50f92779bd
This patch brings two major changes:
- ``Result.filter_urls(..)`` to pass a filter function for URL fields
- The ``enabled_plugins:`` section in SearXNG's settings do no longer exists.
To understand plugin development compile documentation:
$ make docs.clean docs.live
and read http://0.0.0.0:8000/dev/plugins/development.html
There is no longer a distinction between built-in and external plugin, all
plugins are registered via the settings in the ``plugins:`` section.
In SearXNG, plugins can be registered via a fully qualified class name. A
configuration (`PluginCfg`) can be transferred to the plugin, e.g. to activate
it by default / *opt-in* or *opt-out* from user's point of view.
built-in plugins
================
The built-in plugins are all located in the namespace `searx.plugins`.
.. code:: yaml
plugins:
searx.plugins.calculator.SXNGPlugin:
active: true
searx.plugins.hash_plugin.SXNGPlugin:
active: true
searx.plugins.self_info.SXNGPlugin:
active: true
searx.plugins.tracker_url_remover.SXNGPlugin:
active: true
searx.plugins.unit_converter.SXNGPlugin:
active: true
searx.plugins.ahmia_filter.SXNGPlugin:
active: true
searx.plugins.hostnames.SXNGPlugin:
active: true
searx.plugins.oa_doi_rewrite.SXNGPlugin:
active: false
searx.plugins.tor_check.SXNGPlugin:
active: false
external plugins
================
SearXNG supports *external plugins* / there is no need to install one, SearXNG
runs out of the box.
- Only show green hosted results: https://github.com/return42/tgwf-searx-plugins/
To get a developer installation in a SearXNG developer environment:
.. code:: sh
$ git clone git@github.com:return42/tgwf-searx-plugins.git
$ ./manage pyenv.cmd python -m \
pip install -e tgwf-searx-plugins
To register the plugin in SearXNG add ``only_show_green_results.SXNGPlugin`` to
the ``plugins:``:
.. code:: yaml
plugins:
# ...
only_show_green_results.SXNGPlugin:
active: false
Result.filter_urls(..)
======================
The ``Result.filter_urls(..)`` can be used to filter and/or modify URL fields.
In the following example, the filter function ``my_url_filter``:
.. code:: python
def my_url_filter(result, field_name, url_src) -> bool | str:
if "google" in url_src:
return False # remove URL field from result
if "facebook" in url_src:
new_url = url_src.replace("facebook", "fb-dummy")
return new_url # return modified URL
return True # leave URL in field unchanged
is applied to all URL fields in the :py:obj:`Plugin.on_result` hook:
.. code:: python
class MyUrlFilter(Plugin):
...
def on_result(self, request, search, result) -> bool:
result.filter_urls(my_url_filter)
return True
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
91 lines
2.7 KiB
Python
91 lines
2.7 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
# pylint: disable=missing-module-docstring
|
|
from __future__ import annotations
|
|
import typing
|
|
|
|
import re
|
|
from urllib.parse import parse_qsl
|
|
|
|
from flask_babel import gettext
|
|
from searx import get_setting
|
|
from searx.plugins import Plugin, PluginInfo
|
|
from searx.extended_types import sxng_request
|
|
|
|
from ._core import log
|
|
|
|
if typing.TYPE_CHECKING:
|
|
from searx.search import SearchWithPlugins
|
|
from searx.extended_types import SXNG_Request
|
|
from searx.result_types import Result, LegacyResult
|
|
from searx.plugins import PluginCfg
|
|
|
|
|
|
ahmia_blacklist: list = []
|
|
|
|
|
|
def filter_url_field(result: "Result|LegacyResult", field_name: str, url_src: str) -> bool | str:
|
|
"""Returns bool ``True`` to use URL unchanged (``False`` to ignore URL).
|
|
If URL should be modified, the returned string is the new URL to use."""
|
|
|
|
if field_name != "url":
|
|
return True # use it unchanged
|
|
|
|
doi = extract_doi(result.parsed_url)
|
|
if doi and len(doi) < 50:
|
|
for suffix in ("/", ".pdf", ".xml", "/full", "/meta", "/abstract"):
|
|
doi = doi.removesuffix(suffix)
|
|
new_url = get_doi_resolver() + doi
|
|
if "doi" not in result:
|
|
result["doi"] = doi
|
|
log.debug("oa_doi_rewrite: [URL field: %s] %s -> %s", field_name, url_src, new_url)
|
|
return new_url # use new url
|
|
|
|
return True # use it unchanged
|
|
|
|
|
|
class SXNGPlugin(Plugin):
|
|
"""Avoid paywalls by redirecting to open-access."""
|
|
|
|
id = "oa_doi_rewrite"
|
|
|
|
def __init__(self, plg_cfg: "PluginCfg") -> None:
|
|
super().__init__(plg_cfg)
|
|
self.info = PluginInfo(
|
|
id=self.id,
|
|
name=gettext("Open Access DOI rewrite"),
|
|
description=gettext("Avoid paywalls by redirecting to open-access versions of publications when available"),
|
|
preference_section="general",
|
|
)
|
|
|
|
def on_result(
|
|
self,
|
|
request: "SXNG_Request",
|
|
search: "SearchWithPlugins",
|
|
result: "Result",
|
|
) -> bool: # pylint: disable=unused-argument
|
|
if result.parsed_url:
|
|
result.filter_urls(filter_url_field)
|
|
return True
|
|
|
|
|
|
regex = re.compile(r'10\.\d{4,9}/[^\s]+')
|
|
|
|
|
|
def extract_doi(url):
|
|
m = regex.search(url.path)
|
|
if m:
|
|
return m.group(0)
|
|
for _, v in parse_qsl(url.query):
|
|
m = regex.search(v)
|
|
if m:
|
|
return m.group(0)
|
|
return None
|
|
|
|
|
|
def get_doi_resolver() -> str:
|
|
doi_resolvers = get_setting("doi_resolvers")
|
|
selected_resolver = sxng_request.preferences.get_value('doi_resolver')[0]
|
|
if selected_resolver not in doi_resolvers:
|
|
selected_resolver = get_setting("default_doi_resolver")
|
|
return doi_resolvers[selected_resolver]
|