_helpers.html 23 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247
  1. <!DOCTYPE html>
  2. <html lang="en" data-content_root="../../../">
  3. <head>
  4. <meta charset="utf-8" />
  5. <meta name="viewport" content="width=device-width, initial-scale=1.0" />
  6. <meta name="viewport" content="width=device-width, initial-scale=1">
  7. <title>searx.botdetection._helpers &#8212; SearXNG Documentation (2025.5.1+1a1628149)</title>
  8. <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
  9. <link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
  10. <script src="../../../_static/documentation_options.js?v=cc9fc81d"></script>
  11. <script src="../../../_static/doctools.js?v=9a2dae69"></script>
  12. <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
  13. <script data-project="searxng" data-version="2025.5.1+1a1628149" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
  14. <link rel="index" title="Index" href="../../../genindex.html" />
  15. <link rel="search" title="Search" href="../../../search.html" />
  16. </head><body>
  17. <div class="related" role="navigation" aria-label="Related">
  18. <h3>Navigation</h3>
  19. <ul>
  20. <li class="right" style="margin-right: 10px">
  21. <a href="../../../genindex.html" title="General Index"
  22. accesskey="I">index</a></li>
  23. <li class="right" >
  24. <a href="../../../py-modindex.html" title="Python Module Index"
  25. >modules</a> |</li>
  26. <li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2025.5.1+1a1628149)</a> &#187;</li>
  27. <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li>
  28. <li class="nav-item nav-item-this"><a href="">searx.botdetection._helpers</a></li>
  29. </ul>
  30. </div>
  31. <div class="document">
  32. <div class="documentwrapper">
  33. <div class="bodywrapper">
  34. <div class="body" role="main">
  35. <h1>Source code for searx.botdetection._helpers</h1><div class="highlight"><pre>
  36. <span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
  37. <span class="c1"># pylint: disable=missing-module-docstring, invalid-name</span>
  38. <span class="kn">from</span><span class="w"> </span><span class="nn">__future__</span><span class="w"> </span><span class="kn">import</span> <span class="n">annotations</span>
  39. <span class="kn">from</span><span class="w"> </span><span class="nn">ipaddress</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
  40. <span class="n">IPv4Network</span><span class="p">,</span>
  41. <span class="n">IPv6Network</span><span class="p">,</span>
  42. <span class="n">IPv4Address</span><span class="p">,</span>
  43. <span class="n">IPv6Address</span><span class="p">,</span>
  44. <span class="n">ip_network</span><span class="p">,</span>
  45. <span class="n">ip_address</span><span class="p">,</span>
  46. <span class="p">)</span>
  47. <span class="kn">import</span><span class="w"> </span><span class="nn">flask</span>
  48. <span class="kn">import</span><span class="w"> </span><span class="nn">werkzeug</span>
  49. <span class="kn">from</span><span class="w"> </span><span class="nn">searx</span><span class="w"> </span><span class="kn">import</span> <span class="n">logger</span>
  50. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.extended_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">SXNG_Request</span>
  51. <span class="kn">from</span><span class="w"> </span><span class="nn">.</span><span class="w"> </span><span class="kn">import</span> <span class="n">config</span>
  52. <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>
  53. <span class="k">def</span><span class="w"> </span><span class="nf">dump_request</span><span class="p">(</span><span class="n">request</span><span class="p">:</span> <span class="n">SXNG_Request</span><span class="p">):</span>
  54. <span class="k">return</span> <span class="p">(</span>
  55. <span class="n">request</span><span class="o">.</span><span class="n">path</span>
  56. <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>
  57. <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>
  58. <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>
  59. <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>
  60. <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>
  61. <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>
  62. <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>
  63. <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>
  64. <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>
  65. <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>
  66. <span class="p">)</span>
  67. <div class="viewcode-block" id="too_many_requests">
  68. <a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.too_many_requests">[docs]</a>
  69. <span class="k">def</span><span class="w"> </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>
  70. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns a HTTP 429 response object and writes a ERROR message to the</span>
  71. <span class="sd"> &#39;botdetection&#39; logger. This function is used in part by the filter methods</span>
  72. <span class="sd"> to return the default ``Too Many Requests`` response.</span>
  73. <span class="sd"> &quot;&quot;&quot;</span>
  74. <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>
  75. <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>
  76. <div class="viewcode-block" id="get_network">
  77. <a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.get_network">[docs]</a>
  78. <span class="k">def</span><span class="w"> </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>
  79. <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>
  80. <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>
  81. <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>
  82. <span class="k">else</span><span class="p">:</span>
  83. <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>
  84. <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>
  85. <span class="c1"># logger.debug(&quot;get_network(): %s&quot;, network.compressed)</span>
  86. <span class="k">return</span> <span class="n">network</span></div>
  87. <span class="n">_logged_errors</span> <span class="o">=</span> <span class="p">[]</span>
  88. <span class="k">def</span><span class="w"> </span><span class="nf">_log_error_only_once</span><span class="p">(</span><span class="n">err_msg</span><span class="p">):</span>
  89. <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>
  90. <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>
  91. <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>
  92. <div class="viewcode-block" id="get_real_ip">
  93. <a class="viewcode-back" href="../../../src/searx.botdetection.html#searx.botdetection.get_real_ip">[docs]</a>
  94. <span class="k">def</span><span class="w"> </span><span class="nf">get_real_ip</span><span class="p">(</span><span class="n">request</span><span class="p">:</span> <span class="n">SXNG_Request</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  95. <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>
  96. <span class="sd"> headers and incoming headers can be faked it may happen that the IP cannot</span>
  97. <span class="sd"> be determined correctly.</span>
  98. <span class="sd"> .. sidebar:: :py:obj:`flask.Request.remote_addr`</span>
  99. <span class="sd"> SearXNG uses Werkzeug&#39;s ProxyFix_ (with it default ``x_for=1``).</span>
  100. <span class="sd"> This function tries to get the remote IP in the order listed below,</span>
  101. <span class="sd"> additional some tests are done and if inconsistencies or errors are</span>
  102. <span class="sd"> detected, they are logged.</span>
  103. <span class="sd"> The remote IP of the request is taken from (first match):</span>
  104. <span class="sd"> - X-Forwarded-For_ header</span>
  105. <span class="sd"> - `X-real-IP header &lt;https://github.com/searxng/searxng/issues/1237#issuecomment-1147564516&gt;`__</span>
  106. <span class="sd"> - :py:obj:`flask.Request.remote_addr`</span>
  107. <span class="sd"> .. _ProxyFix:</span>
  108. <span class="sd"> https://werkzeug.palletsprojects.com/middleware/proxy_fix/</span>
  109. <span class="sd"> .. _X-Forwarded-For:</span>
  110. <span class="sd"> https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Forwarded-For</span>
  111. <span class="sd"> &quot;&quot;&quot;</span>
  112. <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>
  113. <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>
  114. <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>
  115. <span class="c1"># logger.debug(</span>
  116. <span class="c1"># &quot;X-Forwarded-For: %s || X-Real-IP: %s || request.remote_addr: %s&quot;, forwarded_for, real_ip, remote_addr</span>
  117. <span class="c1"># )</span>
  118. <span class="k">if</span> <span class="ow">not</span> <span class="n">forwarded_for</span><span class="p">:</span>
  119. <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>
  120. <span class="k">else</span><span class="p">:</span>
  121. <span class="kn">from</span><span class="w"> </span><span class="nn">.</span><span class="w"> </span><span class="kn">import</span> <span class="n">cfg</span> <span class="c1"># pylint: disable=import-outside-toplevel, cyclic-import</span>
  122. <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>
  123. <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>
  124. <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>
  125. <span class="k">if</span> <span class="ow">not</span> <span class="n">real_ip</span><span class="p">:</span>
  126. <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>
  127. <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>
  128. <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>
  129. <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>
  130. <span class="n">logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span>
  131. <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>
  132. <span class="p">)</span>
  133. <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>
  134. <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>
  135. <span class="n">request_ip</span> <span class="o">=</span> <span class="n">ip_address</span><span class="p">(</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="p">)</span>
  136. <span class="k">if</span> <span class="n">request_ip</span><span class="o">.</span><span class="n">version</span> <span class="o">==</span> <span class="mi">6</span> <span class="ow">and</span> <span class="n">request_ip</span><span class="o">.</span><span class="n">ipv4_mapped</span><span class="p">:</span>
  137. <span class="n">request_ip</span> <span class="o">=</span> <span class="n">request_ip</span><span class="o">.</span><span class="n">ipv4_mapped</span>
  138. <span class="c1"># logger.debug(&quot;get_real_ip() -&gt; %s&quot;, request_ip)</span>
  139. <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">request_ip</span><span class="p">)</span></div>
  140. </pre></div>
  141. <div class="clearer"></div>
  142. </div>
  143. </div>
  144. </div>
  145. <span id="sidebar-top"></span>
  146. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  147. <div class="sphinxsidebarwrapper">
  148. <p class="logo"><a href="../../../index.html">
  149. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  150. </a></p>
  151. <h3><a href="../../../index.html">Table of Contents</a></h3>
  152. <ul>
  153. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  154. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  155. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  156. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  157. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  158. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  159. </ul>
  160. <h3>Project Links</h3>
  161. <ul>
  162. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  163. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  164. <li><a href="https://searx.space">Public instances</a>
  165. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  166. </ul><h3>Navigation</h3>
  167. <ul>
  168. <li><a href="../../../index.html">Overview</a>
  169. <ul>
  170. <li><a href="../../index.html">Module code</a>
  171. </ul>
  172. </li>
  173. </ul>
  174. </li>
  175. </ul>
  176. <search id="searchbox" style="display: none" role="search">
  177. <h3 id="searchlabel">Quick search</h3>
  178. <div class="searchformwrapper">
  179. <form class="search" action="../../../search.html" method="get">
  180. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  181. <input type="submit" value="Go" />
  182. </form>
  183. </div>
  184. </search>
  185. <script>document.getElementById('searchbox').style.display = "block"</script>
  186. </div>
  187. </div>
  188. <div class="clearer"></div>
  189. </div>
  190. <div class="footer" role="contentinfo">
  191. &#169; Copyright SearXNG team.
  192. </div>
  193. </body>
  194. </html>