mirror of
https://github.com/searxng/searxng.git
synced 2025-07-13 16:29:17 +02:00
[refactor] migrate plugins from "module" to class SXNGPlugin
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>
This commit is contained in:
parent
d36da0a6c3
commit
50f92779bd
23 changed files with 816 additions and 607 deletions
|
@ -2,12 +2,21 @@
|
|||
# pylint: disable=missing-module-docstring
|
||||
|
||||
from __future__ import annotations
|
||||
import typing
|
||||
|
||||
import re
|
||||
from urllib.parse import urlunparse, parse_qsl, urlencode
|
||||
|
||||
from flask_babel import gettext
|
||||
|
||||
from searx.plugins import Plugin, PluginInfo
|
||||
|
||||
if typing.TYPE_CHECKING:
|
||||
from searx.search import SearchWithPlugins
|
||||
from searx.extended_types import SXNG_Request
|
||||
from searx.result_types import Result
|
||||
from searx.plugins import PluginCfg
|
||||
|
||||
regexes = {
|
||||
re.compile(r'utm_[^&]+'),
|
||||
re.compile(r'(wkey|wemail)[^&]*'),
|
||||
|
@ -15,30 +24,35 @@ regexes = {
|
|||
re.compile(r'&$'),
|
||||
}
|
||||
|
||||
name = gettext('Tracker URL remover')
|
||||
description = gettext('Remove trackers arguments from the returned URL')
|
||||
default_on = True
|
||||
preference_section = 'privacy'
|
||||
|
||||
class SXNGPlugin(Plugin):
|
||||
"""Remove trackers arguments from the returned URL"""
|
||||
|
||||
def on_result(_request, _search, result) -> bool:
|
||||
id = "tracker_url_remover"
|
||||
|
||||
def __init__(self, plg_cfg: "PluginCfg") -> None:
|
||||
super().__init__(plg_cfg)
|
||||
self.info = PluginInfo(
|
||||
id=self.id,
|
||||
name=gettext("Tracker URL remover"),
|
||||
description=gettext("Remove trackers arguments from the returned URL"),
|
||||
preference_section="privacy",
|
||||
)
|
||||
|
||||
def on_result(
|
||||
self, request: "SXNG_Request", search: "SearchWithPlugins", result: Result
|
||||
) -> bool: # pylint: disable=unused-argument
|
||||
if not result.parsed_url:
|
||||
return True
|
||||
|
||||
parsed_query: list[tuple[str, str]] = parse_qsl(result.parsed_url.query)
|
||||
for name_value in list(parsed_query):
|
||||
param_name = name_value[0]
|
||||
for reg in regexes:
|
||||
if reg.match(param_name):
|
||||
parsed_query.remove(name_value)
|
||||
result.parsed_url = result.parsed_url._replace(query=urlencode(parsed_query))
|
||||
result.url = urlunparse(result.parsed_url)
|
||||
break
|
||||
|
||||
parsed_url = getattr(result, "parsed_url", None)
|
||||
if not parsed_url:
|
||||
return True
|
||||
|
||||
if parsed_url.query == "":
|
||||
return True
|
||||
|
||||
parsed_query = parse_qsl(parsed_url.query)
|
||||
changes = 0
|
||||
for i, (param_name, _) in enumerate(list(parsed_query)):
|
||||
for reg in regexes:
|
||||
if reg.match(param_name):
|
||||
parsed_query.pop(i - changes)
|
||||
changes += 1
|
||||
result.parsed_url = result.parsed_url._replace(query=urlencode(parsed_query))
|
||||
result.url = urlunparse(result.parsed_url)
|
||||
break
|
||||
|
||||
return True
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue