2 Commits

Author SHA1 Message Date
Ivan Gabaldon
401d7f9f51 fmt 2026-09-01 21:46:00 +02:00
dependabot[bot]
aee33412aa [upd] pypi: Bump black from 25.9.0 to 26.5.1
Bumps [black](https://github.com/psf/black) from 25.9.0 to 26.5.1.
- [Release notes](https://github.com/psf/black/releases)
- [Changelog](https://github.com/psf/black/blob/main/CHANGES.md)
- [Commits](https://github.com/psf/black/compare/25.9.0...26.5.1)

---
updated-dependencies:
- dependency-name: black
  dependency-version: 26.5.1
  dependency-type: direct:development
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-09-01 21:45:23 +02:00
182 changed files with 5410 additions and 5250 deletions

View File

@@ -62,7 +62,7 @@ jobs:
python-version: "${{ env.PYTHON_VERSION }}"
- name: Setup QEMU
uses: docker/setup-qemu-action@1f40c72289eff860ee54a304f1438e3cff362e0a # v4.3.0
uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8 # v4.2.0
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
@@ -105,9 +105,8 @@ jobs:
arch: amd64
- runner: ubuntu-26.04-arm
arch: arm64
# FIXME: https://github.com/searxng/searxng/pull/6655#issuecomment-5550293085
# - runner: ubuntu-26.04-arm
# arch: armv7
- runner: ubuntu-26.04-arm
arch: armv7
steps:
- name: Login to GHCR
@@ -118,7 +117,7 @@ jobs:
password: "${{ secrets.GITHUB_TOKEN }}"
- name: Setup QEMU
uses: docker/setup-qemu-action@1f40c72289eff860ee54a304f1438e3cff362e0a # v4.3.0
uses: docker/setup-qemu-action@96fe6ef7f33517b61c61be40b68a1882f3264fb8 # v4.2.0
- name: Checkout
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1

File diff suppressed because it is too large Load Diff

View File

@@ -29,21 +29,21 @@
"swiped-events": "1.2.0"
},
"devDependencies": {
"@biomejs/biome": "2.5.11",
"@types/node": "^26.4.0",
"@biomejs/biome": "2.5.9",
"@types/node": "^26.2.0",
"browserslist": "^4.28.8",
"browserslist-to-esbuild": "^2.1.1",
"edge.js": "^6.5.1",
"less": "^4.9.0",
"mathjs": "^15.2.0",
"sharp": "~0.35.4",
"sharp": "~0.35.3",
"sort-package-json": "^4.0.0",
"stylelint": "^17.14.1",
"stylelint-config-standard-less": "^4.1.0",
"stylelint-prettier": "^5.0.3",
"svgo": "^4.1.0",
"svgo": "^4.0.2",
"typescript": "~7.0.2",
"vite": "^8.2.2",
"vite": "^8.2.1",
"vite-bundle-analyzer": "^1.3.9"
}
}

View File

@@ -58,9 +58,10 @@ engine is shown. Most of the options have a default value or even are optional.
# overwrite values from section 'outgoing:'
enable_http2: false
enable_http3: false
retries: 1
max_connections: 100
max_keepalive_connections: 10
keepalive_expiry: 5.0
using_tor_proxy: false
proxies:
http:
@@ -162,16 +163,6 @@ engine is shown. Most of the options have a default value or even are optional.
``enable_http`` : optional
Enable HTTP for this engine (by default only HTTPS is enabled).
``enable_http3`` : optional
Use HTTP/3 (falls back to HTTP/2). Default ``false``.
Ignored when a proxy is set.
.. hint::
HTTP/3 places demands on the IP infrastructure that are not met in every
environment. Enable this option only if you are aware of these requirements
and the extent to which they are met.
``retry_on_http_error`` : optional
Retry request on some HTTP status code.
@@ -188,12 +179,20 @@ engine is shown. Most of the options have a default value or even are optional.
Using tor proxy (``true``) or not (``false``) for this engine. The default is
taken from ``using_tor_proxy`` of the :ref:`settings outgoing`.
.. _Pool limit configuration: https://curl-cffi.readthedocs.io/en/latest/api.html#sessions
.. _Pool limit configuration: https://www.python-httpx.org/advanced/#pool-limit-configuration
``max_keepalive_connection#s`` :
`Pool limit configuration`_, overwrites value ``pool_maxsize`` from
:ref:`settings outgoing` for this engine.
``max_connections`` :
`Pool limit configuration`_, overwrites value ``pool_connections`` from
:ref:`settings outgoing` for this engine.
``keepalive_expiry`` :
`Pool limit configuration`_, overwrites value ``keepalive_expiry`` from
:ref:`settings outgoing` for this engine.
.. _private engines:

View File

@@ -12,12 +12,20 @@ Communication with search engines.
request_timeout: 2.0 # default timeout in seconds, can be override by engine
max_request_timeout: 10.0 # the maximum timeout in seconds
useragent_suffix: "" # information like an email address to the administrator
pool_connections: 100 # Maximum number of concurrent connections (default: 100)
enable_http2: true # Enables the use of HTTP2
pool_connections: 100 # Maximum number of allowable connections, or null
# for no limits. The default is 100.
pool_maxsize: 10 # Number of allowable keep-alive connections, or null
# to always allow. The default is 10.
enable_http2: true # See https://www.python-httpx.org/http2/
# uncomment below section if you want to use a custom server certificate
# see https://www.python-httpx.org/advanced/#changing-the-verification-defaults
# and https://www.python-httpx.org/compatibility/#ssl-configuration
# verify: ~/.mitmproxy/mitmproxy-ca-cert.cer
#
# uncomment below section if you want to use a proxy
# uncomment below section if you want to use a proxyq see: SOCKS proxies
# https://2.python-requests.org/en/latest/user/advanced/#proxies
# are also supported: see
# https://2.python-requests.org/en/latest/user/advanced/#socks
#
# proxies:
# all://:
@@ -38,26 +46,30 @@ Communication with search engines.
timeout to load). Can be override by ``timeout`` in the :ref:`settings engines`.
``useragent_suffix`` :
Suffix to add when an engine's User-Agent is set via searxng_useragent().
Contact info here may be useful to avoid an engine blocking you.
Suffix to the user-agent SearXNG uses to send requests to others engines. If an
engine wish to block you, a contact info here may be useful to avoid that.
.. _Pool limit configuration: https://curl-cffi.readthedocs.io/en/latest/api.html#sessions
.. _Pool limit configuration: https://www.python-httpx.org/advanced/#pool-limit-configuration
``pool_maxsize``:
Number of allowable keep-alive connections, or ``null`` to always allow. The
default is 10. See ``max_keepalive_connections`` `Pool limit configuration`_.
``pool_connections`` :
Maximum number of concurrent connections. The default is 100.
See ``max_clients`` `Pool limit configuration`_.
Maximum number of allowable connections, or ``null`` # for no limits. The
default is 100. See ``max_connections`` `Pool limit configuration`_.
.. _curl_cffi proxies: https://curl-cffi.readthedocs.io/en/latest/quick_start.html
``keepalive_expiry`` :
Number of seconds to keep a connection in the pool. By default 5.0 seconds.
See ``keepalive_expiry`` `Pool limit configuration`_.
.. _httpx proxies: https://www.python-httpx.org/advanced/#http-proxying
``proxies`` :
Define one or more proxies you wish to use, see `curl_cffi proxies`_.
Define one or more proxies you wish to use, see `httpx proxies`_.
If there are more than one proxy for one protocol (http, https),
requests to the engines are distributed in a round-robin fashion.
HTTP, HTTPS, SOCKS4, SOCKS5 and SOCKS5h proxies are supported
(``http://``, ``https://``, ``socks4://``, ``socks5://``, ``socks5h://``). You should
use ``socks5h://`` when using Tor so hostnames are resolved by the proxy.
``source_ips`` :
If you use multiple network interfaces, define from which IP the requests must
be made. Example:
@@ -75,15 +87,18 @@ Communication with search engines.
different proxy and source ip.
``enable_http2`` :
Enable by default (HTTP/2). Set to ``false`` to force HTTP/1.1.
HTTP/3 is opt-in per engine (``enable_http3``).
Enable by default. Set to ``false`` to disable HTTP/2.
.. _httpx verification defaults: https://www.python-httpx.org/advanced/#changing-the-verification-defaults
.. _httpx ssl configuration: https://www.python-httpx.org/compatibility/#ssl-configuration
``verify``: : ``$SSL_CERT_FILE``, ``$SSL_CERT_DIR``
HTTPS verification uses the OS's trust store by default.
Set a path to use a custom CA file.
Allow to specify a path to certificate.
see `httpx verification defaults`_.
In addition to ``verify``, SearXNG supports the ``$SSL_CERT_FILE`` (for a file) and
``$SSL_CERT_DIR`` (for a directory) OpenSSL variables.
see `httpx ssl configuration`_.
``max_redirects`` :
30 by default. Maximum redirect before it is an error.

View File

@@ -143,7 +143,7 @@ parameters with default value can be redefined for special purposes.
data dict ``{}``
cookies dict ``{}``
verify bool ``True``
headers.User-Agent str ``''``
headers.User-Agent str a random User-Agent
category str current category, like ``'general'``
safesearch int ``0``, between ``0`` and ``2`` (normal, moderate, strict)
time_range Optional[str] ``None``, can be ``day``, ``week``, ``month``, ``year``
@@ -229,8 +229,6 @@ following parameters can be used to specify a search request:
max_redirects int maximum redirects, hard limit
soft_max_redirects int maximum redirects, soft limit. Record an error but don't stop the engine
raise_for_httperror bool True by default: raise an exception if the HTTP code of response is >= 300
impersonate str curl_cffi impersonate target (default: chrome, none to disable)
curl_options dict Any extra libcurl options for the request
=================== =========== ==========================================================================

View File

@@ -0,0 +1,8 @@
.. _cara engine:
===========
Cara Images
===========
.. automodule:: searx.engines.cara
:members:

View File

@@ -286,7 +286,7 @@ content becomes smart.
files & folders origin :origin:`docs/dev/reST.rst` ``:origin:`docs/dev/reST.rst```
pull request :pull:`4` ``:pull:`4```
patch :patch:`af2cae6` ``:patch:`af2cae6```
PyPi package :pypi:`curl_cffi` ``:pypi:`curl_cffi```
PyPi package :pypi:`httpx` ``:pypi:`httpx```
manual page man :man:`bash` ``:man:`bash```
intersphinx_
--------------------------------------------------------------------------------------------------

View File

@@ -1,10 +1,10 @@
mock==5.2.0
nose2[coverage_plugin]==0.16.0
cov-core==1.15.0
black==25.9.0
pylint==4.0.8
black==26.5.1
pylint==4.0.7
splinter==0.21.0
selenium==4.48.0
selenium==4.47.0
Sphinx==8.2.3;python_version <= "3.11"
Sphinx==9.1.0; python_version > "3.11"
sphinx-issues==6.0.0

View File

@@ -7,11 +7,13 @@ lxml==6.1.2
pygments==2.21.0
python-dateutil==2.9.0.post0
pyyaml==6.0.3
curl_cffi==0.16.1
httpx[http2]==0.28.1
httpx-socks[asyncio]==0.13.1
sniffio==1.3.1
valkey==6.1.1
markdown-it-py==4.2.0
msgspec==0.21.1
typer==0.27.2
typer==0.27.1
isodate==0.7.2
whitenoise==6.12.0
typing-extensions==4.16.0

View File

@@ -1,5 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementation of the :py:obj:`preference <searx.preference>` settings."""
# pylint: disable = too-few-public-methods
import typing as t

View File

@@ -38,7 +38,6 @@ area:
"""
__all__ = ["AnswererInfo", "Answerer", "AnswerStorage"]

View File

@@ -13,7 +13,6 @@ from dataclasses import dataclass
from searx.utils import load_module
from searx.result_types.answer import BaseAnswer
_default = pathlib.Path(__file__).parent
log: logging.Logger = logging.getLogger("searx.answerers")

View File

@@ -11,7 +11,7 @@ from urllib.parse import urlencode
import lxml.etree
import lxml.html
from curl_cffi.requests.exceptions import RequestException
from httpx import HTTPError
from searx import settings
from searx.engines import (
@@ -63,7 +63,7 @@ def bing(query: str, _sxng_locale: str) -> list[str]:
base_url = "https://www.bing.com/AS/Suggestions?"
# cvid has to be a 32 character long string consisting of numbers and uppsercase characters
cvid = ''.join(random.choices(string.ascii_uppercase + string.digits, k=32))
response = get(base_url + urlencode({'qry': query, 'csr': 1, 'cvid': cvid}), enable_http3=True)
response = get(base_url + urlencode({'qry': query, 'csr': 1, 'cvid': cvid}))
results: list[str] = []
if response.ok:
@@ -83,7 +83,7 @@ def brave(query: str, _sxng_locale: str) -> list[str]:
url = 'https://search.brave.com/api/suggest?'
url += urlencode({'q': query})
country = 'all'
kwargs = {'cookies': {'country': country}, 'enable_http3': True}
kwargs = {'cookies': {'country': country}}
resp = get(url, **kwargs)
results: list[str] = []
@@ -147,7 +147,7 @@ def google_complete(query: str, sxng_locale: str) -> list[str]:
)
results: list[str] = []
resp = get('https://www.google.com/complete/search?' + args, enable_http3=True)
resp = get('https://www.google.com/complete/search?' + args)
if resp and resp.ok:
json_txt = resp.text[resp.text.find('[') : resp.text.find(']', -3) + 1]
data = json.loads(json_txt)
@@ -418,5 +418,5 @@ def search_autocomplete(backend_name: str, query: str, sxng_locale: str) -> list
return []
try:
return backend(query, sxng_locale)
except (RequestException, SearxEngineResponseException):
except (HTTPError, SearxEngineResponseException):
return []

View File

@@ -5,7 +5,6 @@ Implementations used for bot detection.
"""
__all__ = ["init", "dump_request", "get_network", "too_many_requests", "ProxyFix"]

View File

@@ -182,7 +182,7 @@ class Config:
if default is UNSET:
raise KeyError(name)
return default
(modulename, name) = str(fqn).rsplit('.', 1)
modulename, name = str(fqn).rsplit('.', 1)
m = __import__(modulename, {}, {}, [name], 0)
return getattr(m, name)

View File

@@ -13,7 +13,6 @@ Accept_ header ..
"""
from ipaddress import (
IPv4Network,
IPv6Network,

View File

@@ -14,7 +14,6 @@ bot if the Accept-Encoding_ header ..
"""
from ipaddress import (
IPv4Network,
IPv6Network,

View File

@@ -11,7 +11,6 @@ if the Accept-Language_ header is unset.
"""
from ipaddress import (
IPv4Network,
IPv6Network,

View File

@@ -11,7 +11,6 @@ the Connection_ header is set to ``close``.
"""
from ipaddress import (
IPv4Network,
IPv6Network,

View File

@@ -20,6 +20,7 @@ Metadata`_. A request is filtered out in case of:
"""
# pylint: disable=unused-argument

View File

@@ -12,7 +12,6 @@ the User-Agent_ header is unset or matches the regular expression
"""
import re
from ipaddress import (
IPv4Network,
@@ -25,7 +24,6 @@ import flask
from . import config
from ._helpers import too_many_requests
USER_AGENT = (
r'('
+ r'unknown'

View File

@@ -55,7 +55,6 @@ from ._helpers import (
logger,
)
logger = logger.getChild('ip_limit')
BURST_WINDOW = 20

View File

@@ -23,6 +23,7 @@ The ``ip_lists`` method implements :py:obj:`block-list <block_ip>` and
]
"""
# pylint: disable=unused-argument

View File

@@ -1,6 +1,7 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementation of a middleware to determine the real IP of an HTTP request
(:py:obj:`flask.request.remote_addr`) behind a proxy chain."""
# pylint: disable=too-many-branches

View File

@@ -1,7 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Providing a Valkey database for the botdetection methods."""
import valkey
__all__ = ["set_valkey_client", "get_valkey_client"]

View File

@@ -1,5 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Implementations needed for a branding of SearXNG."""
# pylint: disable=too-few-public-methods
# Struct fields aren't discovered in Python 3.14

View File

@@ -465,7 +465,7 @@ class ExpireCacheSQLite(sqlitedb.SQLiteAppl, ExpireCache):
# Check if value is expired. It's possible that it's expired but has not
# yet been automatically deleted by the periodic maintenance
(value, expire) = row
value, expire = row
now = time.time()
if expire < now:
# The record is deleted during the maintenance interval. Deleting

View File

@@ -3,7 +3,6 @@
import warnings
# limiter backward compatibility
# ------------------------------

View File

@@ -4,6 +4,7 @@
make data.all
"""
# pylint: disable=invalid-name
__all__ = ["ahmia_blacklist_loader", "data_dir", "get_cache"]

File diff suppressed because it is too large Load Diff

View File

@@ -1,5 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Simple implementation to store TrackerPatterns data in a SQL database."""
# pylint: disable=too-many-branches
import typing as t
@@ -10,7 +11,7 @@ import re
from collections.abc import Iterator
from urllib.parse import urlparse, urlunparse, parse_qsl, urlencode
from curl_cffi.requests.exceptions import RequestException
from httpx import HTTPError
from searx.data.core import get_cache, log
from searx.network import get as http_get
@@ -28,11 +29,11 @@ class TrackerPatternsDB:
ctx_name = "data_tracker_patterns"
# ClearURL rule lists, the first one that responds HTTP 200 is used
CLEAR_LIST_URL = [
"https://cdn.jsdelivr.net/gh/clearurls/rules@refs/heads/gh-pages/data.minify.json",
"https://rules2.clearurls.xyz/data.minify.json",
# ClearURL rule lists, the first one that responds HTTP 200 is used
"https://rules1.clearurls.xyz/data.minify.json",
"https://rules2.clearurls.xyz/data.minify.json",
"https://raw.githubusercontent.com/ClearURLs/Rules/refs/heads/master/data.min.json",
]
class Fields:
@@ -87,8 +88,8 @@ class TrackerPatternsDB:
try:
resp = http_get(url, timeout=3)
except RequestException as exc:
log.warning("TRACKER_PATTERNS: RequestException while fetching %s: %s", url, exc)
except HTTPError as exc:
log.warning("TRACKER_PATTERNS: HTTPError (%s) occured while fetching %s", url, exc)
continue
if resp.status_code != 200:

View File

@@ -305,7 +305,7 @@ class Engine(abc.ABC): # pylint: disable=too-few-public-methods
region: str = ""
"""For an engine, when there is ``region: ...`` in the YAML settings the engine
does support only this one region:
does support only this one region::
.. code:: yaml
@@ -317,9 +317,6 @@ class Engine(abc.ABC): # pylint: disable=too-few-public-methods
enable_http: bool
"""Enable HTTP (by default only HTTPS is enabled)."""
enable_http3: bool = False
"""Enables the use of HTTP/3 if available"""
shortcut: str
"""Code used to execute bang requests (``!foo``)"""

View File

@@ -6,8 +6,7 @@ from urllib.parse import urlencode
from datetime import datetime
from searx.exceptions import SearxEngineAPIException
from searx.result_types import EngineResults
from searx.utils import html_to_text
from searx.utils import html_to_text, get_embeded_stream_url
about = {
"website": "https://tv.360kan.com/",
@@ -30,12 +29,12 @@ def request(query, params):
return params
def response(resp) -> EngineResults:
def response(resp):
try:
data = resp.json()
except Exception as e:
raise SearxEngineAPIException(f"Invalid response: {e}") from e
res = EngineResults()
results = []
if "data" not in data or "result" not in data["data"]:
raise SearxEngineAPIException("Invalid response")
@@ -51,15 +50,16 @@ def response(resp) -> EngineResults:
except (ValueError, TypeError):
published_date = None
res.add(
res.types.LegacyResult(
url=entry["play_url"],
title=html_to_text(entry["title"]),
content=html_to_text(entry["description"]),
template='videos.html',
publishedDate=published_date,
thumbnail=entry["cover_img"],
)
results.append(
{
'url': entry["play_url"],
'title': html_to_text(entry["title"]),
'content': html_to_text(entry["description"]),
'template': 'videos.html',
'publishedDate': published_date,
'thumbnail': entry["cover_img"],
"iframe_src": get_embeded_stream_url(entry["play_url"]),
}
)
return res
return results

View File

@@ -26,7 +26,6 @@ categories: list[str]
disabled: bool
display_error_messages: bool
enable_http: bool
enable_http3: bool
engine_type: str
inactive: bool
max_page: int

View File

@@ -187,9 +187,8 @@ def set_loggers(engine: "Engine|types.ModuleType", engine_name: str):
def update_engine_attributes(engine: "Engine | types.ModuleType", engine_data: dict[str, t.Any]):
# pylint: disable=too-many-branches
# set / update engine attributes from engine_data
# set engine attributes from engine_data
kvargs: dict[str, t.Any]
engine.about = getattr(engine, "about", EngineAbout())
if isinstance(engine.about, EngineAbout):
kvargs = {**msgspec.to_builtins(engine.about), **engine_data.get("about", {})}
else:

View File

@@ -35,7 +35,7 @@ Implementation
==============
"""
import typing as t
from datetime import datetime, timedelta
from urllib.parse import urlencode
@@ -85,7 +85,7 @@ Additional subcategories:
# Do we need support for "free_collection" and "include_stock_enterprise"?
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if not categories:
raise ValueError("adobe_stock engine: categories is unset")
@@ -100,9 +100,9 @@ def setup(_: dict[str, t.Any]) -> bool | None:
raise ValueError("adobe_stock engine: adobe_content_types is unset")
if isinstance(adobe_content_types, list):
for content_type in adobe_content_types:
if content_type not in ADOBE_VALID_TYPES:
raise ValueError("adobe_stock engine: adobe_content_types: '%s' is invalid" % content_type)
for t in adobe_content_types:
if t not in ADOBE_VALID_TYPES:
raise ValueError("adobe_stock engine: adobe_content_types: '%s' is invalid" % t)
else:
raise ValueError(
"adobe_stock engine: adobe_content_types must be a list of strings not %s" % type(adobe_content_types)

View File

@@ -25,6 +25,7 @@ To use this engine, add an entry similar to the following to your engine list in
https://learn.microsoft.com/en-us/entra/identity-platform/quickstart-register-app
"""
import typing as t
from searx.enginelib import EngineCache

View File

@@ -49,9 +49,6 @@ CACHE: EngineCache
def setup(engine_settings: dict[str, t.Any]) -> bool:
if baidu_category not in ('general', 'images', 'it'):
raise SearxEngineAPIException(f"Unsupported category: {baidu_category}")
global CACHE # pylint: disable=global-statement
CACHE = EngineCache(engine_settings["name"])
return True
@@ -68,6 +65,11 @@ def get_image_cookies(headers: dict[str, str]) -> dict[str, str]:
return cookies
def init(_):
if baidu_category not in ('general', 'images', 'it'):
raise SearxEngineAPIException(f"Unsupported category: {baidu_category}")
def request(query, params):
page_num = params["pageno"]

View File

@@ -1,5 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""BASE (Scholar publications)"""
from datetime import datetime
import re

View File

@@ -40,7 +40,6 @@ about: dict[str, t.Any] = {
# engine dependent config
categories = ["general", "web"]
safesearch = True
enable_http3 = True
_safesearch_map: dict[int, str] = {
0: "off",
1: "moderate",

View File

@@ -25,7 +25,6 @@ about = {
# engine dependent config
categories = ["images", "web"]
paging = True
enable_http3 = True
safesearch = True
time_range_support = True
time_map = {

View File

@@ -33,7 +33,6 @@ categories = ["news"]
paging = True
"""If go through the pages and there are actually no new results for another
page, then bing returns the results from the last page again."""
enable_http3 = True
time_range_support = True
time_map = {

View File

@@ -26,7 +26,6 @@ about = {
# engine dependent config
categories = ["videos", "web"]
paging = True
enable_http3 = True
safesearch = True
time_range_support = True

View File

@@ -45,7 +45,7 @@ CACHE_SESSION_ID_KEY = "session_id_key"
KEYWORD_RE = re.compile(r"\[\/?Keyword\]")
def setup(engine_settings: dict[str, t.Any]) -> bool:
def init(engine_settings: dict[str, t.Any]) -> bool:
global CACHE # pylint: disable=global-statement
CACHE = EngineCache(engine_name=engine_settings["name"])
return True

View File

@@ -135,7 +135,7 @@ from searx.utils import (
eval_xpath_getindex,
eval_xpath_list,
extract_text,
get_embedded_stream_url,
get_embeded_stream_url,
js_obj_str_to_json_str,
js_obj_str_to_python,
)
@@ -151,7 +151,6 @@ about = {
base_url = "https://search.brave.com/"
categories = []
enable_http3 = True
brave_category: t.Literal["search", "videos", "images", "news", "goggles"] = "search"
"""Brave supports common web-search, videos, images, news, and goggles search.
@@ -248,13 +247,13 @@ def extract_json_data(text: str) -> dict[str, t.Any]:
# node_ids: [0, 19],
# data: [{type:"data",data: .... ["q","goggles_id"],route:1,url:1}}]
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# form: null,
# error: null
# });
text = text[text.index("<script") : text.index("</script")]
if not text:
raise ValueError("can't find JS/JSON data in the given text")
start = text.index("data: [{")
newline = text.index("\n", start)
end = text.rindex("}}]", start, newline)
js_obj_str = "{" + text[start:end] + "}}]}"
end = text.rindex("}}]")
js_obj_str = text[start:end]
js_obj_str = "{" + js_obj_str + "}}]}"
# js_obj_str = js_obj_str.replace("\xa0", "") # remove ASCII for &nbsp;
# js_obj_str = js_obj_str.replace(r"\u003C", "<").replace(r"\u003c", "<") # fix broken HTML tags in strings
json_str = js_obj_str_to_json_str(js_obj_str)
@@ -339,7 +338,7 @@ def _parse_search(resp: SXNG_Response) -> EngineResults:
if len(video_tag):
# In my tests a video tag in the WEB search was most often not a
# video, except the ones from youtube ..
iframe_src = get_embedded_stream_url(url)
iframe_src = get_embeded_stream_url(url)
if iframe_src:
item["iframe_src"] = iframe_src
item["template"] = "videos.html"
@@ -354,14 +353,14 @@ def _parse_news(resp: SXNG_Response) -> EngineResults:
res = EngineResults()
dom = html.fromstring(resp.text)
for result in eval_xpath_list(dom, "//div[@data-type='news']"):
url = eval_xpath_getindex(result, ".//a/@href", 0, default=None)
for result in eval_xpath_list(dom, "//div[contains(@class, 'results')]//div[@data-type='news']"):
url = eval_xpath_getindex(result, ".//a[contains(@class, 'result-header')]/@href", 0, default=None)
if url is None:
continue
title = eval_xpath_list(result, ".//div[contains(@class, 'title')]")
content = eval_xpath_list(result, ".//div[contains(@class, 'description')]")
thumbnail = eval_xpath_getindex(result, ".//a[contains(@class, 'thumbnail')]//img/@src", 0, default="")
title = eval_xpath_list(result, ".//span[contains(@class, 'snippet-title')]")
content = eval_xpath_list(result, ".//p[contains(@class, 'desc')]")
thumbnail = eval_xpath_getindex(result, ".//div[contains(@class, 'image-wrapper')]//img/@src", 0, default="")
item = res.types.LegacyResult(
template="default.html",
@@ -407,6 +406,9 @@ def _parse_videos(json_resp: dict[str, t.Any]) -> EngineResults:
)
if result["thumbnail"] is not None:
item["thumbnail"] = result["thumbnail"]["src"]
iframe_src = get_embeded_stream_url(result["url"])
if iframe_src:
item["iframe_src"] = iframe_src
res.add(item)

View File

@@ -40,7 +40,7 @@ if t.TYPE_CHECKING:
about = {
"website": "https://api.search.brave.com/",
"wikidata_id": None,
"official_api_documentation": "https://api-dashboard.search.brave.com/api-reference/web/search/get",
"official_api_documentation": "https://api-dashboard.search.brave.com/documentation",
"use_official_api": True,
"require_api_key": True,
"results": "JSON",
@@ -63,10 +63,8 @@ base_url = "https://api.search.brave.com/res/v1/web/search"
time_range_map = {"day": "past_day", "week": "past_week", "month": "past_month", "year": "past_year"}
"""Mapping of SearXNG time ranges to Brave API time ranges."""
max_page = 10
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
"""Initialize the engine."""
if not api_key:
raise SearxEngineAPIException("No API key provided")
@@ -77,7 +75,7 @@ def request(query: str, params: "OnlineParams") -> None:
search_args: dict[str, str | int | None] = {
"q": query,
"count": results_per_page,
"offset": params["pageno"] - 1,
"offset": (params["pageno"] - 1) * results_per_page,
"text_decorations": False,
}
@@ -91,7 +89,6 @@ def request(query: str, params: "OnlineParams") -> None:
params["url"] = f"{base_url}?{urlencode(search_args)}"
params["headers"]["X-Subscription-Token"] = api_key
params["headers"]["Accept"] = "application/json"
def _extract_published_date(published_date_raw: str):

85
searx/engines/cara.py Normal file
View File

@@ -0,0 +1,85 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
# pylint: disable=invalid-name
"""Cara_ is a social media and portfolio-sharing platform for artists and art
enthusiasts.
With the widespread use of generative AI, Cara_ decided to build a place that
filters out gen AI images so that people searching for authentic creatives and
images can do so easily.
.. _Cara: https://cara.app/about
"""
from urllib.parse import urlencode
import typing as t
from searx.result_types import EngineResults
if t.TYPE_CHECKING:
from searx.extended_types import SXNG_Response
from searx.search.processors import OnlineParams
about = {
"website": "https://cara.app",
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
}
base_url = "https://cara.app"
images_url = "https://images.cara.app"
categories = ["images"]
paging = True
results_per_page = 24
# if using HTTP2, we get blocked immediately
enable_http2 = False
def request(query: str, params: "OnlineParams") -> None:
args = {
"q": query,
"sortBy": "Top",
"take": results_per_page,
"skip": (params["pageno"] - 1) * results_per_page,
}
params["url"] = f"{base_url}/api/search/portfolio-posts?{urlencode(args)}"
def response(resp: "SXNG_Response"):
res = EngineResults()
json_data: list[dict[str, t.Any]] = resp.json()
for result in json_data:
thumbnail, img = None, None
i: dict[str, str]
for i in result["images"]:
if thumbnail is None or i["isCoverImg"]:
thumbnail = i
if img is None or not i["isCoverImg"]:
img = i
if not thumbnail or not img:
continue
res.add(
res.types.LegacyResult(
{
"template": "images.html",
"url": f"{base_url}/post/{result['id']}",
"thumbnail_src": f"{images_url}/{thumbnail['src']}?height=256",
"img_src": f"{images_url}/{img['src']}",
"title": result["title"],
"content": result["content"],
"author": result["name"],
}
)
)
return res

View File

@@ -41,7 +41,7 @@ search_index = "cw22"
<https://www.chatnoir.eu/docs/api-general>`_ for a full list."""
def _obtain_api_key() -> tuple[str, str]:
def _obtain_api_key() -> tuple[str, str, str]:
home_resp = get(base_url)
if not home_resp.ok:
raise SearxEngineAPIException("failed to obtain api key")
@@ -58,9 +58,10 @@ def _obtain_api_key() -> tuple[str, str]:
)
if not token_resp.ok:
raise SearxEngineAPIException("failed to obtain api key")
session_id = token_resp.cookies["sessionid"]
scraped_api_key = token_resp.json()["token"]["token"]
return csrf_token, scraped_api_key
return csrf_token, session_id, scraped_api_key
def request(query: str, params: "OnlineParams"):
@@ -72,7 +73,7 @@ def request(query: str, params: "OnlineParams"):
params["headers"].update(headers)
else:
csrf_token, scraped_api_key = _obtain_api_key()
csrf_token, session_id, scraped_api_key = _obtain_api_key()
headers = {
"Authorization": f"Bearer {scraped_api_key}",
@@ -80,11 +81,10 @@ def request(query: str, params: "OnlineParams"):
}
params["headers"].update(headers)
params["cookies"] = {"csrftoken": csrf_token}
params["cookies"] = {"csrftoken": session_id, "sessionid": session_id}
params["url"] = f"{base_url}/api/v1/_search"
params["method"] = "POST"
params["impersonate"] = "none"
json_data = {
"query": query,

View File

@@ -78,7 +78,7 @@ time_range_dict = {'day': '24h', 'week': '1w', 'month': '1m', 'year': '1y'}
base_url = "https://www.chinaso.com"
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if chinaso_news_source not in t.get_args(ChinasoNewsSourceType):
raise ValueError(f"Unsupported news source: {chinaso_news_source}")

View File

@@ -74,7 +74,6 @@ Implementations
===============
"""
import typing as t
import re
from os.path import expanduser, isabs, realpath, commonprefix
from shlex import split as shlex_split
@@ -84,7 +83,6 @@ from threading import Thread
from searx import logger
from searx.result_types import EngineResults
engine_type = 'offline'
paging = True
command = []
@@ -101,7 +99,7 @@ _command_logger = logger.getChild('command')
_compiled_parse_regex = {}
def setup(engine_settings: dict[str, t.Any]) -> bool | None:
def init(engine_settings):
check_parsing_options(engine_settings)
if 'command' not in engine_settings:

View File

@@ -1,5 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Docker Hub (IT)"""
# pylint: disable=use-dict-literal
from urllib.parse import urlencode

View File

@@ -8,9 +8,6 @@ import typing as t
from datetime import datetime, timezone
import html
from searx.enginelib import EngineCache
from searx.exceptions import SearxEngineAPIException
from searx.network import post
from searx.utils import format_duration, html_to_text, humanize_number
from searx.result_types import EngineResults
@@ -38,36 +35,15 @@ dogpile_categ = "search"
base_url = "https://www.dogpile.com"
safe_search_map = {0: "none", 1: "moderate", 2: "heavy"}
CACHE: EngineCache
"""Cache for the API token from dogpile"""
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if dogpile_categ not in ("search", "images", "videos", "news"):
raise ValueError("invalid search type: %s" % dogpile_categ)
global CACHE # pylint: disable=global-statement
CACHE = EngineCache("dogpile") # one token for images/videos/news
return True
def _obtain_token() -> str:
token = CACHE.get("token")
if token:
return token
resp = post(f"{base_url}/api/token/refresh", headers={"Origin": base_url}, cookies={"dp_api_token": "1"})
if not resp.ok:
raise SearxEngineAPIException("failed to obtain dogpile token")
token = resp.json()["token"]
CACHE.set("token", token, expire=240) # 300s ttl
return token
def request(query: str, params: "OnlineParams"):
params["url"] = f"{base_url}/api/{dogpile_categ}"
params["headers"]["Origin"] = base_url
params["cookies"]["dp_api_token"] = "1"
if dogpile_categ != "search": # web doesnt need token
params["headers"]["x-dogpile-token"] = _obtain_token()
params["method"] = "POST"
params["json"] = {"q": query, "qadf": safe_search_map[params["safesearch"]], "page": params["pageno"]}

View File

@@ -164,6 +164,7 @@ Terms / phrases that you keep coming across:
https://developer.mozilla.org/en-US/docs/Web/HTTP/Reference/Headers/Accept-Language
"""
# pylint: disable=global-statement
import json

View File

@@ -12,6 +12,7 @@ least we could not find out how language support should work. It seems that
most of the features are based on English terms.
"""
import typing as t
from urllib.parse import urlencode, urlparse, urljoin

View File

@@ -10,8 +10,7 @@ from datetime import datetime
from urllib.parse import urlencode
from urllib.parse import quote_plus
from searx.result_types import EngineResults, MainResult, LegacyResult, Image
from searx.utils import html_to_text, gen_useragent, extr
from searx.utils import get_embeded_stream_url, html_to_text, gen_useragent, extr
from searx.network import get # see https://github.com/searxng/searxng/issues/762
from searx.engines.duckduckgo import fetch_traits # pylint: disable=unused-import
@@ -48,7 +47,7 @@ _HTTP_User_Agent: str = gen_useragent()
send_accept_language_header = False
def setup(engine_settings: dict[str, t.Any]) -> bool | None:
def init(engine_settings: dict[str, t.Any]):
if engine_settings["ddg_category"] not in ["images", "videos", "news"]:
raise ValueError(f"Unsupported DuckDuckGo category: {engine_settings['ddg_category']}")
@@ -98,7 +97,6 @@ def request(query: str, params: "OnlineParams") -> None:
# The vqd value is generated from the query and the UA header. To be able to
# reuse the vqd value, the UA header must be static.
headers["User-Agent"] = _HTTP_User_Agent
params["impersonate"] = "none"
vqd = get_vqd(query=query, params=params) or fetch_vqd(query=query, params=params)
headers["Accept"] = "*/*"
@@ -150,51 +148,54 @@ def request(query: str, params: "OnlineParams") -> None:
def _image_result(result):
return Image(
url=result['url'],
title=result['title'],
content='',
thumbnail_src=result['thumbnail'],
img_src=result['image'],
resolution='%s x %s' % (result['width'], result['height']),
source=result['source'],
)
return {
'template': 'images.html',
'url': result['url'],
'title': result['title'],
'content': '',
'thumbnail_src': result['thumbnail'],
'img_src': result['image'],
'resolution': '%s x %s' % (result['width'], result['height']),
'source': result['source'],
}
def _video_result(result):
return LegacyResult(
template='videos.html',
url=result['content'],
title=result['title'],
content=result['description'],
thumbnail=result['images'].get('small') or result['images'].get('medium'),
source=result['provider'],
length=result['duration'],
metadata=result.get('uploader'),
)
return {
'template': 'videos.html',
'url': result['content'],
'title': result['title'],
'content': result['description'],
'thumbnail': result['images'].get('small') or result['images'].get('medium'),
'iframe_src': get_embeded_stream_url(result['content']),
'source': result['provider'],
'length': result['duration'],
'metadata': result.get('uploader'),
}
def _news_result(result):
return MainResult(
url=result['url'],
title=result['title'],
content=html_to_text(result['excerpt']),
publishedDate=datetime.fromtimestamp(result['date']),
)
return {
'url': result['url'],
'title': result['title'],
'content': html_to_text(result['excerpt']),
'source': result['source'],
'publishedDate': datetime.fromtimestamp(result['date']),
}
def response(resp: "SXNG_Response") -> EngineResults:
res = EngineResults()
def response(resp):
results = []
res_json = resp.json()
for result in res_json['results']:
if ddg_category == 'images':
res.add(_image_result(result))
results.append(_image_result(result))
elif ddg_category == 'videos':
res.add(_video_result(result))
results.append(_video_result(result))
elif ddg_category == 'news':
res.add(_news_result(result))
results.append(_news_result(result))
else:
raise ValueError(f"Invalid duckduckgo category: {ddg_category}")
return res
return results

View File

@@ -17,7 +17,6 @@ from searx.result_types import EngineResults
from searx.extended_types import SXNG_Response
from searx import weather
about = {
"website": 'https://duckduckgo.com/',
"wikidata_id": 'Q12805',
@@ -109,19 +108,7 @@ def response(resp: SXNG_Response):
json_data = loads(resp.text[resp.text.find('\n') + 1 : resp.text.rfind('\n') - 2])
location = json_data.get("location")
if not location:
return res
metadata = json_data.get("weatherAlerts", {}).get("metadata", {})
geoloc = weather.GeoLocation(
name=location,
latitude=metadata.get("latitude"),
longitude=metadata.get("longitude"),
elevation=0,
country_code=metadata.get("language").split("-")[-1],
timezone=json_data.get("location"),
)
geoloc = weather.GeoLocation.by_query(resp.search_params["query"])
weather_answer = EngineResults.types.WeatherAnswer(
current=_weather_data(geoloc, json_data["currentWeather"]),

View File

@@ -2,7 +2,6 @@
# pylint: disable=invalid-name
"""Dummy Offline"""
# about
about = {
"wikidata_id": None,

View File

@@ -41,7 +41,6 @@ authentication configured to read from ``my-index`` index.
"""
import typing as t
from json import loads, dumps
from searx.exceptions import SearxEngineAPIException
from searx.result_types import EngineResults
@@ -69,7 +68,7 @@ show_metadata = False
page_size = 10
def setup(engine_settings: dict[str, t.Any]) -> bool | None:
def init(engine_settings):
if 'query_type' in engine_settings and engine_settings['query_type'] not in _available_query_types:
raise ValueError('unsupported query type', engine_settings['query_type'])

View File

@@ -78,7 +78,7 @@ content_max_characters: int = 500
"""Maximum characters for the requested content."""
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if not api_key:
raise SearxEngineAPIException("No API key provided")
if not 1 <= results_per_page <= 100:

View File

@@ -47,7 +47,7 @@ CACHE_VALID_DURATION = 30 * 24 * 3600 # one month, same as website
"""Duration how long settings cookies are valid."""
def setup(engine_settings: dict[str, t.Any]) -> bool | None:
def init(engine_settings: dict[str, t.Any]):
global CACHE # pylint: disable=global-statement
CACHE = EngineCache(engine_settings["name"])

View File

@@ -38,7 +38,6 @@ Implementation
"""
import typing as t
from urllib.parse import urlencode
from dateutil import parser
@@ -78,7 +77,7 @@ page_size: int = 10
"""Maximum number of results per page (default 10)."""
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if not base_url:
raise ValueError('gitea engine: base_url is unset')

View File

@@ -65,7 +65,6 @@ code lines are just relabeled (starting from 1) and appended (a disjoint set of
code blocks in a single file might be returned from the API).
"""
import typing as t
from urllib.parse import urlencode

View File

@@ -327,7 +327,6 @@ def google_request(
params["url"] = f"https://www.google.com/wml/search?{urlencode(args)}"
params["headers"]["User-Agent"] = random.choice(nokia_useragents)
params["impersonate"] = "chrome99_android"
def request(query: str, params: "OnlineParams") -> None:

View File

@@ -30,7 +30,6 @@ about = {
categories = ["general", "web"]
paging = True
enable_http3 = True
max_page = 5
page_size = 20
time_range_support = True

View File

@@ -26,7 +26,6 @@ about = {
# engine dependent config
categories = ["images", "web"]
paging = True
enable_http3 = True
max_page = 50
"""Google supports up to 50 pages of results, see the `Google max_page discussion`_.

View File

@@ -20,7 +20,6 @@ about = {
}
play_categ = None # apps|movies
enable_http3 = True
base_url = 'https://play.google.com'
search_url = base_url + "/store/search?{query}&c={play_categ}"

View File

@@ -27,7 +27,7 @@ import typing as t
from urllib.parse import urlencode
from datetime import datetime
from lxml import html
from curl_cffi.requests.exceptions import TooManyRedirects
import httpx
from searx.utils import (
eval_xpath,
@@ -63,7 +63,6 @@ about = {
# engine dependent config
categories = ["science", "scientific publications"]
paging = True
enable_http3 = True
max_page = 50
"""`Google max 50 pages`_
@@ -103,7 +102,7 @@ def response(resp: "SXNG_Response") -> EngineResults: # pylint: disable=too-man
raise SearxEngineAccessDeniedException(
message="google_scholar: unusual traffic detected",
)
raise TooManyRedirects(f"location {resp.headers['Location'].split('?')[0]}")
raise httpx.TooManyRedirects(f"location {resp.headers['Location'].split('?')[0]}")
res = EngineResults()
dom = html.fromstring(resp.text)

View File

@@ -10,6 +10,7 @@ from searx.utils import (
eval_xpath_getindex,
eval_xpath_list,
extract_text,
get_embeded_stream_url,
parse_duration_string,
)
@@ -78,6 +79,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
title=title,
thumbnail=thumbnail,
length=length,
iframe_src=get_embeded_stream_url(url) or "",
template="videos.html",
)
)

127
searx/engines/heexy.py Normal file
View File

@@ -0,0 +1,127 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Heexy_ is a minimalist search engine that focuses on privacy.
Although it also supports news and videos, these are not implemented here
because they usually return no result to very few irrelevant ones.
It seems to use Bing internally, as the image thumbnails are loaded from Bing.
.. _Heexy: https://docs.heexy.org/introduction
"""
from urllib.parse import urlencode
import typing as t
from searx.enginelib import EngineCache
from searx.network import get
from searx.exceptions import SearxEngineAPIException, SearxEngineAccessDeniedException
from searx.result_types import EngineResults
from searx.utils import gen_useragent
if t.TYPE_CHECKING:
from searx.extended_types import SXNG_Response
from searx.search.processors import OnlineParams
about = {
"website": "https://heexy.org",
"wikidata_id": None,
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
}
paging = True
safesearch = True
categories = ["general"]
heexy_categ = "web"
"""Category to search in. Can be either "web" or "image"."""
base_url = "https://heexy.org"
api_url = "https://seapi.heexy.org"
safe_search_map = {0: "off", 1: "on", 2: "on"}
CACHE: EngineCache
"""Cache for storing the ``X-Data-Cacheft`` token (acts like an API key)."""
def setup(engine_settings: dict[str, t.Any]) -> bool:
global CACHE # pylint: disable=global-statement
if heexy_categ not in ("web", "image"):
raise ValueError("invalid search category: %s" % heexy_categ)
CACHE = EngineCache(engine_settings["name"])
return True
def _get_api_token(query: str) -> str:
"""The API token is independent of the search query. We just need any query
to obtain it initially, and don't hardcode it here to decrease chances of
getting blocked. The token must be passed as ``X-Data-Cacheft`` header."""
cached_token: str = CACHE.get("token")
if cached_token:
return cached_token
resp = get(
f"{base_url}/search?q={query}", headers={"User-Agent": gen_useragent(), "Accept-Language": "en-US,en:q=0.9"}
)
if not resp.ok:
raise SearxEngineAPIException("failed to obtain request token: invalid response code")
token = resp.cookies["cacheft"]
if not token:
raise SearxEngineAPIException("failed to obtain request token: no token found")
CACHE.set("token", token, expire=3 * 60)
return token
def request(query: str, params: "OnlineParams") -> None:
args = {
"q": query,
"page": params["pageno"],
"safe": safe_search_map[params["safesearch"]],
}
if params["searxng_locale"] != "all":
args["lang"] = params["searxng_locale"].split("-")[0]
params["url"] = f"{api_url}/search/{heexy_categ}?{urlencode(args)}"
params["headers"]["Origin"] = api_url
params["cookies"]["cacheft"] = _get_api_token(query)
def response(resp: "SXNG_Response"):
res = EngineResults()
json_resp = resp.json()
if not json_resp["success"]:
raise SearxEngineAccessDeniedException()
result: dict[str, str]
for result in json_resp["results"]:
if heexy_categ == "web":
res.add(
res.types.MainResult(
url=result["url"],
title=result["title"],
content=result["description"],
)
)
elif heexy_categ == "image":
res.add(
res.types.Image(
title=result["description"],
url=result["url"],
thumbnail_src=result["image"],
img_src=result["rawImage"],
)
)
return res

View File

@@ -4,7 +4,6 @@
from urllib.parse import urlencode
from dateutil import parser
about = {
# pylint: disable=line-too-long
"website": "https://hex.pm/",

View File

@@ -33,7 +33,6 @@ Implementations
"""
import typing as t
from urllib.parse import urlencode
from datetime import datetime
@@ -63,7 +62,7 @@ huggingface_endpoint = 'models'
"""
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if huggingface_endpoint not in ('datasets', 'models', 'spaces'):
raise SearxEngineAPIException(f"Unsupported Hugging Face endpoint: {huggingface_endpoint}")

View File

@@ -8,7 +8,6 @@ No public instance offer a public API now
"""
import typing as t
import time
import random
from urllib.parse import quote_plus, urlparse
@@ -35,7 +34,7 @@ time_range_support = True
base_url: list[str] | str = []
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if not base_url:
raise ValueError("missing invidious base_url")

View File

@@ -108,14 +108,12 @@ def get_infobox(alt_forms, result_url, definitions):
infobox_content.append(f'<p><i>Other forms:</i> {", ".join(alt_forms[1:])}</p>')
# definitions
infobox_content.append(
'''
infobox_content.append('''
<small><a href="https://www.edrdg.org/wiki/index.php/JMdict-EDICT_Dictionary_Project">JMdict</a>
and <a href="https://www.edrdg.org/enamdict/enamdict_doc.html">JMnedict</a>
by <a href="https://www.edrdg.org/edrdg/licence.html">EDRDG</a>, CC BY-SA 3.0.</small>
<ul>
'''
)
''')
for pos, engdef, extra in definitions:
if pos == 'Wikipedia definition':
infobox_content.append('</ul><small>Wikipedia, CC BY-SA 3.0.</small><ul>')

View File

@@ -87,7 +87,7 @@ api_key = ""
"""Kagi API key. Required for using this engine."""
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if not api_key:
raise ValueError("api_key is required for using kagi")

View File

@@ -37,17 +37,21 @@ about = {
}
categories = []
safesearch = True
safeseach = True
base_url = "https://luxxle.com"
luxxle_categ = "search"
"""Supported categories: "search", "news", "images", "videos"."""
# otherwise all requests get blocked (http2-fingerprinted probably)
enable_http2 = False
safe_search_map = {0: "Off", 1: "Moderate", 2: "Strict"}
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if luxxle_categ not in ("search", "images", "videos", "news"):
raise ValueError("invalid luxxle category: %s" % luxxle_categ)

View File

@@ -10,7 +10,7 @@ Lofgren .
.. _marginalia filters:
Marginalia Filters
==================
=================
Custom filters enable server-side customization of Marginalia search results.
Filter definitions are written in XML and scoped to an API key. Filters can
@@ -82,7 +82,7 @@ api_key = None
https://about.marginalia-search.com/article/api/
"""
filter_name: str = ""
filter_name: str | None = None
"""The name of the custom filter to apply to each search."""
@@ -164,7 +164,7 @@ def response(resp: SXNG_Response):
return res
def setup(_: dict[str, t.Any]) -> bool:
def init(_: dict[str, t.Any]):
if not api_key:
logger.error("missing api_key: see https://about.marginalia-search.com/article/api")

View File

@@ -26,8 +26,6 @@ Implementations
"""
import typing as t
try:
import mariadb # pyright: ignore [reportMissingImports]
except ImportError:
@@ -62,17 +60,15 @@ paging = True
_connection = None
def setup(engine_settings: dict[str, t.Any]) -> bool | 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')
def init(_):
global _connection # pylint: disable=global-statement
_connection = mariadb.connect(database=database, user=username, password=password, host=host, port=port)

View File

@@ -35,7 +35,7 @@ Here is a simple example to query a Meilisearch instance:
"""
# pylint: disable=global-statement
import typing as t
from json import dumps
from searx.result_types import EngineResults
from searx.extended_types import SXNG_Response
@@ -49,7 +49,7 @@ categories = ['general']
paging = True
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if index == '':
raise ValueError('index cannot be empty')

View File

@@ -1,7 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Mojeek (general, images, news)"""
import typing as t
from datetime import datetime
from urllib.parse import urlencode
@@ -52,7 +51,7 @@ region_param = "arc"
_delta_kwargs = {"day": "days", "week": "weeks", "month": "months", "year": "years"}
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if search_type not in ("", "images", "news"):
raise ValueError(f"Invalid search type {search_type}")

View File

@@ -49,7 +49,6 @@ except ImportError:
from searx.result_types import EngineResults
engine_type = 'offline'
# mongodb connection variables

View File

@@ -19,7 +19,6 @@ Implementation
==============
"""
import typing as t
from urllib.parse import quote_plus
about = {
@@ -38,7 +37,7 @@ matrix_url = "https://matrix.to"
page_size = 20
def setup(_: dict[str, t.Any]) -> bool | None:
def init(engine_settings): # pylint: disable=unused-argument
"""The ``base_url`` must be set in the configuration, if ``base_url`` is not
set, a :py:obj:`ValueError` is raised during initialization.

View File

@@ -25,8 +25,6 @@ Implementations
"""
import typing as t
from searx.result_types import EngineResults
try:
@@ -62,17 +60,15 @@ paging = True
_connection = None
def setup(engine_settings: dict[str, t.Any]) -> bool | 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')
def init(_):
global _connection # pylint: disable=global-statement
_connection = mysql.connector.connect(
database=database,
user=username,

View File

@@ -2,8 +2,6 @@
# pylint: disable=line-too-long
"""Naver for SearXNG"""
import typing as t
from urllib.parse import urlencode
from lxml import html
@@ -18,6 +16,7 @@ from searx.utils import (
html_to_text,
parse_duration_string,
js_obj_str_to_python,
get_embeded_stream_url,
)
# engine metadata
@@ -68,7 +67,7 @@ naver_category_dict = {
}
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if naver_category not in ('general', 'images', 'news', 'videos'):
raise SearxEngineAPIException(f"Unsupported category: {naver_category}")
@@ -194,7 +193,7 @@ def parse_news(data):
def parse_videos(data):
res = EngineResults()
results = []
dom = html.fromstring(data)
@@ -213,14 +212,15 @@ def parse_videos(data):
except (ValueError, TypeError):
pass
res.add(
res.types.LegacyResult(
template="videos.html",
title=extract_text(eval_xpath(item, ".//a[contains(@class, 'info_title')]")),
url=url,
thumbnail=thumbnail,
length=length,
)
results.append(
{
"template": "videos.html",
"title": extract_text(eval_xpath(item, ".//a[contains(@class, 'info_title')]")),
"url": url,
"thumbnail": thumbnail,
"length": length,
"iframe_src": get_embeded_stream_url(url),
}
)
return res
return results

View File

@@ -6,14 +6,10 @@
from json import loads
import typing as t
from urllib.parse import urlencode
from lxml import html
from searx.exceptions import SearxEngineAPIException
from searx.extended_types import SXNG_Response
from searx.network import get
from searx.result_types import EngineResults
from searx.utils import eval_xpath, extract_text
if t.TYPE_CHECKING:
from searx.enginelib.traits import EngineTraits
@@ -29,33 +25,18 @@ about = {
"results": "JSON",
}
paging = False
enable_http3 = True
base_url = "https://neosearch.org"
categories = ["general"]
def _obtain_xsrf_token() -> str:
resp = get(base_url)
doc = html.fromstring(resp.text)
xsrf_token = extract_text(eval_xpath(doc, "//meta[@name='xsrf-token']/@content"))
if not xsrf_token:
raise SearxEngineAPIException("failed to obtain xsrf token")
return xsrf_token
paging = False
def request(query: str, params: "OnlineParams"):
params["url"] = f"{base_url}/search"
params["headers"]["X-XSRF-TOKEN"] = _obtain_xsrf_token()
params["method"] = "POST"
args = {"q": query, "generate": "auto"}
countrycode = params["searxng_locale"].split("-")[-1].upper()
if countrycode in traits.custom["countrycodes"]:
args["loc"] = countrycode
params["json"] = args
params["url"] = f"{base_url}/search?{urlencode(args)}"
def response(resp: "SXNG_Response") -> EngineResults:
@@ -86,6 +67,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
def fetch_traits(engine_traits: "EngineTraits") -> None:
# pylint: disable=import-outside-toplevel
from searx.network import get
from searx.utils import extr, js_obj_str_to_python
from babel.core import get_global

View File

@@ -4,7 +4,6 @@
from urllib.parse import urlencode
from dateutil import parser
about = {
"website": "https://npms.io/",
"wikidata_id": "Q7067518",

View File

@@ -9,7 +9,6 @@ from datetime import datetime
from searx.result_types import EngineResults, WeatherAnswer
from searx import weather
about = {
"website": "https://open-meteo.com",
"wikidata_id": None,

View File

@@ -8,7 +8,6 @@ Openverse (formerly known as: Creative Commons search engine) [Images]
from json import loads
from urllib.parse import urlencode
about = {
"website": 'https://openverse.org/',
"wikidata_id": None,

View File

@@ -2,18 +2,16 @@
"""Pexels (images)"""
import re
import typing as t
from urllib.parse import urlencode
from lxml import html
from searx.result_types import EngineResults
from searx.utils import eval_xpath_list
from searx.utils import eval_xpath_list, gen_useragent
from searx.enginelib import EngineCache
from searx.exceptions import SearxEngineAPIException, SearxEngineAccessDeniedException
from searx.network import get
# about
about = {
"website": 'https://www.pexels.com',
@@ -44,17 +42,24 @@ SECRET_KEY_DB_KEY = "secret-key"
CACHE: EngineCache
"""Cache to store the secret API key for the engine."""
enable_http2 = False
def setup(engine_settings: dict[str, t.Any]) -> bool:
def init(engine_settings):
global CACHE # pylint: disable=global-statement
CACHE = EngineCache(engine_settings["name"])
return True
def _get_secret_key():
resp = get(
base_url,
headers={"Referer": base_url},
headers={
# circumvents Cloudflare bot protections
"User-Agent": gen_useragent(),
"Referer": base_url,
"Sec-GPC": "1",
"Connection": "keep-alive",
},
)
if resp.status_code != 200:
@@ -97,6 +102,8 @@ def request(query, params):
params["headers"]["secret-key"] = secret_key
return params
def response(resp):
res = EngineResults()

View File

@@ -48,7 +48,6 @@ Implementations
"""
import time
import random
from urllib.parse import urlencode

View File

@@ -27,6 +27,9 @@ time_range_support = True
safesearch_map = {0: 'off', 1: '1', 2: '1'}
time_range_map = {'day': '1d', 'week': '1w', 'month': '1m', 'year': '1y'}
# using http2 returns forbidden errors
enable_http2 = False
def request(query, params):
args = {
@@ -47,6 +50,8 @@ def request(query, params):
# prevent automatic redirects to first page on pagination
params['allow_redirects'] = False
return params
def _image_result(result):
return {

View File

@@ -21,8 +21,6 @@ Implementations
"""
import typing as t
try:
import psycopg2 # type: ignore
except ImportError:
@@ -57,17 +55,15 @@ paging = True
_connection = None
def setup(engine_settings: dict[str, t.Any]) -> bool | 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')
def init(_):
global _connection # pylint: disable=global-statement
_connection = psycopg2.connect(
database=database,
user=username,

View File

@@ -14,11 +14,10 @@ from lxml import html
import babel
from searx.enginelib.traits import EngineTraits
from searx.utils import eval_xpath_list, eval_xpath, extract_text, extr
from searx.utils import eval_xpath_list, eval_xpath, extract_text, get_embeded_stream_url, extr
from searx.locales import region_tag
from searx.result_types import EngineResults
if t.TYPE_CHECKING:
from lxml.etree import ElementBase
from searx.extended_types import SXNG_Response
@@ -61,7 +60,7 @@ video_page_map = {
}
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if privacywall_category not in ("general", "images", "videos"):
raise ValueError("invalid category: %s" % privacywall_category)
@@ -154,6 +153,7 @@ def _video_results(doc: "ElementBase") -> EngineResults:
title=extract_text(eval_xpath(result, ".//h2[contains(@class, 'video-card-title')]")) or "",
content=extract_text(eval_xpath(result, ".//p")) or "",
thumbnail=thumbnail or "",
iframe_src=get_embeded_stream_url(url) or "",
)
)

View File

@@ -1,7 +1,6 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""Quark (Shenma) search engine for searxng"""
import typing as t
from urllib.parse import urlencode
from datetime import datetime
import re
@@ -44,7 +43,7 @@ def is_alibaba_captcha(html):
return bool(re.search(CAPTCHA_PATTERN, html))
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if quark_category not in ('general', 'images'):
raise SearxEngineAPIException(f"Unsupported category: {quark_category}")

View File

@@ -60,6 +60,9 @@ from searx.exceptions import (
SearxEngineTooManyRequestsException,
)
from searx.network import raise_for_httperror
from searx.utils import (
get_embeded_stream_url,
)
from searx.result_types import EngineResults
if t.TYPE_CHECKING:
@@ -296,6 +299,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
title=title,
url=res_url,
content=content,
iframe_src=get_embeded_stream_url(res_url),
publishedDate=pub_date,
thumbnail=thumbnail,
template="videos.html",

View File

@@ -35,6 +35,7 @@ Implementations
===============
"""
import typing as t
from datetime import date, timedelta

View File

@@ -10,7 +10,6 @@ from urllib.parse import urlencode
from lxml import html
from searx import locales
from searx.exceptions import SearxEngineResponseException
from searx.result_types import EngineResults
from searx.utils import eval_xpath_list, eval_xpath, extract_text
@@ -43,7 +42,7 @@ resulthunter_categ = "web"
"""Supported categories are ``web`` and ``images``."""
def setup(_: dict[str, t.Any]) -> bool | None:
def init(_):
if resulthunter_categ not in ("web", "images"):
raise ValueError("invalid category: %s" % resulthunter_categ)
@@ -53,7 +52,6 @@ def request(query: str, params: "OnlineParams") -> None:
"q": query,
"search_type": resulthunter_categ,
"offset": params["pageno"] - 1,
"search_source": "other",
}
# uses Brave's engine traits
@@ -113,11 +111,6 @@ def _image_results(doc: "ElementBase") -> EngineResults:
def response(resp: "SXNG_Response") -> EngineResults:
doc = html.fromstring(resp.text)
# if the request was wrong (e.g. missing params), the site doesn't contain a result container
# and instead shows an "Installation required" page to download the resulthunter browser extension
if not eval_xpath(doc, "//div[contains(@class, 'organic-results-container')]"):
raise SearxEngineResponseException()
match resulthunter_categ:
case "web":
return _general_results(doc)

View File

@@ -38,10 +38,12 @@ CACHE: EngineCache
"""Cache to store verification tokens for pagination."""
def setup(engine_settings: dict[str, t.Any]) -> bool:
def init(_):
if not base_url:
raise ValueError("base_url must be set")
def setup(engine_settings: dict[str, t.Any]) -> bool:
global CACHE # pylint: disable=global-statement
CACHE = EngineCache(engine_settings["name"])
return True
@@ -80,7 +82,7 @@ def response(resp: "SXNG_Response") -> EngineResults:
res.types.MainResult(
url=extract_text(eval_xpath(result, ".//a[contains(@class, 'title')]/@href")),
title=extract_text(eval_xpath(result, ".//a[contains(@class, 'title')]")),
content=extract_text(eval_xpath(result, ".//span[contains(@class, 'description') or not(@class)]")),
content=extract_text(eval_xpath(result, ".//span[contains(@class, 'description') or @class='']")),
)
)

View File

@@ -1,63 +0,0 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""JavaScript-based s1search implementation. See :ref:`s1search engine`.
Works for all s1search sites that contain the ``__RAMPJS__`` JavaScript variable.
"""
import json
import typing as t
from urllib.parse import urlencode
from searx.result_types import EngineResults
from searx.utils import extr, html_to_text
if t.TYPE_CHECKING:
from searx.search.processors import OnlineParams
from searx.extended_types import SXNG_Response
about = {
"website": "https://s1search.co",
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "JSON",
}
categories = ["general"]
paging = True
base_url = "https://search.answers.com"
# other working base URLs:
# - https://search.nation.online
# - https://search.activebeat.com
# - https://search.legalboulevard.com
# - https://search.walletgenius.com
# - https://search.legalboulevard.com
def request(query: str, params: "OnlineParams"):
args = {"q": query, "page": params["pageno"]}
params["url"] = f"{base_url}/?{urlencode(args)}"
def response(resp: "SXNG_Response") -> EngineResults:
res = EngineResults()
data_raw = extr(resp.text, "response: ", " };")
data = json.loads(data_raw)
mainline = [s for s in data["search"]["regions"] if s["name"] == "mainline"][0]
for group in mainline["groups"]:
for result in group["results"]:
if not ("url" in result or "clickUrl" in result):
continue
res.add(
res.types.MainResult(
url=result.get("url") or result.get("clickUrl"),
title=html_to_text(result["title"]),
content=html_to_text(result["description"]),
)
)
return res

View File

@@ -1,88 +0,0 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""SearchRockit is an American search engine. It allegedly has its own index,
but the results seem to come from Google."""
import typing as t
from urllib.parse import urlencode
from lxml import html
from dateutil import parser
from searx.result_types import EngineResults
from searx.utils import (
eval_xpath_list,
extract_text,
eval_xpath,
)
if t.TYPE_CHECKING:
from searx.search.processors import OnlineParams
from searx.extended_types import SXNG_Response
about = {
"website": "https://searchrockit.com",
"official_api_documentation": None,
"use_official_api": False,
"require_api_key": False,
"results": "HTML",
}
categories = ["general"]
paging = True
SearchrockitCateg = t.Literal["web", "images", "news"]
searchrockit_categ: SearchrockitCateg = "web"
base_url = "https://searchrockit.com"
def setup(_):
if searchrockit_categ not in t.get_args(SearchrockitCateg):
raise ValueError("invalid search category: %s" % searchrockit_categ)
def request(query: str, params: "OnlineParams") -> None:
args = {"q": query, "p": params["pageno"]}
params["url"] = f"{base_url}/results/{searchrockit_categ}?{urlencode(args)}"
def response(resp: "SXNG_Response") -> EngineResults:
doc = html.fromstring(resp.text)
res = EngineResults()
match searchrockit_categ:
case "web" | "news":
for result in eval_xpath_list(
doc, "//div[contains(@class, 'results-list')]/div[contains(@class, 'result-item')]"
):
publishedDate = None
try:
d = extract_text(eval_xpath(result, ".//span[contains(@class, 'result-item--publishedAt')]")) or ""
publishedDate = parser.parse(d)
except parser.ParserError:
pass
res.add(
res.types.MainResult(
url=extract_text(eval_xpath(result, ".//a[contains(@class, 'result-item--title')]/@href")),
title=extract_text(eval_xpath(result, ".//a[contains(@class, 'result-item--title')]")) or "",
content=extract_text(eval_xpath(result, ".//a[contains(@class, 'result-item--desc')]")) or "",
thumbnail=extract_text(
eval_xpath(result, ".//a[contains(@class, 'result-item--thumb')]/img/@src")
)
or "",
publishedDate=publishedDate,
)
)
case "images":
for result in eval_xpath_list(
doc, "//div[contains(@class, 'image-grid')]/a[contains(@class, 'image-card')]"
):
res.add(
res.types.Image(
url=extract_text(eval_xpath(result, "./@href")),
title=extract_text(eval_xpath(result, "./div[contains(@class, 'image-title')]")) or "",
thumbnail_src=extract_text(eval_xpath(result, "./img/@src")) or "",
img_src=extract_text(eval_xpath(result, "./@data-full-url")) or "",
)
)
return res

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