update_external_bangs.html 20 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250
  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>searxng_extra.update.update_external_bangs &#8212; SearXNG Documentation (2025.4.30+fd33559cf)</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=b12b0e12"></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="2025.4.30+fd33559cf" 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 (2025.4.30+fd33559cf)</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="">searxng_extra.update.update_external_bangs</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 searxng_extra.update.update_external_bangs</h1><div class="highlight"><pre>
  36. <span></span><span class="ch">#!/usr/bin/env python</span>
  37. <span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
  38. <span class="sd">&quot;&quot;&quot;Update :origin:`searx/data/external_bangs.json` using the duckduckgo bangs</span>
  39. <span class="sd">from :py:obj:`BANGS_URL`.</span>
  40. <span class="sd">- :origin:`CI Update data ... &lt;.github/workflows/data-update.yml&gt;`</span>
  41. <span class="sd">&quot;&quot;&quot;</span>
  42. <span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
  43. <span class="kn">import</span><span class="w"> </span><span class="nn">httpx</span>
  44. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.external_bang</span><span class="w"> </span><span class="kn">import</span> <span class="n">LEAF_KEY</span>
  45. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">data_dir</span>
  46. <span class="n">DATA_FILE</span> <span class="o">=</span> <span class="n">data_dir</span> <span class="o">/</span> <span class="s1">&#39;external_bangs.json&#39;</span>
  47. <span class="n">BANGS_URL</span> <span class="o">=</span> <span class="s1">&#39;https://duckduckgo.com/bang.js&#39;</span>
  48. <span class="sd">&quot;&quot;&quot;JSON file which contains the bangs.&quot;&quot;&quot;</span>
  49. <span class="n">HTTPS_COLON</span> <span class="o">=</span> <span class="s1">&#39;https:&#39;</span>
  50. <span class="n">HTTP_COLON</span> <span class="o">=</span> <span class="s1">&#39;http:&#39;</span>
  51. <span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
  52. <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;fetch bangs from </span><span class="si">{</span><span class="n">BANGS_URL</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">)</span>
  53. <span class="n">response</span> <span class="o">=</span> <span class="n">httpx</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">BANGS_URL</span><span class="p">)</span>
  54. <span class="n">response</span><span class="o">.</span><span class="n">raise_for_status</span><span class="p">()</span>
  55. <span class="n">ddg_bangs</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">decode</span><span class="p">())</span>
  56. <span class="n">trie</span> <span class="o">=</span> <span class="n">parse_ddg_bangs</span><span class="p">(</span><span class="n">ddg_bangs</span><span class="p">)</span>
  57. <span class="n">output</span> <span class="o">=</span> <span class="p">{</span>
  58. <span class="s1">&#39;version&#39;</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
  59. <span class="s1">&#39;trie&#39;</span><span class="p">:</span> <span class="n">trie</span><span class="p">,</span>
  60. <span class="p">}</span>
  61. <span class="k">with</span> <span class="n">DATA_FILE</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="s1">&#39;w&#39;</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s2">&quot;utf8&quot;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
  62. <span class="n">json</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">f</span><span class="p">,</span> <span class="n">indent</span><span class="o">=</span><span class="mi">4</span><span class="p">,</span> <span class="n">sort_keys</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">ensure_ascii</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
  63. <div class="viewcode-block" id="merge_when_no_leaf">
  64. <a class="viewcode-back" href="../../../dev/searxng_extra/update.html#searxng_extra.update.update_external_bangs.merge_when_no_leaf">[docs]</a>
  65. <span class="k">def</span><span class="w"> </span><span class="nf">merge_when_no_leaf</span><span class="p">(</span><span class="n">node</span><span class="p">):</span>
  66. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Minimize the number of nodes</span>
  67. <span class="sd"> ``A -&gt; B -&gt; C``</span>
  68. <span class="sd"> - ``B`` is child of ``A``</span>
  69. <span class="sd"> - ``C`` is child of ``B``</span>
  70. <span class="sd"> If there are no ``C`` equals to ``&lt;LEAF_KEY&gt;``, then each ``C`` are merged</span>
  71. <span class="sd"> into ``A``. For example (5 nodes)::</span>
  72. <span class="sd"> d -&gt; d -&gt; g -&gt; &lt;LEAF_KEY&gt; (ddg)</span>
  73. <span class="sd"> -&gt; i -&gt; g -&gt; &lt;LEAF_KEY&gt; (dig)</span>
  74. <span class="sd"> becomes (3 nodes)::</span>
  75. <span class="sd"> d -&gt; dg -&gt; &lt;LEAF_KEY&gt;</span>
  76. <span class="sd"> -&gt; ig -&gt; &lt;LEAF_KEY&gt;</span>
  77. <span class="sd"> &quot;&quot;&quot;</span>
  78. <span class="n">restart</span> <span class="o">=</span> <span class="kc">False</span>
  79. <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
  80. <span class="k">return</span>
  81. <span class="c1"># create a copy of the keys so node can be modified</span>
  82. <span class="n">keys</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span>
  83. <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">keys</span><span class="p">:</span>
  84. <span class="k">if</span> <span class="n">key</span> <span class="o">==</span> <span class="n">LEAF_KEY</span><span class="p">:</span>
  85. <span class="k">continue</span>
  86. <span class="n">value</span> <span class="o">=</span> <span class="n">node</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
  87. <span class="n">value_keys</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">value</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span>
  88. <span class="k">if</span> <span class="n">LEAF_KEY</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">value_keys</span><span class="p">:</span>
  89. <span class="k">for</span> <span class="n">value_key</span> <span class="ow">in</span> <span class="n">value_keys</span><span class="p">:</span>
  90. <span class="n">node</span><span class="p">[</span><span class="n">key</span> <span class="o">+</span> <span class="n">value_key</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span><span class="p">[</span><span class="n">value_key</span><span class="p">]</span>
  91. <span class="n">merge_when_no_leaf</span><span class="p">(</span><span class="n">node</span><span class="p">[</span><span class="n">key</span> <span class="o">+</span> <span class="n">value_key</span><span class="p">])</span>
  92. <span class="k">del</span> <span class="n">node</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
  93. <span class="n">restart</span> <span class="o">=</span> <span class="kc">True</span>
  94. <span class="k">else</span><span class="p">:</span>
  95. <span class="n">merge_when_no_leaf</span><span class="p">(</span><span class="n">value</span><span class="p">)</span>
  96. <span class="k">if</span> <span class="n">restart</span><span class="p">:</span>
  97. <span class="n">merge_when_no_leaf</span><span class="p">(</span><span class="n">node</span><span class="p">)</span></div>
  98. <span class="k">def</span><span class="w"> </span><span class="nf">optimize_leaf</span><span class="p">(</span><span class="n">parent</span><span class="p">,</span> <span class="n">parent_key</span><span class="p">,</span> <span class="n">node</span><span class="p">):</span>
  99. <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
  100. <span class="k">return</span>
  101. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">node</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="n">LEAF_KEY</span> <span class="ow">in</span> <span class="n">node</span> <span class="ow">and</span> <span class="n">parent</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
  102. <span class="n">parent</span><span class="p">[</span><span class="n">parent_key</span><span class="p">]</span> <span class="o">=</span> <span class="n">node</span><span class="p">[</span><span class="n">LEAF_KEY</span><span class="p">]</span>
  103. <span class="k">else</span><span class="p">:</span>
  104. <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">node</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
  105. <span class="n">optimize_leaf</span><span class="p">(</span><span class="n">node</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
  106. <span class="k">def</span><span class="w"> </span><span class="nf">parse_ddg_bangs</span><span class="p">(</span><span class="n">ddg_bangs</span><span class="p">):</span>
  107. <span class="n">bang_trie</span> <span class="o">=</span> <span class="p">{}</span>
  108. <span class="n">bang_urls</span> <span class="o">=</span> <span class="p">{}</span>
  109. <span class="k">for</span> <span class="n">bang_definition</span> <span class="ow">in</span> <span class="n">ddg_bangs</span><span class="p">:</span>
  110. <span class="c1"># bang_list</span>
  111. <span class="n">bang_url</span> <span class="o">=</span> <span class="n">bang_definition</span><span class="p">[</span><span class="s1">&#39;u&#39;</span><span class="p">]</span>
  112. <span class="k">if</span> <span class="s1">&#39;{{</span><span class="si">{s}</span><span class="s1">}}&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">bang_url</span><span class="p">:</span>
  113. <span class="c1"># ignore invalid bang</span>
  114. <span class="k">continue</span>
  115. <span class="n">bang_url</span> <span class="o">=</span> <span class="n">bang_url</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;{{</span><span class="si">{s}</span><span class="s1">}}&#39;</span><span class="p">,</span> <span class="nb">chr</span><span class="p">(</span><span class="mi">2</span><span class="p">))</span>
  116. <span class="c1"># only for the https protocol: &quot;https://example.com&quot; becomes &quot;//example.com&quot;</span>
  117. <span class="k">if</span> <span class="n">bang_url</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">HTTPS_COLON</span> <span class="o">+</span> <span class="s1">&#39;//&#39;</span><span class="p">):</span>
  118. <span class="n">bang_url</span> <span class="o">=</span> <span class="n">bang_url</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">HTTPS_COLON</span><span class="p">)</span> <span class="p">:]</span>
  119. <span class="c1">#</span>
  120. <span class="k">if</span> <span class="n">bang_url</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">HTTP_COLON</span> <span class="o">+</span> <span class="s1">&#39;//&#39;</span><span class="p">)</span> <span class="ow">and</span> <span class="n">bang_url</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">HTTP_COLON</span><span class="p">)</span> <span class="p">:]</span> <span class="ow">in</span> <span class="n">bang_urls</span><span class="p">:</span>
  121. <span class="c1"># if the bang_url uses the http:// protocol, and the same URL exists in https://</span>
  122. <span class="c1"># then reuse the https:// bang definition. (written //example.com)</span>
  123. <span class="n">bang_def_output</span> <span class="o">=</span> <span class="n">bang_urls</span><span class="p">[</span><span class="n">bang_url</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">HTTP_COLON</span><span class="p">)</span> <span class="p">:]]</span>
  124. <span class="k">else</span><span class="p">:</span>
  125. <span class="c1"># normal use case : new http:// URL or https:// URL (without &quot;https:&quot;, see above)</span>
  126. <span class="n">bang_rank</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">bang_definition</span><span class="p">[</span><span class="s1">&#39;r&#39;</span><span class="p">])</span>
  127. <span class="n">bang_def_output</span> <span class="o">=</span> <span class="n">bang_url</span> <span class="o">+</span> <span class="nb">chr</span><span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="o">+</span> <span class="n">bang_rank</span>
  128. <span class="n">bang_def_output</span> <span class="o">=</span> <span class="n">bang_urls</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="n">bang_url</span><span class="p">,</span> <span class="n">bang_def_output</span><span class="p">)</span>
  129. <span class="n">bang_urls</span><span class="p">[</span><span class="n">bang_url</span><span class="p">]</span> <span class="o">=</span> <span class="n">bang_def_output</span>
  130. <span class="c1"># bang name</span>
  131. <span class="n">bang</span> <span class="o">=</span> <span class="n">bang_definition</span><span class="p">[</span><span class="s1">&#39;t&#39;</span><span class="p">]</span>
  132. <span class="c1"># bang_trie</span>
  133. <span class="n">t</span> <span class="o">=</span> <span class="n">bang_trie</span>
  134. <span class="k">for</span> <span class="n">bang_letter</span> <span class="ow">in</span> <span class="n">bang</span><span class="p">:</span>
  135. <span class="n">t</span> <span class="o">=</span> <span class="n">t</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="n">bang_letter</span><span class="p">,</span> <span class="p">{})</span>
  136. <span class="n">t</span> <span class="o">=</span> <span class="n">t</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="n">LEAF_KEY</span><span class="p">,</span> <span class="n">bang_def_output</span><span class="p">)</span>
  137. <span class="c1"># optimize the trie</span>
  138. <span class="n">merge_when_no_leaf</span><span class="p">(</span><span class="n">bang_trie</span><span class="p">)</span>
  139. <span class="n">optimize_leaf</span><span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="n">bang_trie</span><span class="p">)</span>
  140. <span class="k">return</span> <span class="n">bang_trie</span>
  141. <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
  142. <span class="n">main</span><span class="p">()</span>
  143. </pre></div>
  144. <div class="clearer"></div>
  145. </div>
  146. </div>
  147. </div>
  148. <span id="sidebar-top"></span>
  149. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  150. <div class="sphinxsidebarwrapper">
  151. <p class="logo"><a href="../../../index.html">
  152. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  153. </a></p>
  154. <h3><a href="../../../index.html">Table of Contents</a></h3>
  155. <ul>
  156. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  157. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  158. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  159. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  160. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  161. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  162. </ul>
  163. <h3>Project Links</h3>
  164. <ul>
  165. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  166. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  167. <li><a href="https://searx.space">Public instances</a>
  168. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  169. </ul><h3>Navigation</h3>
  170. <ul>
  171. <li><a href="../../../index.html">Overview</a>
  172. <ul>
  173. <li><a href="../../index.html">Module code</a>
  174. </ul>
  175. </li>
  176. </ul>
  177. </li>
  178. </ul>
  179. <search id="searchbox" style="display: none" role="search">
  180. <h3 id="searchlabel">Quick search</h3>
  181. <div class="searchformwrapper">
  182. <form class="search" action="../../../search.html" method="get">
  183. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  184. <input type="submit" value="Go" />
  185. </form>
  186. </div>
  187. </search>
  188. <script>document.getElementById('searchbox').style.display = "block"</script>
  189. </div>
  190. </div>
  191. <div class="clearer"></div>
  192. </div>
  193. <div class="footer" role="contentinfo">
  194. &#169; Copyright SearXNG team.
  195. </div>
  196. </body>
  197. </html>