searxng/_modules/searx/botdetection/link_token.html
2024-04-24 14:03:54 +00:00

274 lines
21 KiB
HTML

<!DOCTYPE html>
<html lang="en" data-content_root="../../../">
<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.botdetection.link_token &#8212; SearXNG Documentation (2024.4.24+e0214412f)</title>
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=4f649999" />
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
<link rel="stylesheet" type="text/css" href="../../../_static/tabs.css?v=a5c4661c" />
<script src="../../../_static/documentation_options.js?v=68e7c2e2"></script>
<script src="../../../_static/doctools.js?v=888ff710"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/tabs.js?v=3030b3cb"></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">SearXNG Documentation (2024.4.24+e0214412f)</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.botdetection.link_token</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for searx.botdetection.link_token</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="sd">Method ``link_token``</span>
<span class="sd">---------------------</span>
<span class="sd">The ``link_token`` method evaluates a request as :py:obj:`suspicious</span>
<span class="sd">&lt;is_suspicious&gt;` if the URL ``/client&lt;token&gt;.css`` is not requested by the</span>
<span class="sd">client. By adding a random component (the token) in the URL, a bot can not send</span>
<span class="sd">a ping by request a static URL.</span>
<span class="sd">.. note::</span>
<span class="sd"> This method requires a redis DB and needs a HTTP X-Forwarded-For_ header.</span>
<span class="sd">To get in use of this method a flask URL route needs to be added:</span>
<span class="sd">.. code:: python</span>
<span class="sd"> @app.route(&#39;/client&lt;token&gt;.css&#39;, methods=[&#39;GET&#39;, &#39;POST&#39;])</span>
<span class="sd"> def client_token(token=None):</span>
<span class="sd"> link_token.ping(request, token)</span>
<span class="sd"> return Response(&#39;&#39;, mimetype=&#39;text/css&#39;)</span>
<span class="sd">And in the HTML template from flask a stylesheet link is needed (the value of</span>
<span class="sd">``link_token`` comes from :py:obj:`get_token`):</span>
<span class="sd">.. code:: html</span>
<span class="sd"> &lt;link rel=&quot;stylesheet&quot;</span>
<span class="sd"> href=&quot;{{ url_for(&#39;client_token&#39;, token=link_token) }}&quot;</span>
<span class="sd"> type=&quot;text/css&quot; /&gt;</span>
<span class="sd">.. _X-Forwarded-For:</span>
<span class="sd"> https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Forwarded-For</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">annotations</span>
<span class="kn">from</span> <span class="nn">ipaddress</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">IPv4Network</span><span class="p">,</span>
<span class="n">IPv6Network</span><span class="p">,</span>
<span class="n">ip_address</span><span class="p">,</span>
<span class="p">)</span>
<span class="kn">import</span> <span class="nn">string</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">import</span> <span class="nn">flask</span>
<span class="kn">from</span> <span class="nn">searx</span> <span class="kn">import</span> <span class="n">logger</span>
<span class="kn">from</span> <span class="nn">searx</span> <span class="kn">import</span> <span class="n">redisdb</span>
<span class="kn">from</span> <span class="nn">searx.redislib</span> <span class="kn">import</span> <span class="n">secret_hash</span>
<span class="kn">from</span> <span class="nn">._helpers</span> <span class="kn">import</span> <span class="p">(</span>
<span class="n">get_network</span><span class="p">,</span>
<span class="n">get_real_ip</span><span class="p">,</span>
<span class="p">)</span>
<span class="n">TOKEN_LIVE_TIME</span> <span class="o">=</span> <span class="mi">600</span>
<span class="sd">&quot;&quot;&quot;Livetime (sec) of limiter&#39;s CSS token.&quot;&quot;&quot;</span>
<span class="n">PING_LIVE_TIME</span> <span class="o">=</span> <span class="mi">3600</span>
<span class="sd">&quot;&quot;&quot;Livetime (sec) of the ping-key from a client (request)&quot;&quot;&quot;</span>
<span class="n">PING_KEY</span> <span class="o">=</span> <span class="s1">&#39;SearXNG_limiter.ping&#39;</span>
<span class="sd">&quot;&quot;&quot;Prefix of all ping-keys generated by :py:obj:`get_ping_key`&quot;&quot;&quot;</span>
<span class="n">TOKEN_KEY</span> <span class="o">=</span> <span class="s1">&#39;SearXNG_limiter.token&#39;</span>
<span class="sd">&quot;&quot;&quot;Key for which the current token is stored in the DB&quot;&quot;&quot;</span>
<span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span><span class="o">.</span><span class="n">getChild</span><span class="p">(</span><span class="s1">&#39;botdetection.link_token&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="is_suspicious">
<a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.link_token.is_suspicious">[docs]</a>
<span class="k">def</span> <span class="nf">is_suspicious</span><span class="p">(</span><span class="n">network</span><span class="p">:</span> <span class="n">IPv4Network</span> <span class="o">|</span> <span class="n">IPv6Network</span><span class="p">,</span> <span class="n">request</span><span class="p">:</span> <span class="n">flask</span><span class="o">.</span><span class="n">Request</span><span class="p">,</span> <span class="n">renew</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Checks whether a valid ping is exists for this (client) network, if not</span>
<span class="sd"> this request is rated as *suspicious*. If a valid ping exists and argument</span>
<span class="sd"> ``renew`` is ``True`` the expire time of this ping is reset to</span>
<span class="sd"> :py:obj:`PING_LIVE_TIME`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">redis_client</span> <span class="o">=</span> <span class="n">redisdb</span><span class="o">.</span><span class="n">client</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">redis_client</span><span class="p">:</span>
<span class="k">return</span> <span class="kc">False</span>
<span class="n">ping_key</span> <span class="o">=</span> <span class="n">get_ping_key</span><span class="p">(</span><span class="n">network</span><span class="p">,</span> <span class="n">request</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">redis_client</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">ping_key</span><span class="p">):</span>
<span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;missing ping (IP: </span><span class="si">%s</span><span class="s2">) / request: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">network</span><span class="o">.</span><span class="n">compressed</span><span class="p">,</span> <span class="n">ping_key</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="k">if</span> <span class="n">renew</span><span class="p">:</span>
<span class="n">redis_client</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">ping_key</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">ex</span><span class="o">=</span><span class="n">PING_LIVE_TIME</span><span class="p">)</span>
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;found ping for (client) network </span><span class="si">%s</span><span class="s2"> -&gt; </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">network</span><span class="o">.</span><span class="n">compressed</span><span class="p">,</span> <span class="n">ping_key</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">False</span></div>
<div class="viewcode-block" id="ping">
<a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.link_token.ping">[docs]</a>
<span class="k">def</span> <span class="nf">ping</span><span class="p">(</span><span class="n">request</span><span class="p">:</span> <span class="n">flask</span><span class="o">.</span><span class="n">Request</span><span class="p">,</span> <span class="n">token</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;This function is called by a request to URL ``/client&lt;token&gt;.css``. If</span>
<span class="sd"> ``token`` is valid a :py:obj:`PING_KEY` for the client is stored in the DB.</span>
<span class="sd"> The expire time of this ping-key is :py:obj:`PING_LIVE_TIME`.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="kn">import</span> <span class="n">redis_client</span><span class="p">,</span> <span class="n">cfg</span> <span class="c1"># pylint: disable=import-outside-toplevel, cyclic-import</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">redis_client</span><span class="p">:</span>
<span class="k">return</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">token_is_valid</span><span class="p">(</span><span class="n">token</span><span class="p">):</span>
<span class="k">return</span>
<span class="n">real_ip</span> <span class="o">=</span> <span class="n">ip_address</span><span class="p">(</span><span class="n">get_real_ip</span><span class="p">(</span><span class="n">request</span><span class="p">))</span>
<span class="n">network</span> <span class="o">=</span> <span class="n">get_network</span><span class="p">(</span><span class="n">real_ip</span><span class="p">,</span> <span class="n">cfg</span><span class="p">)</span>
<span class="n">ping_key</span> <span class="o">=</span> <span class="n">get_ping_key</span><span class="p">(</span><span class="n">network</span><span class="p">,</span> <span class="n">request</span><span class="p">)</span>
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;store ping_key for (client) network </span><span class="si">%s</span><span class="s2"> (IP </span><span class="si">%s</span><span class="s2">) -&gt; </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">network</span><span class="o">.</span><span class="n">compressed</span><span class="p">,</span> <span class="n">real_ip</span><span class="p">,</span> <span class="n">ping_key</span><span class="p">)</span>
<span class="n">redis_client</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">ping_key</span><span class="p">,</span> <span class="mi">1</span><span class="p">,</span> <span class="n">ex</span><span class="o">=</span><span class="n">PING_LIVE_TIME</span><span class="p">)</span></div>
<div class="viewcode-block" id="get_ping_key">
<a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.link_token.get_ping_key">[docs]</a>
<span class="k">def</span> <span class="nf">get_ping_key</span><span class="p">(</span><span class="n">network</span><span class="p">:</span> <span class="n">IPv4Network</span> <span class="o">|</span> <span class="n">IPv6Network</span><span class="p">,</span> <span class="n">request</span><span class="p">:</span> <span class="n">flask</span><span class="o">.</span><span class="n">Request</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Generates a hashed key that fits (more or less) to a *WEB-browser</span>
<span class="sd"> session* in a network.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="p">(</span>
<span class="n">PING_KEY</span>
<span class="o">+</span> <span class="s2">&quot;[&quot;</span>
<span class="o">+</span> <span class="n">secret_hash</span><span class="p">(</span>
<span class="n">network</span><span class="o">.</span><span class="n">compressed</span> <span class="o">+</span> <span class="n">request</span><span class="o">.</span><span class="n">headers</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;Accept-Language&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">)</span> <span class="o">+</span> <span class="n">request</span><span class="o">.</span><span class="n">headers</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;User-Agent&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">)</span>
<span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot;]&quot;</span>
<span class="p">)</span></div>
<span class="k">def</span> <span class="nf">token_is_valid</span><span class="p">(</span><span class="n">token</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="n">valid</span> <span class="o">=</span> <span class="n">token</span> <span class="o">==</span> <span class="n">get_token</span><span class="p">()</span>
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;token is valid --&gt; </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">valid</span><span class="p">)</span>
<span class="k">return</span> <span class="n">valid</span>
<div class="viewcode-block" id="get_token">
<a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.link_token.get_token">[docs]</a>
<span class="k">def</span> <span class="nf">get_token</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns current token. If there is no currently active token a new token</span>
<span class="sd"> is generated randomly and stored in the redis DB.</span>
<span class="sd"> - :py:obj:`TOKEN_LIVE_TIME`</span>
<span class="sd"> - :py:obj:`TOKEN_KEY`</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">redis_client</span> <span class="o">=</span> <span class="n">redisdb</span><span class="o">.</span><span class="n">client</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">redis_client</span><span class="p">:</span>
<span class="c1"># This function is also called when limiter is inactive / no redis DB</span>
<span class="c1"># (see render function in webapp.py)</span>
<span class="k">return</span> <span class="s1">&#39;12345678&#39;</span>
<span class="n">token</span> <span class="o">=</span> <span class="n">redis_client</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">TOKEN_KEY</span><span class="p">)</span>
<span class="k">if</span> <span class="n">token</span><span class="p">:</span>
<span class="n">token</span> <span class="o">=</span> <span class="n">token</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">&#39;UTF-8&#39;</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">token</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">choice</span><span class="p">(</span><span class="n">string</span><span class="o">.</span><span class="n">ascii_lowercase</span> <span class="o">+</span> <span class="n">string</span><span class="o">.</span><span class="n">digits</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">16</span><span class="p">))</span>
<span class="n">redis_client</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">TOKEN_KEY</span><span class="p">,</span> <span class="n">token</span><span class="p">,</span> <span class="n">ex</span><span class="o">=</span><span class="n">TOKEN_LIVE_TIME</span><span class="p">)</span>
<span class="k">return</span> <span class="n">token</span></div>
</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/searxng-wordmark.svg" alt="Logo"/>
</a></p>
<h3><a href="../../../index.html">Table of Contents</a></h3>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
</ul>
<h3>Project Links</h3>
<ul>
<li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
<li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
<li><a href="https://searx.space">Public instances</a>
<li><a href="https://github.com/searxng/searxng/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 SearXNG team.
</div>
<script src="../../../_static/version_warning_offset.js"></script>
</body>
</html>