint: disable=attribute-defined-outside-init
# return self._DB
def init(self):
"""Initializes the DB schema and properties, is only executed once even
if called several times."""
if self._init_done:
return
self._init_done = True
logger.debug("init DB: %s", self.db_url)
self.properties.init()
ver = self.properties("DB_SCHEMA")
if ver is None:
with self.properties.DB:
self.create_schema(self.properties.DB)
else:
ver = int(ver)
if ver != self.DB_SCHEMA:
raise sqlite3.DatabaseError("Expected DB schema v%s, DB schema is v%s" % (self.DB_SCHEMA, ver))
logger.debug("DB_SCHEMA = %s", ver)
def create_schema(self, conn):
logger.debug("create schema ..")
with conn:
for table_name, sql in self.DDL_CREATE_TABLES.items():
conn.execute(sql)
self.properties.set(f"Table {table_name} created", table_name)
self.properties.set("DB_SCHEMA", self.DB_SCHEMA)
self.properties.set("LAST_MAINTENANCE", "")
class SQLiteProperties(SQLiteAppl):
"""Simple class to manage properties of a DB application in the DB. The
object has its own DB connection and transaction area.
.. code:: sql
CREATE TABLE IF NOT EXISTS properties (
name TEXT,
value TEXT,
m_time INTEGER DEFAULT (strftime('%s', 'now')),
PRIMARY KEY (name))
"""
SQLITE_JOURNAL_MODE = "WAL"
DDL_PROPERTIES = """\
CREATE TABLE IF NOT EXISTS properties (
name TEXT,
value TEXT,
m_time INTEGER DEFAULT (strftime('%s', 'now')), -- last modified (unix epoch) time in sec.
PRIMARY KEY (name))"""
"""Table to store properties of the DB application"""
SQL_GET = "SELECT value FROM properties WHERE name = ?"
SQL_M_TIME = "SELECT m_time FROM properties WHERE name = ?"
SQL_SET = (
"INSERT INTO properties (name, value) VALUES (?, ?)"
" ON CONFLICT(name) DO UPDATE"
" SET value=excluded.value, m_time=strftime('%s', 'now')"
)
SQL_TABLE_EXISTS = (
"SELECT name FROM sqlite_master"
" WHERE type='table' AND name='properties'"
) # fmt:skip
SQLITE_CONNECT_ARGS = dict(SQLiteAppl.SQLITE_CONNECT_ARGS)
SQLITE_CONNECT_ARGS["autocommit"] = True # This option has no effect before Python 3.12
def __init__(self, db_url: str): # pylint: disable=super-init-not-called
self.db_url = db_url
self.thread_local = threading.local()
self._init_done = False
self._compatibility()
def init(self):
"""Initializes DB schema of the properties in the DB."""
if self._init_done:
return
self._init_done = True
logger.debug("init properties of DB: %s", self.db_url)
with self.DB as conn:
res = conn.execute(self.SQL_TABLE_EXISTS)
if res.fetchone() is None: # DB schema needs to be be created
self.create_schema(conn)
def __call__(self, name, default=None):
"""Returns the value of the property ``name`` or ``default`` if property
not exists in DB."""
res = self.DB.execute(self.SQL_GET, (name,)).fetchone()
if res is None:
return default
return res[0]
def set(self, name, value):
"""Set ``value`` of property ``name`` in DB. If property already
exists, update the ``m_time`` (and the value)."""
self.DB.execute(self.SQL_SET, (name, value))
if sys.version_info <= (3, 12):
# Prior Python 3.12 there is no "autocommit" option / lets commit
# explicitely.
self.DB.commit()
def row(self, name, default=None):
"""Returns the DB row of property ``name`` or ``default`` if property
not exists in DB."""
cur = self.DB.cursor()
cur.execute("SELECT * FROM properties WHERE name = ?", (name,))
res = cur.fetchone()
if res is None:
return default
col_names = [column[0] for column in cur.description]
return dict(zip(col_names, res))
def m_time(self, name, default: int = 0) -> int:
"""Last modification time of this property."""
res = self.DB.execute(self.SQL_M_TIME, (name,)).fetchone()
if res is None:
return default
return int(res[0])
def create_schema(self, conn):
with conn:
conn.execute(self.DDL_PROPERTIES)

2
searx/static/themes/simple/css/searxng-rtl.min.css vendored
View file

File diff suppressed because one or more lines are too long

2
searx/static/themes/simple/css/searxng-rtl.min.css.map
View file

File diff suppressed because one or more lines are too long

2
searx/static/themes/simple/css/searxng.min.css vendored
View file

File diff suppressed because one or more lines are too long

2
searx/static/themes/simple/css/searxng.min.css.map
View file

File diff suppressed because one or more lines are too long

4
searx/static/themes/simple/img/empty_favicon.svg Normal file
View file

@ -0,0 +1,4 @@
<svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 24 24">
<path fill="#58f" d="M11 20.85a.92.92 0 0 1-1.1.93A10 10 0 0 1 2.06 13c-.06-.55.4-1 .95-1h3a1 1 0 0 1 1 1 3 3 0 0 0 3 3 1 1 0 0 1 1 1v3.85Zm6-1.92c0 .77.83 1.23 1.42.74a10 10 0 0 0 2.03-2.32c.39-.61-.09-1.35-.81-1.35H18a1 1 0 0 0-1 1v1.93ZM12 2a10 10 0 0 1 6.65 2.53c.61.55.17 1.47-.65 1.47h-.15A2.85 2.85 0 0 0 15 8.85c0 .33-.18.62-.47.77l-.08.04a1 1 0 0 1-.9 0l-.08-.04a.85.85 0 0 1-.47-.77A2.85 2.85 0 0 0 10.15 6H10a1 1 0 0 1-1-1V3.2c0-.44.28-.84.7-.94C10.45 2.1 11.22 2 12 2Z"/>
<path fill="#58f" d="M3.42 10c-.63 0-1.1-.58-.9-1.18.6-1.8 1.7-3.36 3.12-4.53C6.2 3.82 7 4.26 7 5a3 3 0 0 0 3 3h.15c.47 0 .85.38.85.85 0 1.09.61 2.07 1.58 2.56l.08.04a3 3 0 0 0 2.68 0l.08-.04A2.85 2.85 0 0 0 17 8.85c0-.47.38-.85.85-.85h2.66c.4 0 .77.23.9.6a9.98 9.98 0 0 1 .52 4.6.94.94 0 0 1-.95.8H18a3 3 0 0 0-3 3v3.8c0 .44-.28.84-.7.94l-.2.04a.92.92 0 0 1-1.1-.93V17a3 3 0 0 0-3-3 1 1 0 0 1-1-1 3 3 0 0 0-3-3H3.42Z"/>
</svg>
Side by side

After

Width:  |  Height:  |  Size: 989 B

1
searx/static/themes/simple/src/less/autocomplete.less
View file

@ -56,7 +56,6 @@
z-index: 100;
margin-top: 3.5rem;
border-radius: 0.8rem;
box-shadow: 0 2px 8px rgb(34 38 46 / 25%);
&:empty {
display: none;

2
searx/static/themes/simple/src/less/code.less
View file

@ -29,7 +29,7 @@
}
span.linenos {
color: #64708d;
color: var(--color-line-number);
}
}
}

29
searx/static/themes/simple/src/less/definitions.less
View file

@ -115,6 +115,17 @@
--color-toolkit-loader-borderleft: rgba(255, 255, 255, 0);
--color-doc-code: #003;
--color-doc-code-background: #ddeaff;
/// Other misc colors
--color-bar-chart-primary: #5bc0de;
--color-bar-chart-secondary: #deb15b;
--color-image-resolution-background: rgba(0, 0, 0, 50%);
--color-image-resolution-font: #fff;
--color-loading-indicator: rgba(255, 255, 255, 0.2);
--color-loading-indicator-gap: #fff;
--color-line-number: #64708d;
// Favicons Colors
--color-favicon-background-color: #ddd;
--color-favicon-border-color: #ccc;
}
.dark-themes() {
@ -227,6 +238,17 @@
--color-toolkit-loader-borderleft: rgba(0, 0, 0, 0);
--color-doc-code: #ddd;
--color-doc-code-background: #4d5a6f;
// Favicons Colors
--color-favicon-background-color: #ddd;
--color-favicon-border-color: #ccc;
}
.black-themes() {
--color-base-background: #000;
--color-base-background-mobile: #000;
--color-header-background: #000;
--color-footer-background: #000;
--color-sidebar-background: #000;
}
/// Dark Theme (autoswitch based on device pref)
@ -241,6 +263,11 @@
.dark-themes();
}
:root.theme-black {
.dark-themes();
.black-themes();
}
/// General Size
@results-width: 45rem;
@results-sidebar-width: 25rem;
@ -250,7 +277,7 @@
@results-margin: 0.125rem;
@result-padding: 1rem;
@results-image-row-height: 12rem;
@results-image-row-height-phone: 6rem;
@results-image-row-height-phone: 10rem;
@search-width: 44rem;
// heigh of #search, see detail.less
@search-height: 7.6rem;

11
searx/static/themes/simple/src/less/new_issue.less
View file

@ -2,18 +2,7 @@
.stats_endpoint {
.github-issue-button {
display: block;
padding: 8px 16px;
font-family: sans-serif;
font-size: 16px;
color: white;
background-color: #238636;
border: #2ea043;
border-radius: 10px !important;
box-shadow: rgba(0, 0, 0, 0) 0 0 0 0;
}
.github-issue-button:hover {
background-color: #2ea043;
}
.issue-hide {

9
searx/static/themes/simple/src/less/search.less
View file

@ -378,3 +378,12 @@ html.no-js #clear_search.hide_if_nojs {
#categories_container {
position: relative;
}
.favicon img {
height: 1.5rem;
width: 1.5rem;
border-radius: 10%;
background-color: var(--color-favicon-background-color);
border: 1px solid var(--color-favicon-border-color);
display: flex;
}

6
searx/static/themes/simple/src/less/stats.less
View file

@ -75,18 +75,18 @@ failed-test {
}
.bar-chart-bar {
border: 3px solid #5bc0de;
border: 3px solid var(--color-bar-chart-primary);
margin: 1px 0;
}
.bar-chart-serie1 {
border: 3px solid #5bc0de;
border: 3px solid var(--color-bar-chart-primary);
margin: 1px 0;
float: left;
}
.bar-chart-serie2 {
border: 3px solid #deb15b;
border: 3px solid var(--color-bar-chart-secondary);
margin: 1px 0;
float: left;
}

4
searx/static/themes/simple/src/less/style-rtl.less
View file

@ -94,6 +94,10 @@
direction: initial;
text-align: right;
.result .url_header {
direction: rtl;
}
.result .url_wrapper {
justify-content: end;
}

31
searx/static/themes/simple/src/less/style.less
View file

@ -170,6 +170,8 @@ article[data-vim-selected].category-social {
.result {
margin: @results-margin 0;
padding: @result-padding;
box-sizing: border-box;
width: 100%;
.ltr-border-left(0.2rem solid transparent);
h3 {
@ -232,8 +234,14 @@ article[data-vim-selected].category-social {
}
}
.url_header {
display: flex;
gap: 0.5rem;
}
.url_wrapper {
display: flex;
align-items: center;
font-size: 1rem;
color: var(--color-result-url-font);
flex-wrap: nowrap;
@ -448,6 +456,7 @@ article[data-vim-selected].category-social {
margin: 0.25rem;
border: none !important;
height: @results-image-row-height;
width: unset;
& > a {
position: relative;
@ -469,10 +478,10 @@ article[data-vim-selected].category-social {
position: absolute;
right: 0;
bottom: 0;
background: rgba(0, 0, 0, 50%);
background: var(--color-image-resolution-background);
padding: 0.3rem 0.5rem;
font-size: 0.9rem;
color: #fff;
color: var(--color-image-resolution-font);
border-top-left-radius: 0.3rem;
}
@ -748,6 +757,20 @@ summary.title {
}
}
#engines_msg {
.engine-name {
width: 10rem;
}
.response-error {
color: var(--color-error);
}
.bar-chart-value {
width: auto;
}
}
#search_url {
div.selectable_url {
pre {
@ -1076,7 +1099,8 @@ summary.title {
.result {
background: var(--color-result-background);
border: 1px solid var(--color-result-background);
margin: 1rem 10px;
margin: 1rem 2%;
width: 96%;
.rounded-corners;
}
@ -1084,6 +1108,7 @@ summary.title {
margin: 0;
height: @results-image-row-height-phone;
background: var(--color-base-background-mobile);
width: unset;
}
.infobox {

8
searx/static/themes/simple/src/less/toolkit_loader.less
View file

@ -10,10 +10,10 @@
font-size: 10px;
position: relative;
text-indent: -9999em;
border-top: 1.1em solid rgba(255, 255, 255, 0.2);
border-right: 1.1em solid rgba(255, 255, 255, 0.2);
border-bottom: 1.1em solid rgba(255, 255, 255, 0.2);
border-left: 1.1em solid #fff;
border-top: 1.1em solid var(--color-loading-indicator);
border-right: 1.1em solid var(--color-loading-indicator);
border-bottom: 1.1em solid var(--color-loading-indicator);
border-left: 1.1em solid var(--color-loading-indicator-gap);
-webkit-transform: translateZ(0);
-ms-transform: translateZ(0);
transform: translateZ(0);

7
searx/sxng_locales.py
View file

@ -16,9 +16,9 @@ sxng_locales = (
('bg', 'Български', '', 'Bulgarian', '\U0001f310'),
('bg-BG', 'Български', 'България', 'Bulgarian', '\U0001f1e7\U0001f1ec'),
('ca', 'Català', '', 'Catalan', '\U0001f310'),
('ca-ES', 'Català', 'Espanya', 'Catalan', '\U0001f1ea\U0001f1f8'),
('cs', 'Čeština', '', 'Czech', '\U0001f310'),
('cs-CZ', 'Čeština', 'Česko', 'Czech', '\U0001f1e8\U0001f1ff'),
('cy', 'Cymraeg', '', 'Welsh', '\U0001f310'),
('da', 'Dansk', '', 'Danish', '\U0001f310'),
('da-DK', 'Dansk', 'Danmark', 'Danish', '\U0001f1e9\U0001f1f0'),
('de', 'Deutsch', '', 'German', '\U0001f310'),
@ -56,6 +56,8 @@ sxng_locales = (
('fr-CA', 'Français', 'Canada', 'French', '\U0001f1e8\U0001f1e6'),
('fr-CH', 'Français', 'Suisse', 'French', '\U0001f1e8\U0001f1ed'),
('fr-FR', 'Français', 'France', 'French', '\U0001f1eb\U0001f1f7'),
('ga', 'Gaeilge', '', 'Irish', '\U0001f310'),
('gd', 'Gàidhlig', '', 'Scottish Gaelic', '\U0001f310'),
('gl', 'Galego', '', 'Galician', '\U0001f310'),
('he', 'עברית', '', 'Hebrew', '\U0001f1ee\U0001f1f1'),
('hi', 'हिन्दी', '', 'Hindi', '\U0001f310'),
@ -92,6 +94,7 @@ sxng_locales = (
('ru-RU', 'Русский', 'Россия', 'Russian', '\U0001f1f7\U0001f1fa'),
('sk', 'Slovenčina', '', 'Slovak', '\U0001f310'),
('sl', 'Slovenščina', '', 'Slovenian', '\U0001f310'),
('sq', 'Shqip', '', 'Albanian', '\U0001f310'),
('sv', 'Svenska', '', 'Swedish', '\U0001f310'),
('sv-SE', 'Svenska', 'Sverige', 'Swedish', '\U0001f1f8\U0001f1ea'),
('ta', 'தமிழ்', '', 'Tamil', '\U0001f310'),
@ -100,10 +103,8 @@ sxng_locales = (
('tr', 'Türkçe', '', 'Turkish', '\U0001f310'),
('tr-TR', 'Türkçe', 'Türkiye', 'Turkish', '\U0001f1f9\U0001f1f7'),
('uk', 'Українська', '', 'Ukrainian', '\U0001f310'),
('uk-UA', 'Українська', 'Україна', 'Ukrainian', '\U0001f1fa\U0001f1e6'),
('ur', 'اردو', '', 'Urdu', '\U0001f310'),
('vi', 'Tiếng Việt', '', 'Vietnamese', '\U0001f310'),
('vi-VN', 'Tiếng Việt', 'Việt Nam', 'Vietnamese', '\U0001f1fb\U0001f1f3'),
('zh', '中文', '', 'Chinese', '\U0001f310'),
('zh-CN', '中文', '中国', 'Chinese', '\U0001f1e8\U0001f1f3'),
('zh-HK', '中文', '中國香港特別行政區', 'Chinese', '\U0001f1ed\U0001f1f0'),

14
searx/templates/simple/base.html
View file

@ -1,7 +1,7 @@
<!DOCTYPE html>
<html class="no-js theme-{{ preferences.get_value('simple_style') or 'auto' }} center-aligment-{{ preferences.get_value('center_alignment') and 'yes' or 'no' }}" lang="{{ locale_rfc5646 }}" {% if rtl %} dir="rtl"{% endif %}>
<head>
<meta charset="UTF-8" />
<meta charset="UTF-8">
<meta name="description" content="SearXNG — a privacy-respecting, open metasearch engine">
<meta name="keywords" content="SearXNG, search, search engine, metasearch, meta search">
<meta name="generator" content="searxng/{{ searx_version }}">
@ -13,23 +13,23 @@
<title>{% block title %}{% endblock %}{{ instance_name }}</title>
{% block meta %}{% endblock %}
{% if rtl %}
<link rel="stylesheet" href="{{ url_for('static', filename='css/searxng-rtl.min.css') }}" type="text/css" media="screen" />
<link rel="stylesheet" href="{{ url_for('static', filename='css/searxng-rtl.min.css') }}" type="text/css" media="screen">
{% else %}
<link rel="stylesheet" href="{{ url_for('static', filename='css/searxng.min.css') }}" type="text/css" media="screen" />
<link rel="stylesheet" href="{{ url_for('static', filename='css/searxng.min.css') }}" type="text/css" media="screen">
{% endif %}
{% if get_setting('server.limiter') or get_setting('server.public_instance') %}
<link rel="stylesheet" href="{{ url_for('client_token', token=link_token) }}" type="text/css" />
<link rel="stylesheet" href="{{ url_for('client_token', token=link_token) }}" type="text/css">
{% endif %}
{% block styles %}{% endblock %}
<!--[if gte IE 9]>-->
<script src="{{ url_for('static', filename='js/searxng.head.min.js') }}" client_settings="{{ client_settings }}"></script>
<!--<![endif]-->
{% block head %}
<link title="{{ instance_name }}" type="application/opensearchdescription+xml" rel="search" href="{{ opensearch_url }}"/>
<link title="{{ instance_name }}" type="application/opensearchdescription+xml" rel="search" href="{{ opensearch_url }}">
{% endblock %}
<link rel="icon" href="{{ url_for('static', filename='img/favicon.png') }}" sizes="any">
<link rel="icon" href="{{ url_for('static', filename='img/favicon.svg') }}" type="image/svg+xml">
<link rel="apple-touch-icon" href="{{ url_for('static', filename='img/favicon.png') }}"/>
<link rel="apple-touch-icon" href="{{ url_for('static', filename='img/favicon.png') }}">
</head>
<body class="{{ endpoint }}_endpoint" >
<main id="main_{{ self._TemplateReference__context.name|replace("simple/", "")|replace(".html", "") }}" class="{{body_class}}">
@ -65,7 +65,7 @@
</main>
<footer>
<p>
{{ _('Powered by') }} <a href="{{ url_for('info', pagename='about') }}">searxng</a> - {{ searx_version }} — {{ _('a privacy-respecting, open metasearch engine') }}<br/>
{{ _('Powered by') }} <a href="{{ url_for('info', pagename='about') }}">searxng</a> - {{ searx_version }} — {{ _('a privacy-respecting, open metasearch engine') }}<br>
<a href="{{ searx_git_url }}">{{ _('Source code') }}</a>
| <a href="{{ get_setting('brand.issue_url') }}">{{ _('Issue tracker') }}</a>
{% if enable_metrics %}| <a href="{{ url_for('stats') }}">{{ _('Engine stats') }}</a>{% endif %}

2
searx/templates/simple/categories.html
View file

@ -16,7 +16,7 @@
{%- if not search_on_category_select or not display_tooltip -%}
{%- for category in categories -%}
<div class="category category_checkbox">{{- '' -}}
<input type="checkbox" id="checkbox_{{ category|replace(' ', '_') }}" name="category_{{ category }}"{% if category in selected_categories %} checked="checked"{% endif %}/>
<input type="checkbox" id="checkbox_{{ category|replace(' ', '_') }}" name="category_{{ category }}"{% if category in selected_categories %} checked="checked"{% endif %}>
<label for="checkbox_{{ category|replace(' ', '_') }}" class="tooltips">
{{- icon_big(category_icons[category]) if category in category_icons else icon_big('globe-outline') -}}
<div class="category_name">{{- _(category) -}}</div>

47
searx/templates/simple/elements/engines_msg.html
View file

@ -1,27 +1,34 @@
<div id="engines_msg">
{% if not results and not answers %}
{% if (not results and not answers) or not max_response_time %}
<details class="sidebar-collapsable" open>
<summary class="title" id="engines_msg-title">{{ _('Messages from the search engines') }}</summary>
{% else %}
<details class="sidebar-collapsable">
<summary class="title" id="engines_msg-title">{{ _('Response time') }}: {{ max_response_time | round(1) }} {{ _('seconds') }}</summary>
{% endif %}
<summary class="title" id="engines_msg-title">{{ _('Messages from the search engines') }}</summary>
<div class="dialog-error" role="alert">
{{ icon_big('warning') }}
<div>
<p>
<strong>{{ _('Error!') }}</strong>
{{ _('Engines cannot retrieve results') }}:
</p>
{%- for engine_name, error_type in unresponsive_engines -%}
<p>{{- engine_name }} (
<a href="{{ url_for('stats', engine=engine_name|e) }}"
title="{{ _('View error logs and submit a bug report') }}">
{{- error_type -}}
</a>
){{- '' -}}
</p>
{%- endfor -%}
</div>
</div>
<table class="engine-stats" id="engines_msg-table">
{%- for engine_name, error_type in unresponsive_engines -%}
<tr>
<td class="engine-name">
<a href="{{ url_for('stats', engine=engine_name|e) }}"
title="{{ _('View error logs and submit a bug report') }}">
{{- engine_name -}}
</a>
</td>
<td class="response-error">{{- error_type -}}</td>
</tr>
{%- endfor -%}
{%- for engine_name, response_time in timings -%}
<tr>
<td class="engine-name"><a href="{{ url_for('stats', engine=engine_name|e) }}">{{ engine_name }}</a></td>
<td class="response-time">
<div class="bar-chart-value">{{- response_time | round(1) -}}</div>
<div class="bar-chart-graph" aria-labelledby="{{engine_name}}_time" aria-hidden="true">
<div class="bar-chart-bar bar{{ (100 * response_time / max_response_time) | round | int }}"></div>
</div>
</td>
</tr>
{%- endfor -%}
</table>
</details>
</div>

2
searx/templates/simple/elements/infobox.html
View file

@ -38,7 +38,7 @@
<input type="hidden" name="safesearch" value="{{ safesearch }}">
<input type="hidden" name="theme" value="{{ theme }}">
{%- if timeout_limit -%}<input type="hidden" name="timeout_limit" value="{{ timeout_limit|e }}" >{%- endif -%}
<input type="submit" value="{{ suggestion }}" />
<input type="submit" value="{{ suggestion }}">
</form>
{%- endfor -%}
</div>

13
searx/templates/simple/macros.html
View file

@ -20,10 +20,15 @@
<!-- Draw result header -->
{% macro result_header(result, favicons, image_proxify) -%}
<article class="result {% if result['template'] %}result-{{ result.template|replace('.html', '') }}{% else %}result-default{% endif %} {% if result['category'] %}category-{{ result['category'] }}{% endif %}{% for e in result.engines %} {{ e }}{% endfor %}">
{{- result_open_link(result.url, "url_wrapper") -}}
{%- for part in get_pretty_url(result.parsed_url) -%}
<span class="url_o{{loop.index}}"><span class="url_i{{loop.index}}">{{- part -}}</span></span>
{%- endfor %}
{{- result_open_link(result.url, "url_header") -}}
{%- if favicon_resolver != "" %}
<div class="favicon"><img loading="lazy" src="{{ favicon_url(result.parsed_url.netloc) }}"></div>
{%- endif -%}
<div class="url_wrapper">
{%- for part in get_pretty_url(result.parsed_url) -%}
<span class="url_o{{loop.index}}"><span class="url_i{{loop.index}}">{{- part -}}</span></span>
{%- endfor %}
</div>
{{- result_close_link() -}}
{%- if result.thumbnail %}{{ result_open_link(result.url) }}<img class="thumbnail" src="{{ image_proxify(result.thumbnail) }}" title="{{ result.title|striptags }}" loading="lazy">{{ result_close_link() }}{% endif -%}
<h3>{{ result_link(result.url, result.title|safe) }}</h3>

2
searx/templates/simple/new_issue.html
View file

@ -69,7 +69,7 @@ or manually by executing the searx/webapp.py file? -->
<label class="step1 step1_delay" for="step2" >{{ _('I confirm there is no existing bug about the issue I encounter') }}</label>
<div class="step2 step_content">
<p>{{ _('If this is a public instance, please specify the URL in the bug report') }}</p>
<button type="submit" class="github-issue-button" title="{{ get_setting('brand.new_issue_url') }}">{{ _('Submit a new issue on Github including the above information') }}</button>
<button type="submit" class="github-issue-button button" title="{{ get_setting('brand.new_issue_url') }}">{{ _('Submit a new issue on Github including the above information') }}</button>
</div>
</form>
{% endmacro %}

25
searx/templates/simple/preferences.html
View file

@ -6,9 +6,9 @@
{%- endmacro -%}
{%- macro tab_header(name, id, label, checked) -%}
<input type="radio" name="{{ name }}" id="tab-{{ id }}" {% if checked is sameas true %}checked="checked"{% endif %} />
<input type="radio" name="{{ name }}" id="tab-{{ id }}" {% if checked is sameas true %}checked="checked"{% endif %}>
<label id="tab-label-{{ id }}" for="tab-{{ id }}" role="tab" aria-controls="tab-content-{{ id }}">{{ label }}</label>
<section id="tab-content-{{ id }}" role="tabpanel" aria-labelledby="tab-label-{{ id }}" aria-hidden="false">
<section id="tab-content-{{ id }}" role="tabpanel" aria-hidden="false">
{%- endmacro -%}
{%- macro tab_footer() -%}
@ -23,28 +23,28 @@
{%- if checked == '?' -%}
{{- icon_small('warning') -}}
{%- else -%}
<input type="checkbox" {%- if name %} name="{{ name }}" {%- endif %} value="None" {%- if checked %} checked {%- endif -%}{%- if disabled %} disabled {%- endif -%}/>
<input type="checkbox" {%- if name %} name="{{ name }}" {%- endif %} value="None" {%- if checked %} checked {%- endif -%}{%- if disabled %} disabled {%- endif -%}>
{%- endif -%}
{%- endmacro -%}
{%- macro checkbox_onoff_reversed(name, checked) -%}
{%- macro checkbox_onoff_reversed(name, checked, labelledby) -%}
<input type="checkbox" {{- ' ' -}}
name="{{ name }}" {{- ' ' -}}
id="{{ name }}" {{- ' ' -}}
aria-labelledby="pref_{{ name }}"{{- ' ' -}}
{%- if labelledby -%} aria-labelledby="{{ labelledby }}"{{- ' ' -}}{%- endif -%}
class="checkbox-onoff reversed-checkbox"{{- ' ' -}}
{%- if checked -%} checked{%- endif -%}/>
{%- if checked -%} checked{%- endif -%}>
{%- endmacro -%}
{%- macro plugin_preferences(section) -%}
{%- for plugin in plugins -%}
{%- if plugin.preference_section == section and (plugin.is_allowed() if plugin.is_allowed else True) -%}
{%- if plugin.preference_section == section -%}
<fieldset>{{- '' -}}
<legend>{{ _(plugin.name) }}</legend>{{- '' -}}
<div class="value">
{{- checkbox_onoff_reversed('plugin_' + plugin.id, plugin.id not in allowed_plugins) -}}
{{- checkbox_onoff_reversed('plugin_' + plugin.id, plugin.id not in allowed_plugins, 'plugin_labelledby' + plugin.id) -}}
</div>{{- '' -}}
<div class="description">
<div class="description" id="{{ 'plugin_labelledby' + plugin.id }}">
{{- _(plugin.description) -}}
</div>{{- '' -}}
</fieldset>
@ -90,7 +90,7 @@
<td class="{{ label }}">{{- '' -}}
{%- if stats[engine_name].time != None -%}
<span class="stacked-bar-chart-value">{{- stats[engine_name].time -}}</span>{{- '' -}}
<span class="stacked-bar-chart" aria-labelledby="{{engine_name}}_chart" aria-hidden="true">
<span class="stacked-bar-chart" aria-hidden="true">
{%- if max_rate95 is not none and max_rate95 > 0 -%}
<div class="stacked-bar-chart-median bar{{ (100 * (stats[engine_name].time / max_rate95))|round }}"></div>{{- '' -}}
<div class="stacked-bar-chart-rate80 bar{{ (100 * ((stats[engine_name].rate80 - stats[engine_name].time) / max_rate95))|round }}"></div>{{- '' -}}
@ -127,7 +127,7 @@
{%- if checker_result or errors -%}
<td class="{{ label }} column-reliability">{{- '' -}}
<a href="{{ url_for('stats', engine=engine_name|e) }}">{{- '' -}}
<span aria-labelledby="{{engine_name}}_reliability">
<span>
{{- icon_big('warning', 'The engine is not reliabled') }} {{ r -}}
</span>{{- '' -}}
</a>{{- '' -}}
@ -173,6 +173,9 @@
{%- if 'autocomplete' not in locked_preferences -%}
{%- include 'simple/preferences/autocomplete.html' -%}
{%- endif -%}
{%- if 'favicon' not in locked_preferences -%}
{%- include 'simple/preferences/favicon.html' -%}
{%- endif -%}
{% if 'safesearch' not in locked_preferences %}
{%- include 'simple/preferences/safesearch.html' -%}
{%- endif -%}

4
searx/templates/simple/preferences/answerers.html
View file

@ -33,10 +33,10 @@
{%- for plugin in plugins -%}
{%- if plugin.preference_section == 'query' -%}
<tr>{{- '' -}}
<td class="checkbox-col">{{- checkbox_onoff_reversed('plugin_' + plugin.id, plugin.id not in allowed_plugins) -}}</td>{{- '' -}}
<td class="checkbox-col">{{- checkbox_onoff_reversed('plugin_' + plugin.id, plugin.id not in allowed_plugins, 'plugin_labelledby' + plugin.id) -}}</td>{{- '' -}}
<td>{{ plugin.query_keywords|join(', ') }}</td>{{- '' -}}
<td>{{ _(plugin.name) }}</td>{{- '' -}}
<td>{{ _(plugin.description) }}</td>{{- '' -}}
<td id="{{ 'plugin_labelledby' + plugin.id }}">{{ _(plugin.description) }}</td>{{- '' -}}
<td>{{ plugin.query_examples }}</td>{{- '' -}}
</tr>
{%- endif -%}

2
searx/templates/simple/preferences/center_alignment.html
View file

@ -8,7 +8,7 @@
{%- if preferences.get_value('center_alignment') -%}
checked
{%- endif -%}{{- ' ' -}}
/>{{- '' -}}
>{{- '' -}}
</p>{{- '' -}}
<div class="description">
{{- _('Displays results in the center of the page (Oscar layout).') -}}

4
searx/templates/simple/preferences/cookies.html
View file

@ -1,7 +1,7 @@
<p class="text-muted">
{{- _('This is the list of cookies and their values SearXNG is storing on your computer.') }}
<br />{{- _('With that list, you can assess SearXNG transparency.') -}}
<br />{{- '' -}}
<br>{{- _('With that list, you can assess SearXNG transparency.') -}}
<br>{{- '' -}}
</p>
{% if cookies %}
<table class="cookies">

17
searx/templates/simple/preferences/favicon.html Normal file
View file

@ -0,0 +1,17 @@
<fieldset>{{- '' -}}
<legend id="pref_favicon_resolver">{{- _('Favicon Resolver') -}}</legend>{{- '' -}}
<div class="value">{{- '' -}}
<select name="favicon_resolver" aria-labelledby="pref_favicon_resolver">{{- '' -}}
<option value=""> - </option>
{%- for backend in favicon_resolver_names -%}
<option value="{{ backend }}"
{%- if backend == favicon_resolver %} selected="selected" {%- endif -%}>
{{- backend -}}
</option>
{%- endfor -%}
</select>{{- '' -}}
</div>{{- '' -}}
<div class="description">
{{- _('Display favicons near search results') -}}
</div>{{- '' -}}
</fieldset>{{- '' -}}

4
searx/templates/simple/preferences/footer.html
View file

@ -1,9 +1,9 @@
<p class="small_font">
{{- _('These settings are stored in your cookies, this allows us not to store this data about you.') -}}
<br />{{- _("These cookies serve your sole convenience, we don't use these cookies to track you.") -}}
<br>{{- _("These cookies serve your sole convenience, we don't use these cookies to track you.") -}}
</p>{{- '' -}}
<input type="submit" value="{{ _('Save') }}" />{{- '' -}}
<input type="submit" value="{{ _('Save') }}">{{- '' -}}
<div class="{% if rtl %}left{% else %}right{% endif %} preferences_back">{{- '' -}}
<a href="{{ url_for('clear_cookies') }}">{{ _('Reset defaults') }}</a>{{- '' -}}

2
searx/templates/simple/preferences/image_proxy.html
View file

@ -8,7 +8,7 @@
{%- if preferences.get_value('image_proxy') -%}
checked
{%- endif -%}{{- ' ' -}}
/>{{- '' -}}
>{{- '' -}}
</p>{{- '' -}}
<div class="description">
{{- _('Proxying image results through SearXNG') -}}

Some files were not shown because too many files have changed in this diff Show more