searx/_modules/searx_extra/standalone_searx.html

321 lines
13 KiB
HTML

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta name="viewport" content="width=device-width, initial-scale=1">
<title>searx_extra.standalone_searx &#8212; Searx Documentation (Searx-1.1.0.tex)</title>
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css" />
<link rel="stylesheet" type="text/css" href="../../_static/searx.css" />
<link rel="stylesheet" type="text/css" href="../../_static/tabs.css" />
<script data-url_root="../../" id="documentation_options" src="../../_static/documentation_options.js"></script>
<script src="../../_static/jquery.js"></script>
<script src="../../_static/underscore.js"></script>
<script src="../../_static/_sphinx_javascript_frameworks_compat.js"></script>
<script src="../../_static/doctools.js"></script>
<script src="../../_static/tabs.js"></script>
<link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" />
</head><body>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="../../genindex.html" title="General Index"
accesskey="I">index</a></li>
<li class="right" >
<a href="../../py-modindex.html" title="Python Module Index"
>modules</a> |</li>
<li class="nav-item nav-item-0"><a href="../../index.html">Searx Documentation (Searx-1.1.0.tex)</a> &#187;</li>
<li class="nav-item nav-item-1"><a href="../index.html" accesskey="U">Module code</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">searx_extra.standalone_searx</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for searx_extra.standalone_searx</h1><div class="highlight"><pre>
<span></span>#!/usr/bin/env python
&quot;&quot;&quot;Script to run searx from terminal.
Getting categories without initiate the engine will only return `[&#39;general&#39;]`
&gt;&gt;&gt; import searx.engines
... list(searx.engines.categories.keys())
[&#39;general&#39;]
&gt;&gt;&gt; import searx.search
... searx.search.initialize()
... list(searx.engines.categories.keys())
[&#39;general&#39;, &#39;it&#39;, &#39;science&#39;, &#39;images&#39;, &#39;news&#39;, &#39;videos&#39;, &#39;music&#39;, &#39;files&#39;, &#39;social media&#39;, &#39;map&#39;]
Example to use this script:
.. code:: bash
$ python3 searx_extra/standalone_searx.py rain
Example to run it from python:
&gt;&gt;&gt; import importlib
... import json
... import sys
... import searx.engines
... import searx.search
... search_query = &#39;rain&#39;
... # initialize engines
... searx.search.initialize()
... # load engines categories once instead of each time the function called
... engine_cs = list(searx.engines.categories.keys())
... # load module
... spec = importlib.util.spec_from_file_location(
... &#39;utils.standalone_searx&#39;, &#39;searx_extra/standalone_searx.py&#39;)
... sas = importlib.util.module_from_spec(spec)
... spec.loader.exec_module(sas)
... # use function from module
... prog_args = sas.parse_argument([search_query], category_choices=engine_cs)
... search_q = sas.get_search_query(prog_args, engine_categories=engine_cs)
... res_dict = sas.to_dict(search_q)
... sys.stdout.write(json.dumps(
... res_dict, sort_keys=True, indent=4, ensure_ascii=False,
... default=sas.json_serial))
{
&quot;answers&quot;: [],
&quot;infoboxes&quot;: [ {...} ],
&quot;paging&quot;: true,
&quot;results&quot;: [... ],
&quot;results_number&quot;: 820000000.0,
&quot;search&quot;: {
&quot;lang&quot;: &quot;all&quot;,
&quot;pageno&quot;: 1,
&quot;q&quot;: &quot;rain&quot;,
&quot;safesearch&quot;: 0,
&quot;timerange&quot;: null
},
&quot;suggestions&quot;: [...]
}
&quot;&quot;&quot; # noqa: E501
# pylint: disable=pointless-string-statement
&#39;&#39;&#39;
searx is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
searx is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with searx. If not, see &lt; http://www.gnu.org/licenses/ &gt;.
(C) 2016- by Alexandre Flament, &lt;alex@al-f.net&gt;
&#39;&#39;&#39;
# pylint: disable=wrong-import-position
import argparse
import sys
from datetime import datetime
from json import dumps
from typing import Any, Dict, List, Optional
import searx
import searx.preferences
import searx.query
import searx.search
import searx.webadapter
EngineCategoriesVar = Optional[List[str]]
<div class="viewcode-block" id="get_search_query"><a class="viewcode-back" href="../../searx_extra/standalone_searx.py.html#searx_extra.standalone_searx.get_search_query">[docs]</a>def get_search_query(
args: argparse.Namespace, engine_categories: EngineCategoriesVar = None
) -&gt; searx.search.SearchQuery:
&quot;&quot;&quot;Get search results for the query&quot;&quot;&quot;
if engine_categories is None:
engine_categories = list(searx.engines.categories.keys())
try:
category = args.category.decode(&#39;utf-8&#39;)
except AttributeError:
category = args.category
form = {
&quot;q&quot;: args.query,
&quot;categories&quot;: category,
&quot;pageno&quot;: str(args.pageno),
&quot;language&quot;: args.lang,
&quot;time_range&quot;: args.timerange
}
preferences = searx.preferences.Preferences(
[&#39;oscar&#39;], engine_categories, searx.engines.engines, [])
preferences.key_value_settings[&#39;safesearch&#39;].parse(args.safesearch)
search_query = searx.webadapter.get_search_query_from_webapp(
preferences, form)[0]
return search_query</div>
<div class="viewcode-block" id="no_parsed_url"><a class="viewcode-back" href="../../searx_extra/standalone_searx.py.html#searx_extra.standalone_searx.no_parsed_url">[docs]</a>def no_parsed_url(results: List[Dict[str, Any]]) -&gt; List[Dict[str, Any]]:
&quot;&quot;&quot;Remove parsed url from dict.&quot;&quot;&quot;
for result in results:
del result[&#39;parsed_url&#39;]
return results</div>
<div class="viewcode-block" id="json_serial"><a class="viewcode-back" href="../../searx_extra/standalone_searx.py.html#searx_extra.standalone_searx.json_serial">[docs]</a>def json_serial(obj: Any) -&gt; Any:
&quot;&quot;&quot;JSON serializer for objects not serializable by default json code.
:raise TypeError: raised when **obj** is not serializable
&quot;&quot;&quot;
if isinstance(obj, datetime):
serial = obj.isoformat()
return serial
if isinstance(obj, bytes):
return obj.decode(&#39;utf8&#39;)
if isinstance(obj, set):
return list(obj)
raise TypeError(&quot;Type ({}) not serializable&quot;.format(type(obj)))</div>
<div class="viewcode-block" id="to_dict"><a class="viewcode-back" href="../../searx_extra/standalone_searx.py.html#searx_extra.standalone_searx.to_dict">[docs]</a>def to_dict(search_query: searx.search.SearchQuery) -&gt; Dict[str, Any]:
&quot;&quot;&quot;Get result from parsed arguments.&quot;&quot;&quot;
result_container = searx.search.Search(search_query).search()
result_container_json = {
&quot;search&quot;: {
&quot;q&quot;: search_query.query,
&quot;pageno&quot;: search_query.pageno,
&quot;lang&quot;: search_query.lang,
&quot;safesearch&quot;: search_query.safesearch,
&quot;timerange&quot;: search_query.time_range,
},
&quot;results&quot;: no_parsed_url(result_container.get_ordered_results()),
&quot;infoboxes&quot;: result_container.infoboxes,
&quot;suggestions&quot;: list(result_container.suggestions),
&quot;answers&quot;: list(result_container.answers),
&quot;paging&quot;: result_container.paging,
&quot;results_number&quot;: result_container.results_number()
}
return result_container_json</div>
<div class="viewcode-block" id="parse_argument"><a class="viewcode-back" href="../../searx_extra/standalone_searx.py.html#searx_extra.standalone_searx.parse_argument">[docs]</a>def parse_argument(
args: Optional[List[str]]=None,
category_choices: EngineCategoriesVar=None
) -&gt; argparse.Namespace:
&quot;&quot;&quot;Parse command line.
:raise SystemExit: Query argument required on `args`
Examples:
&gt;&gt;&gt; import importlib
... # load module
... spec = importlib.util.spec_from_file_location(
... &#39;utils.standalone_searx&#39;, &#39;utils/standalone_searx.py&#39;)
... sas = importlib.util.module_from_spec(spec)
... spec.loader.exec_module(sas)
... sas.parse_argument()
usage: ptipython [-h] [--category [{general}]] [--lang [LANG]] [--pageno [PAGENO]] [--safesearch [{0,1,2}]] [--timerange [{day,week,month,year}]]
query
SystemExit: 2
&gt;&gt;&gt; sas.parse_argument([&#39;rain&#39;])
Namespace(category=&#39;general&#39;, lang=&#39;all&#39;, pageno=1, query=&#39;rain&#39;, safesearch=&#39;0&#39;, timerange=None)
&quot;&quot;&quot; # noqa: E501
if not category_choices:
category_choices = list(searx.engines.categories.keys())
parser = argparse.ArgumentParser(description=&#39;Standalone searx.&#39;)
parser.add_argument(&#39;query&#39;, type=str,
help=&#39;Text query&#39;)
parser.add_argument(&#39;--category&#39;, type=str, nargs=&#39;?&#39;,
choices=category_choices,
default=&#39;general&#39;,
help=&#39;Search category&#39;)
parser.add_argument(&#39;--lang&#39;, type=str, nargs=&#39;?&#39;, default=&#39;all&#39;,
help=&#39;Search language&#39;)
parser.add_argument(&#39;--pageno&#39;, type=int, nargs=&#39;?&#39;, default=1,
help=&#39;Page number starting from 1&#39;)
parser.add_argument(
&#39;--safesearch&#39;, type=str, nargs=&#39;?&#39;,
choices=[&#39;0&#39;, &#39;1&#39;, &#39;2&#39;], default=&#39;0&#39;,
help=&#39;Safe content filter from none to strict&#39;)
parser.add_argument(
&#39;--timerange&#39;, type=str,
nargs=&#39;?&#39;, choices=[&#39;day&#39;, &#39;week&#39;, &#39;month&#39;, &#39;year&#39;],
help=&#39;Filter by time range&#39;)
return parser.parse_args(args)</div>
if __name__ == &#39;__main__&#39;:
searx.search.initialize()
engine_cs = list(searx.engines.categories.keys())
prog_args = parse_argument(category_choices=engine_cs)
search_q = get_search_query(prog_args, engine_categories=engine_cs)
res_dict = to_dict(search_q)
sys.stdout.write(dumps(
res_dict, sort_keys=True, indent=4, ensure_ascii=False,
default=json_serial))
</pre></div>
<div class="clearer"></div>
</div>
</div>
</div>
<span id="sidebar-top"></span>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<p class="logo"><a href="../../index.html">
<img class="logo" src="../../_static/searx_logo_small.png" alt="Logo"/>
</a></p>
<h3>Project Links</h3>
<ul>
<li><a href="https://searx.github.io/searx/blog/index.html">Blog</a>
<li><a href="https://github.com/searx/searx">Source</a>
<li><a href="https://github.com/searx/searx/wiki">Wiki</a>
<li><a href="https://twitter.com/Searx_engine">Twitter</a>
<li><a href="https://github.com/searx/searx/issues">Issue Tracker</a>
</ul><h3>Navigation</h3>
<ul>
<li><a href="../../index.html">Overview</a>
<ul>
<li><a href="../index.html">Module code</a>
</ul>
</li>
</ul>
</li>
</ul>
<div id="searchbox" style="display: none" role="search">
<h3 id="searchlabel">Quick search</h3>
<div class="searchformwrapper">
<form class="search" action="../../search.html" method="get">
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
<input type="submit" value="Go" />
</form>
</div>
</div>
<script>document.getElementById('searchbox').style.display = "block"</script>
</div>
</div>
<div class="clearer"></div>
</div>
<div class="footer" role="contentinfo">
&#169; Copyright 2015-2022, Adam Tauber, Noémi Ványi.
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.1.1.
</div>
<script src="../../_static/version_warning_offset.js"></script>
</body>
</html>