yahoo.html 28 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304
  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.engines.yahoo &#8212; SearXNG Documentation (2025.5.2+590b21165)</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=8c00f3b4"></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="2025.5.2+590b21165" 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 (2025.5.2+590b21165)</a> &#187;</li>
  27. <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li>
  28. <li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> &#187;</li>
  29. <li class="nav-item nav-item-this"><a href="">searx.engines.yahoo</a></li>
  30. </ul>
  31. </div>
  32. <div class="document">
  33. <div class="documentwrapper">
  34. <div class="bodywrapper">
  35. <div class="body" role="main">
  36. <h1>Source code for searx.engines.yahoo</h1><div class="highlight"><pre>
  37. <span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
  38. <span class="sd">&quot;&quot;&quot;Yahoo Search (Web)</span>
  39. <span class="sd">Languages are supported by mapping the language to a domain. If domain is not</span>
  40. <span class="sd">found in :py:obj:`lang2domain` URL ``&lt;lang&gt;.search.yahoo.com`` is used.</span>
  41. <span class="sd">&quot;&quot;&quot;</span>
  42. <span class="kn">from</span><span class="w"> </span><span class="nn">urllib.parse</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
  43. <span class="n">unquote</span><span class="p">,</span>
  44. <span class="n">urlencode</span><span class="p">,</span>
  45. <span class="p">)</span>
  46. <span class="kn">from</span><span class="w"> </span><span class="nn">lxml</span><span class="w"> </span><span class="kn">import</span> <span class="n">html</span>
  47. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.utils</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
  48. <span class="n">eval_xpath_getindex</span><span class="p">,</span>
  49. <span class="n">eval_xpath_list</span><span class="p">,</span>
  50. <span class="n">extract_text</span><span class="p">,</span>
  51. <span class="n">html_to_text</span><span class="p">,</span>
  52. <span class="p">)</span>
  53. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.enginelib.traits</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineTraits</span>
  54. <span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
  55. <span class="c1"># about</span>
  56. <span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
  57. <span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="s1">&#39;https://search.yahoo.com/&#39;</span><span class="p">,</span>
  58. <span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
  59. <span class="s2">&quot;official_api_documentation&quot;</span><span class="p">:</span> <span class="s1">&#39;https://developer.yahoo.com/api/&#39;</span><span class="p">,</span>
  60. <span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  61. <span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  62. <span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s1">&#39;HTML&#39;</span><span class="p">,</span>
  63. <span class="p">}</span>
  64. <span class="c1"># engine dependent config</span>
  65. <span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;general&#39;</span><span class="p">,</span> <span class="s1">&#39;web&#39;</span><span class="p">]</span>
  66. <span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
  67. <span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
  68. <span class="c1"># send_accept_language_header = True</span>
  69. <span class="n">time_range_dict</span> <span class="o">=</span> <span class="p">{</span>
  70. <span class="s1">&#39;day&#39;</span><span class="p">:</span> <span class="p">(</span><span class="s1">&#39;1d&#39;</span><span class="p">,</span> <span class="s1">&#39;d&#39;</span><span class="p">),</span>
  71. <span class="s1">&#39;week&#39;</span><span class="p">:</span> <span class="p">(</span><span class="s1">&#39;1w&#39;</span><span class="p">,</span> <span class="s1">&#39;w&#39;</span><span class="p">),</span>
  72. <span class="s1">&#39;month&#39;</span><span class="p">:</span> <span class="p">(</span><span class="s1">&#39;1m&#39;</span><span class="p">,</span> <span class="s1">&#39;m&#39;</span><span class="p">),</span>
  73. <span class="p">}</span>
  74. <span class="n">lang2domain</span> <span class="o">=</span> <span class="p">{</span>
  75. <span class="s1">&#39;zh_chs&#39;</span><span class="p">:</span> <span class="s1">&#39;hk.search.yahoo.com&#39;</span><span class="p">,</span>
  76. <span class="s1">&#39;zh_cht&#39;</span><span class="p">:</span> <span class="s1">&#39;tw.search.yahoo.com&#39;</span><span class="p">,</span>
  77. <span class="s1">&#39;any&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  78. <span class="s1">&#39;en&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  79. <span class="s1">&#39;bg&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  80. <span class="s1">&#39;cs&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  81. <span class="s1">&#39;da&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  82. <span class="s1">&#39;el&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  83. <span class="s1">&#39;et&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  84. <span class="s1">&#39;he&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  85. <span class="s1">&#39;hr&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  86. <span class="s1">&#39;ja&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  87. <span class="s1">&#39;ko&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  88. <span class="s1">&#39;sk&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  89. <span class="s1">&#39;sl&#39;</span><span class="p">:</span> <span class="s1">&#39;search.yahoo.com&#39;</span><span class="p">,</span>
  90. <span class="p">}</span>
  91. <span class="sd">&quot;&quot;&quot;Map language to domain&quot;&quot;&quot;</span>
  92. <span class="n">yahoo_languages</span> <span class="o">=</span> <span class="p">{</span>
  93. <span class="s2">&quot;all&quot;</span><span class="p">:</span> <span class="s2">&quot;any&quot;</span><span class="p">,</span>
  94. <span class="s2">&quot;ar&quot;</span><span class="p">:</span> <span class="s2">&quot;ar&quot;</span><span class="p">,</span>
  95. <span class="s2">&quot;bg&quot;</span><span class="p">:</span> <span class="s2">&quot;bg&quot;</span><span class="p">,</span>
  96. <span class="s2">&quot;cs&quot;</span><span class="p">:</span> <span class="s2">&quot;cs&quot;</span><span class="p">,</span>
  97. <span class="s2">&quot;da&quot;</span><span class="p">:</span> <span class="s2">&quot;da&quot;</span><span class="p">,</span>
  98. <span class="s2">&quot;de&quot;</span><span class="p">:</span> <span class="s2">&quot;de&quot;</span><span class="p">,</span>
  99. <span class="s2">&quot;el&quot;</span><span class="p">:</span> <span class="s2">&quot;el&quot;</span><span class="p">,</span>
  100. <span class="s2">&quot;en&quot;</span><span class="p">:</span> <span class="s2">&quot;en&quot;</span><span class="p">,</span>
  101. <span class="s2">&quot;es&quot;</span><span class="p">:</span> <span class="s2">&quot;es&quot;</span><span class="p">,</span>
  102. <span class="s2">&quot;et&quot;</span><span class="p">:</span> <span class="s2">&quot;et&quot;</span><span class="p">,</span>
  103. <span class="s2">&quot;fi&quot;</span><span class="p">:</span> <span class="s2">&quot;fi&quot;</span><span class="p">,</span>
  104. <span class="s2">&quot;fr&quot;</span><span class="p">:</span> <span class="s2">&quot;fr&quot;</span><span class="p">,</span>
  105. <span class="s2">&quot;he&quot;</span><span class="p">:</span> <span class="s2">&quot;he&quot;</span><span class="p">,</span>
  106. <span class="s2">&quot;hr&quot;</span><span class="p">:</span> <span class="s2">&quot;hr&quot;</span><span class="p">,</span>
  107. <span class="s2">&quot;hu&quot;</span><span class="p">:</span> <span class="s2">&quot;hu&quot;</span><span class="p">,</span>
  108. <span class="s2">&quot;it&quot;</span><span class="p">:</span> <span class="s2">&quot;it&quot;</span><span class="p">,</span>
  109. <span class="s2">&quot;ja&quot;</span><span class="p">:</span> <span class="s2">&quot;ja&quot;</span><span class="p">,</span>
  110. <span class="s2">&quot;ko&quot;</span><span class="p">:</span> <span class="s2">&quot;ko&quot;</span><span class="p">,</span>
  111. <span class="s2">&quot;lt&quot;</span><span class="p">:</span> <span class="s2">&quot;lt&quot;</span><span class="p">,</span>
  112. <span class="s2">&quot;lv&quot;</span><span class="p">:</span> <span class="s2">&quot;lv&quot;</span><span class="p">,</span>
  113. <span class="s2">&quot;nl&quot;</span><span class="p">:</span> <span class="s2">&quot;nl&quot;</span><span class="p">,</span>
  114. <span class="s2">&quot;no&quot;</span><span class="p">:</span> <span class="s2">&quot;no&quot;</span><span class="p">,</span>
  115. <span class="s2">&quot;pl&quot;</span><span class="p">:</span> <span class="s2">&quot;pl&quot;</span><span class="p">,</span>
  116. <span class="s2">&quot;pt&quot;</span><span class="p">:</span> <span class="s2">&quot;pt&quot;</span><span class="p">,</span>
  117. <span class="s2">&quot;ro&quot;</span><span class="p">:</span> <span class="s2">&quot;ro&quot;</span><span class="p">,</span>
  118. <span class="s2">&quot;ru&quot;</span><span class="p">:</span> <span class="s2">&quot;ru&quot;</span><span class="p">,</span>
  119. <span class="s2">&quot;sk&quot;</span><span class="p">:</span> <span class="s2">&quot;sk&quot;</span><span class="p">,</span>
  120. <span class="s2">&quot;sl&quot;</span><span class="p">:</span> <span class="s2">&quot;sl&quot;</span><span class="p">,</span>
  121. <span class="s2">&quot;sv&quot;</span><span class="p">:</span> <span class="s2">&quot;sv&quot;</span><span class="p">,</span>
  122. <span class="s2">&quot;th&quot;</span><span class="p">:</span> <span class="s2">&quot;th&quot;</span><span class="p">,</span>
  123. <span class="s2">&quot;tr&quot;</span><span class="p">:</span> <span class="s2">&quot;tr&quot;</span><span class="p">,</span>
  124. <span class="s2">&quot;zh&quot;</span><span class="p">:</span> <span class="s2">&quot;zh_chs&quot;</span><span class="p">,</span>
  125. <span class="s2">&quot;zh_Hans&quot;</span><span class="p">:</span> <span class="s2">&quot;zh_chs&quot;</span><span class="p">,</span>
  126. <span class="s1">&#39;zh-CN&#39;</span><span class="p">:</span> <span class="s2">&quot;zh_chs&quot;</span><span class="p">,</span>
  127. <span class="s2">&quot;zh_Hant&quot;</span><span class="p">:</span> <span class="s2">&quot;zh_cht&quot;</span><span class="p">,</span>
  128. <span class="s2">&quot;zh-HK&quot;</span><span class="p">:</span> <span class="s2">&quot;zh_cht&quot;</span><span class="p">,</span>
  129. <span class="s1">&#39;zh-TW&#39;</span><span class="p">:</span> <span class="s2">&quot;zh_cht&quot;</span><span class="p">,</span>
  130. <span class="p">}</span>
  131. <div class="viewcode-block" id="request">
  132. <a class="viewcode-back" href="../../../dev/engines/online/yahoo.html#searx.engines.yahoo.request">[docs]</a>
  133. <span class="k">def</span><span class="w"> </span><span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
  134. <span class="w"> </span><span class="sd">&quot;&quot;&quot;build request&quot;&quot;&quot;</span>
  135. <span class="n">lang</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s2">&quot;language&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;-&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
  136. <span class="n">lang</span> <span class="o">=</span> <span class="n">yahoo_languages</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">lang</span><span class="p">,</span> <span class="s2">&quot;any&quot;</span><span class="p">)</span>
  137. <span class="n">offset</span> <span class="o">=</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;pageno&#39;</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="mi">7</span> <span class="o">+</span> <span class="mi">1</span>
  138. <span class="n">age</span><span class="p">,</span> <span class="n">btf</span> <span class="o">=</span> <span class="n">time_range_dict</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;time_range&#39;</span><span class="p">],</span> <span class="p">(</span><span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">))</span>
  139. <span class="n">args</span> <span class="o">=</span> <span class="n">urlencode</span><span class="p">(</span>
  140. <span class="p">{</span>
  141. <span class="s1">&#39;p&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
  142. <span class="s1">&#39;ei&#39;</span><span class="p">:</span> <span class="s1">&#39;UTF-8&#39;</span><span class="p">,</span>
  143. <span class="s1">&#39;fl&#39;</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span>
  144. <span class="s1">&#39;vl&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_&#39;</span> <span class="o">+</span> <span class="n">lang</span><span class="p">,</span>
  145. <span class="s1">&#39;btf&#39;</span><span class="p">:</span> <span class="n">btf</span><span class="p">,</span>
  146. <span class="s1">&#39;fr2&#39;</span><span class="p">:</span> <span class="s1">&#39;time&#39;</span><span class="p">,</span>
  147. <span class="s1">&#39;age&#39;</span><span class="p">:</span> <span class="n">age</span><span class="p">,</span>
  148. <span class="s1">&#39;b&#39;</span><span class="p">:</span> <span class="n">offset</span><span class="p">,</span>
  149. <span class="s1">&#39;xargs&#39;</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
  150. <span class="p">}</span>
  151. <span class="p">)</span>
  152. <span class="n">domain</span> <span class="o">=</span> <span class="n">lang2domain</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">lang</span><span class="p">,</span> <span class="s1">&#39;</span><span class="si">%s</span><span class="s1">.search.yahoo.com&#39;</span> <span class="o">%</span> <span class="n">lang</span><span class="p">)</span>
  153. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;url&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;https://</span><span class="si">%s</span><span class="s1">/search?</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">domain</span><span class="p">,</span> <span class="n">args</span><span class="p">)</span>
  154. <span class="k">return</span> <span class="n">params</span></div>
  155. <div class="viewcode-block" id="parse_url">
  156. <a class="viewcode-back" href="../../../dev/engines/online/yahoo.html#searx.engines.yahoo.parse_url">[docs]</a>
  157. <span class="k">def</span><span class="w"> </span><span class="nf">parse_url</span><span class="p">(</span><span class="n">url_string</span><span class="p">):</span>
  158. <span class="w"> </span><span class="sd">&quot;&quot;&quot;remove yahoo-specific tracking-url&quot;&quot;&quot;</span>
  159. <span class="n">endings</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;/RS&#39;</span><span class="p">,</span> <span class="s1">&#39;/RK&#39;</span><span class="p">]</span>
  160. <span class="n">endpositions</span> <span class="o">=</span> <span class="p">[]</span>
  161. <span class="n">start</span> <span class="o">=</span> <span class="n">url_string</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">&#39;http&#39;</span><span class="p">,</span> <span class="n">url_string</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">&#39;/RU=&#39;</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span><span class="p">)</span>
  162. <span class="k">for</span> <span class="n">ending</span> <span class="ow">in</span> <span class="n">endings</span><span class="p">:</span>
  163. <span class="n">endpos</span> <span class="o">=</span> <span class="n">url_string</span><span class="o">.</span><span class="n">rfind</span><span class="p">(</span><span class="n">ending</span><span class="p">)</span>
  164. <span class="k">if</span> <span class="n">endpos</span> <span class="o">&gt;</span> <span class="o">-</span><span class="mi">1</span><span class="p">:</span>
  165. <span class="n">endpositions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">endpos</span><span class="p">)</span>
  166. <span class="k">if</span> <span class="n">start</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">endpositions</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
  167. <span class="k">return</span> <span class="n">url_string</span>
  168. <span class="n">end</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">endpositions</span><span class="p">)</span>
  169. <span class="k">return</span> <span class="n">unquote</span><span class="p">(</span><span class="n">url_string</span><span class="p">[</span><span class="n">start</span><span class="p">:</span><span class="n">end</span><span class="p">])</span></div>
  170. <div class="viewcode-block" id="response">
  171. <a class="viewcode-back" href="../../../dev/engines/online/yahoo.html#searx.engines.yahoo.response">[docs]</a>
  172. <span class="k">def</span><span class="w"> </span><span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
  173. <span class="w"> </span><span class="sd">&quot;&quot;&quot;parse response&quot;&quot;&quot;</span>
  174. <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
  175. <span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
  176. <span class="c1"># parse results</span>
  177. <span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">&#39;//div[contains(@class,&quot;algo-sr&quot;)]&#39;</span><span class="p">):</span>
  178. <span class="n">url</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">&#39;.//h3/a/@href&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
  179. <span class="k">if</span> <span class="n">url</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  180. <span class="k">continue</span>
  181. <span class="n">url</span> <span class="o">=</span> <span class="n">parse_url</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
  182. <span class="n">title</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">&#39;.//h3//a/@aria-label&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">)</span>
  183. <span class="n">title</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">title</span><span class="p">)</span>
  184. <span class="n">content</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">&#39;.//div[contains(@class, &quot;compText&quot;)]&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">)</span>
  185. <span class="n">content</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">content</span><span class="p">,</span> <span class="n">allow_none</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
  186. <span class="c1"># append result</span>
  187. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
  188. <span class="p">{</span>
  189. <span class="s1">&#39;url&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span>
  190. <span class="c1"># title sometimes contains HTML tags / see</span>
  191. <span class="c1"># https://github.com/searxng/searxng/issues/3790</span>
  192. <span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="s2">&quot; &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">html_to_text</span><span class="p">(</span><span class="n">title</span><span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">()),</span>
  193. <span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="s2">&quot; &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">html_to_text</span><span class="p">(</span><span class="n">content</span><span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">()),</span>
  194. <span class="p">}</span>
  195. <span class="p">)</span>
  196. <span class="k">for</span> <span class="n">suggestion</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">&#39;//div[contains(@class, &quot;AlsoTry&quot;)]//table//a&#39;</span><span class="p">):</span>
  197. <span class="c1"># append suggestion</span>
  198. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">&#39;suggestion&#39;</span><span class="p">:</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">suggestion</span><span class="p">)})</span>
  199. <span class="k">return</span> <span class="n">results</span></div>
  200. </pre></div>
  201. <div class="clearer"></div>
  202. </div>
  203. </div>
  204. </div>
  205. <span id="sidebar-top"></span>
  206. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  207. <div class="sphinxsidebarwrapper">
  208. <p class="logo"><a href="../../../index.html">
  209. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  210. </a></p>
  211. <h3><a href="../../../index.html">Table of Contents</a></h3>
  212. <ul>
  213. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  214. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  215. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  216. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  217. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  218. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  219. </ul>
  220. <h3>Project Links</h3>
  221. <ul>
  222. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  223. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  224. <li><a href="https://searx.space">Public instances</a>
  225. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  226. </ul><h3>Navigation</h3>
  227. <ul>
  228. <li><a href="../../../index.html">Overview</a>
  229. <ul>
  230. <li><a href="../../index.html">Module code</a>
  231. <ul>
  232. <li><a href="../engines.html">searx.engines</a>
  233. </ul>
  234. </li></ul>
  235. </li>
  236. </ul>
  237. </li>
  238. </ul>
  239. <search id="searchbox" style="display: none" role="search">
  240. <h3 id="searchlabel">Quick search</h3>
  241. <div class="searchformwrapper">
  242. <form class="search" action="../../../search.html" method="get">
  243. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  244. <input type="submit" value="Go" />
  245. </form>
  246. </div>
  247. </search>
  248. <script>document.getElementById('searchbox').style.display = "block"</script>
  249. </div>
  250. </div>
  251. <div class="clearer"></div>
  252. </div>
  253. <div class="footer" role="contentinfo">
  254. &#169; Copyright SearXNG team.
  255. </div>
  256. </body>
  257. </html>