jandieman
/
searxng
mirror of https://github.com/searxng/searxng.git
2
0
Fork 0
Code Issues Projects Releases Wiki Activity
searxng/_modules/searx/botdetection/_helpers.html

242 lines
22 KiB
HTML
Raw Normal View History

[doc] build from commit 0f9694c90b012834400d11491a3c58790a857f6d
2024-11-23 17:01:29 +00:00
<!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._helpers &#8212; SearXNG Documentation (2024.11.23+0f9694c90)</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/autodoc_pydantic.css" />
<script src="../../../_static/documentation_options.js?v=1b1224d6"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script data-project="searxng" data-version="2024.11.23+0f9694c90" src="../../../_static/describe_version.js?v=fa7f30d0"></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">
<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 (2024.11.23+0f9694c90)</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._helpers</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for searx.botdetection._helpers</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
<span class="c1"># pylint: disable=missing-module-docstring, invalid-name</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">IPv4Address</span><span class="p">,</span>
<span class="n">IPv6Address</span><span class="p">,</span>
<span class="n">ip_network</span><span class="p">,</span>
<span class="p">)</span>
<span class="kn">import</span> <span class="nn">flask</span>
<span class="kn">import</span> <span class="nn">werkzeug</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">.</span> <span class="kn">import</span> <span class="n">config</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&#39;</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">dump_request</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="k">return</span> <span class="p">(</span>
<span class="n">request</span><span class="o">.</span><span class="n">path</span>
<span class="o">+</span> <span class="s2">&quot; || X-Forwarded-For: </span><span class="si">%s</span><span class="s2">&quot;</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;X-Forwarded-For&#39;</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot; || X-Real-IP: </span><span class="si">%s</span><span class="s2">&quot;</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;X-Real-IP&#39;</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot; || form: </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">request</span><span class="o">.</span><span class="n">form</span>
<span class="o">+</span> <span class="s2">&quot; || Accept: </span><span class="si">%s</span><span class="s2">&quot;</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&#39;</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot; || Accept-Language: </span><span class="si">%s</span><span class="s2">&quot;</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="o">+</span> <span class="s2">&quot; || Accept-Encoding: </span><span class="si">%s</span><span class="s2">&quot;</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-Encoding&#39;</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot; || Content-Type: </span><span class="si">%s</span><span class="s2">&quot;</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;Content-Type&#39;</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot; || Content-Length: </span><span class="si">%s</span><span class="s2">&quot;</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;Content-Length&#39;</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot; || Connection: </span><span class="si">%s</span><span class="s2">&quot;</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;Connection&#39;</span><span class="p">)</span>
<span class="o">+</span> <span class="s2">&quot; || User-Agent: </span><span class="si">%s</span><span class="s2">&quot;</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="p">)</span>
<div class="viewcode-block" id="too_many_requests">
<a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.too_many_requests">[docs]</a>
<span class="k">def</span> <span class="nf">too_many_requests</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">log_msg</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">werkzeug</span><span class="o">.</span><span class="n">Response</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns a HTTP 429 response object and writes a ERROR message to the</span>
<span class="sd"> &#39;botdetection&#39; logger. This function is used in part by the filter methods</span>
<span class="sd"> to return the default ``Too Many Requests`` response.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;BLOCK </span><span class="si">%s</span><span class="s2">: </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">log_msg</span><span class="p">)</span>
<span class="k">return</span> <span class="n">flask</span><span class="o">.</span><span class="n">make_response</span><span class="p">((</span><span class="s1">&#39;Too Many Requests&#39;</span><span class="p">,</span> <span class="mi">429</span><span class="p">))</span></div>
<div class="viewcode-block" id="get_network">
<a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.get_network">[docs]</a>
<span class="k">def</span> <span class="nf">get_network</span><span class="p">(</span><span class="n">real_ip</span><span class="p">:</span> <span class="n">IPv4Address</span> <span class="o">|</span> <span class="n">IPv6Address</span><span class="p">,</span> <span class="n">cfg</span><span class="p">:</span> <span class="n">config</span><span class="o">.</span><span class="n">Config</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">IPv4Network</span> <span class="o">|</span> <span class="n">IPv6Network</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the (client) network of whether the real_ip is part of.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">real_ip</span><span class="o">.</span><span class="n">version</span> <span class="o">==</span> <span class="mi">6</span><span class="p">:</span>
<span class="n">prefix</span> <span class="o">=</span> <span class="n">cfg</span><span class="p">[</span><span class="s1">&#39;real_ip.ipv6_prefix&#39;</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">prefix</span> <span class="o">=</span> <span class="n">cfg</span><span class="p">[</span><span class="s1">&#39;real_ip.ipv4_prefix&#39;</span><span class="p">]</span>
<span class="n">network</span> <span class="o">=</span> <span class="n">ip_network</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">real_ip</span><span class="si">}</span><span class="s2">/</span><span class="si">{</span><span class="n">prefix</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">strict</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
<span class="c1"># logger.debug(&quot;get_network(): %s&quot;, network.compressed)</span>
<span class="k">return</span> <span class="n">network</span></div>
<span class="n">_logged_errors</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">def</span> <span class="nf">_log_error_only_once</span><span class="p">(</span><span class="n">err_msg</span><span class="p">):</span>
<span class="k">if</span> <span class="n">err_msg</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">_logged_errors</span><span class="p">:</span>
<span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">err_msg</span><span class="p">)</span>
<span class="n">_logged_errors</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">err_msg</span><span class="p">)</span>
<div class="viewcode-block" id="get_real_ip">
<a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.get_real_ip">[docs]</a>
<span class="k">def</span> <span class="nf">get_real_ip</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;Returns real IP of the request. Since not all proxies set all the HTTP</span>
<span class="sd"> headers and incoming headers can be faked it may happen that the IP cannot</span>
<span class="sd"> be determined correctly.</span>
<span class="sd"> .. sidebar:: :py:obj:`flask.Request.remote_addr`</span>
<span class="sd"> SearXNG uses Werkzeug&#39;s ProxyFix_ (with it default ``x_for=1``).</span>
<span class="sd"> This function tries to get the remote IP in the order listed below,</span>
<span class="sd"> additional some tests are done and if inconsistencies or errors are</span>
<span class="sd"> detected, they are logged.</span>
<span class="sd"> The remote IP of the request is taken from (first match):</span>
<span class="sd"> - X-Forwarded-For_ header</span>
<span class="sd"> - `X-real-IP header &lt;https://github.com/searxng/searxng/issues/1237#issuecomment-1147564516&gt;`__</span>
<span class="sd"> - :py:obj:`flask.Request.remote_addr`</span>
<span class="sd"> .. _ProxyFix:</span>
<span class="sd"> https://werkzeug.palletsprojects.com/middleware/proxy_fix/</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="n">forwarded_for</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="s2">&quot;X-Forwarded-For&quot;</span><span class="p">)</span>
<span class="n">real_ip</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;X-Real-IP&#39;</span><span class="p">)</span>
<span class="n">remote_addr</span> <span class="o">=</span> <span class="n">request</span><span class="o">.</span><span class="n">remote_addr</span>
<span class="c1"># logger.debug(</span>
<span class="c1"># &quot;X-Forwarded-For: %s || X-Real-IP: %s || request.remote_addr: %s&quot;, forwarded_for, real_ip, remote_addr</span>
<span class="c1"># )</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">forwarded_for</span><span class="p">:</span>
<span class="n">_log_error_only_once</span><span class="p">(</span><span class="s2">&quot;X-Forwarded-For header is not set!&quot;</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="kn">import</span> <span class="n">cfg</span> <span class="c1"># pylint: disable=import-outside-toplevel, cyclic-import</span>
<span class="n">forwarded_for</span> <span class="o">=</span> <span class="p">[</span><span class="n">x</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">forwarded_for</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;,&#39;</span><span class="p">)]</span>
<span class="n">x_for</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">cfg</span><span class="p">[</span><span class="s1">&#39;real_ip.x_for&#39;</span><span class="p">]</span> <span class="c1"># type: ignore</span>
<span class="n">forwarded_for</span> <span class="o">=</span> <span class="n">forwarded_for</span><span class="p">[</span><span class="o">-</span><span class="nb">min</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">forwarded_for</span><span class="p">),</span> <span class="n">x_for</span><span class="p">)]</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">real_ip</span><span class="p">:</span>
<span class="n">_log_error_only_once</span><span class="p">(</span><span class="s2">&quot;X-Real-IP header is not set!&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">forwarded_for</span> <span class="ow">and</span> <span class="n">real_ip</span> <span class="ow">and</span> <span class="n">forwarded_for</span> <span class="o">!=</span> <span class="n">real_ip</span><span class="p">:</span>
<span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">&quot;IP from X-Real-IP (</span><span class="si">%s</span><span class="s2">) is not equal to IP from X-Forwarded-For (</span><span class="si">%s</span><span class="s2">)&quot;</span><span class="p">,</span> <span class="n">real_ip</span><span class="p">,</span> <span class="n">forwarded_for</span><span class="p">)</span>
<span class="k">if</span> <span class="n">forwarded_for</span> <span class="ow">and</span> <span class="n">remote_addr</span> <span class="ow">and</span> <span class="n">forwarded_for</span> <span class="o">!=</span> <span class="n">remote_addr</span><span class="p">:</span>
<span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span>
<span class="s2">&quot;IP from WSGI environment (</span><span class="si">%s</span><span class="s2">) is not equal to IP from X-Forwarded-For (</span><span class="si">%s</span><span class="s2">)&quot;</span><span class="p">,</span> <span class="n">remote_addr</span><span class="p">,</span> <span class="n">forwarded_for</span>
<span class="p">)</span>
<span class="k">if</span> <span class="n">real_ip</span> <span class="ow">and</span> <span class="n">remote_addr</span> <span class="ow">and</span> <span class="n">real_ip</span> <span class="o">!=</span> <span class="n">remote_addr</span><span class="p">:</span>
<span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">&quot;IP from WSGI environment (</span><span class="si">%s</span><span class="s2">) is not equal to IP from X-Real-IP (</span><span class="si">%s</span><span class="s2">)&quot;</span><span class="p">,</span> <span class="n">remote_addr</span><span class="p">,</span> <span class="n">real_ip</span><span class="p">)</span>
<span class="n">request_ip</span> <span class="o">=</span> <span class="n">forwarded_for</span> <span class="ow">or</span> <span class="n">real_ip</span> <span class="ow">or</span> <span class="n">remote_addr</span> <span class="ow">or</span> <span class="s1">&#39;0.0.0.0&#39;</span>
<span class="c1"># logger.debug(&quot;get_real_ip() -&gt; %s&quot;, request_ip)</span>
<span class="k">return</span> <span class="n">request_ip</span></div>
</pre></div>
<div class="clearer"></div>
</div>
</div>
</div>
<span id="sidebar-top"></span>
<div class="sphinxsidebar" role="navigation" aria-label="Main">
<div class="sphinxsidebarwrapper">
<p class="logo"><a href="../../../index.html">
<img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
</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>
<search 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>
</search>
<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>
</body>
</html>