mirror of
https://github.com/searxng/searxng.git
synced 2025-07-16 01:39:24 +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:
Markus Heiser
Markus Heiser
parent
d36da0a6c3
commit
50f92779bd
23 changed files with 816 additions and 607 deletions
|
|
@ -1,19 +1,10 @@
|
|||
# SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
# pylint: disable=too-many-branches
|
||||
# pylint: disable=too-many-branches, unused-argument
|
||||
"""
|
||||
.. attention::
|
||||
|
||||
The **"Hostname replace"** plugin has been replace by **"Hostnames
|
||||
plugin"**, see :pull:`3463` & :pull:`3552`.
|
||||
|
||||
The **Hostnames plugin** can be enabled by adding it to the
|
||||
``enabled_plugins`` **list** in the ``setting.yml`` like so.
|
||||
|
||||
.. code:: yaml
|
||||
|
||||
enabled_plugins:
|
||||
- 'Hostnames plugin'
|
||||
...
|
||||
During the initialization phase, the plugin checks whether a ``hostnames:``
|
||||
configuration exists. If this is not the case, the plugin is not included
|
||||
in the PluginStorage (it is not available for selection).
|
||||
|
||||
- ``hostnames.replace``: A **mapping** of regular expressions to hostnames to be
|
||||
replaced by other hostnames.
|
||||
|
|
@ -92,6 +83,7 @@ something like this:
|
|||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
import typing
|
||||
|
||||
import re
|
||||
from urllib.parse import urlunparse, urlparse
|
||||
|
|
@ -99,84 +91,114 @@ from urllib.parse import urlunparse, urlparse
|
|||
from flask_babel import gettext
|
||||
|
||||
from searx import settings
|
||||
from searx.result_types._base import MainResult, LegacyResult
|
||||
from searx.settings_loader import get_yaml_cfg
|
||||
from searx.plugins import Plugin, PluginInfo
|
||||
|
||||
from ._core import log
|
||||
|
||||
if typing.TYPE_CHECKING:
|
||||
import flask
|
||||
from searx.search import SearchWithPlugins
|
||||
from searx.extended_types import SXNG_Request
|
||||
from searx.result_types import Result
|
||||
from searx.plugins import PluginCfg
|
||||
|
||||
|
||||
name = gettext('Hostnames plugin')
|
||||
description = gettext('Rewrite hostnames, remove results or prioritize them based on the hostname')
|
||||
default_on = False
|
||||
preference_section = 'general'
|
||||
|
||||
plugin_id = 'hostnames'
|
||||
|
||||
parsed = 'parsed_url'
|
||||
_url_fields = ['iframe_src', 'audio_src']
|
||||
REPLACE: dict[re.Pattern, str] = {}
|
||||
REMOVE: set = set()
|
||||
HIGH: set = set()
|
||||
LOW: set = set()
|
||||
|
||||
|
||||
def _load_regular_expressions(settings_key) -> dict | set | None:
|
||||
setting_value = settings.get(plugin_id, {}).get(settings_key)
|
||||
class SXNGPlugin(Plugin):
|
||||
"""Rewrite hostnames, remove results or prioritize them."""
|
||||
|
||||
if not setting_value:
|
||||
return None
|
||||
id = "hostnames"
|
||||
|
||||
# load external file with configuration
|
||||
if isinstance(setting_value, str):
|
||||
setting_value = get_yaml_cfg(setting_value)
|
||||
def __init__(self, plg_cfg: "PluginCfg") -> None:
|
||||
super().__init__(plg_cfg)
|
||||
self.info = PluginInfo(
|
||||
id=self.id,
|
||||
name=gettext("Hostnames plugin"),
|
||||
description=gettext("Rewrite hostnames, remove results or prioritize them based on the hostname"),
|
||||
preference_section="general",
|
||||
)
|
||||
|
||||
if isinstance(setting_value, list):
|
||||
return {re.compile(r) for r in setting_value}
|
||||
def on_result(self, request: "SXNG_Request", search: "SearchWithPlugins", result: Result) -> bool:
|
||||
|
||||
if isinstance(setting_value, dict):
|
||||
return {re.compile(p): r for (p, r) in setting_value.items()}
|
||||
for pattern in REMOVE:
|
||||
if result.parsed_url and pattern.search(result.parsed_url.netloc):
|
||||
# if the link (parsed_url) of the result match, then remove the
|
||||
# result from the result list, in any other case, the result
|
||||
# remains in the list / see final "return True" below.
|
||||
# log.debug("FIXME: remove [url/parsed_url] %s %s", pattern.pattern, result.url)
|
||||
return False
|
||||
|
||||
return None
|
||||
result.filter_urls(filter_url_field)
|
||||
|
||||
if isinstance(result, (MainResult, LegacyResult)):
|
||||
for pattern in LOW:
|
||||
if result.parsed_url and pattern.search(result.parsed_url.netloc):
|
||||
result.priority = "low"
|
||||
|
||||
replacements: dict = _load_regular_expressions('replace') or {} # type: ignore
|
||||
removables: set = _load_regular_expressions('remove') or set() # type: ignore
|
||||
high_priority: set = _load_regular_expressions('high_priority') or set() # type: ignore
|
||||
low_priority: set = _load_regular_expressions('low_priority') or set() # type: ignore
|
||||
for pattern in HIGH:
|
||||
if result.parsed_url and pattern.search(result.parsed_url.netloc):
|
||||
result.priority = "high"
|
||||
|
||||
return True
|
||||
|
||||
def _matches_parsed_url(result, pattern):
|
||||
return result[parsed] and (parsed in result and pattern.search(result[parsed].netloc))
|
||||
def init(self, app: "flask.Flask") -> bool: # pylint: disable=unused-argument
|
||||
global REPLACE, REMOVE, HIGH, LOW # pylint: disable=global-statement
|
||||
|
||||
|
||||
def on_result(_request, _search, result) -> bool:
|
||||
for pattern, replacement in replacements.items():
|
||||
if _matches_parsed_url(result, pattern):
|
||||
# logger.debug(result['url'])
|
||||
result[parsed] = result[parsed]._replace(netloc=pattern.sub(replacement, result[parsed].netloc))
|
||||
result['url'] = urlunparse(result[parsed])
|
||||
# logger.debug(result['url'])
|
||||
|
||||
for url_field in _url_fields:
|
||||
if not getattr(result, url_field, None):
|
||||
continue
|
||||
|
||||
url_src = urlparse(result[url_field])
|
||||
if pattern.search(url_src.netloc):
|
||||
url_src = url_src._replace(netloc=pattern.sub(replacement, url_src.netloc))
|
||||
result[url_field] = urlunparse(url_src)
|
||||
|
||||
for pattern in removables:
|
||||
if _matches_parsed_url(result, pattern):
|
||||
if not settings.get(self.id):
|
||||
# Remove plugin, if there isn't a "hostnames:" setting
|
||||
return False
|
||||
|
||||
for url_field in _url_fields:
|
||||
if not getattr(result, url_field, None):
|
||||
continue
|
||||
REPLACE = self._load_regular_expressions("replace") or {} # type: ignore
|
||||
REMOVE = self._load_regular_expressions("remove") or set() # type: ignore
|
||||
HIGH = self._load_regular_expressions("high_priority") or set() # type: ignore
|
||||
LOW = self._load_regular_expressions("low_priority") or set() # type: ignore
|
||||
|
||||
url_src = urlparse(result[url_field])
|
||||
if pattern.search(url_src.netloc):
|
||||
del result[url_field]
|
||||
return True
|
||||
|
||||
for pattern in low_priority:
|
||||
if _matches_parsed_url(result, pattern):
|
||||
result['priority'] = 'low'
|
||||
def _load_regular_expressions(self, settings_key) -> dict[re.Pattern, str] | set | None:
|
||||
setting_value = settings.get(self.id, {}).get(settings_key)
|
||||
|
||||
for pattern in high_priority:
|
||||
if _matches_parsed_url(result, pattern):
|
||||
result['priority'] = 'high'
|
||||
if not setting_value:
|
||||
return None
|
||||
|
||||
# load external file with configuration
|
||||
if isinstance(setting_value, str):
|
||||
setting_value = get_yaml_cfg(setting_value)
|
||||
|
||||
if isinstance(setting_value, list):
|
||||
return {re.compile(r) for r in setting_value}
|
||||
|
||||
if isinstance(setting_value, dict):
|
||||
return {re.compile(p): r for (p, r) in setting_value.items()}
|
||||
|
||||
return None
|
||||
|
||||
|
||||
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 not url_src:
|
||||
log.debug("missing a URL in field %s", field_name)
|
||||
return True
|
||||
|
||||
url_src_parsed = urlparse(url=url_src)
|
||||
|
||||
for pattern in REMOVE:
|
||||
if pattern.search(url_src_parsed.netloc):
|
||||
return False
|
||||
|
||||
for pattern, replacement in REPLACE.items():
|
||||
if pattern.search(url_src_parsed.netloc):
|
||||
new_url = url_src_parsed._replace(netloc=pattern.sub(replacement, url_src_parsed.netloc))
|
||||
new_url = urlunparse(new_url)
|
||||
return new_url
|
||||
|
||||
return True
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue