duckduckgo.html 68 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632
  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.duckduckgo &#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" >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.duckduckgo</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.duckduckgo</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;</span>
  39. <span class="sd">DuckDuckGo WEB</span>
  40. <span class="sd">~~~~~~~~~~~~~~</span>
  41. <span class="sd">&quot;&quot;&quot;</span>
  42. <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>
  43. <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">TYPE_CHECKING</span>
  44. <span class="kn">import</span><span class="w"> </span><span class="nn">re</span>
  45. <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="n">quote_plus</span>
  46. <span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
  47. <span class="kn">import</span><span class="w"> </span><span class="nn">babel</span>
  48. <span class="kn">import</span><span class="w"> </span><span class="nn">lxml.html</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="p">(</span>
  50. <span class="n">locales</span><span class="p">,</span>
  51. <span class="n">redislib</span><span class="p">,</span>
  52. <span class="n">external_bang</span><span class="p">,</span>
  53. <span class="p">)</span>
  54. <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>
  55. <span class="n">eval_xpath</span><span class="p">,</span>
  56. <span class="n">eval_xpath_getindex</span><span class="p">,</span>
  57. <span class="n">extr</span><span class="p">,</span>
  58. <span class="n">extract_text</span><span class="p">,</span>
  59. <span class="p">)</span>
  60. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.network</span><span class="w"> </span><span class="kn">import</span> <span class="n">get</span> <span class="c1"># see https://github.com/searxng/searxng/issues/762</span>
  61. <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">redisdb</span>
  62. <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>
  63. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.exceptions</span><span class="w"> </span><span class="kn">import</span> <span class="n">SearxEngineCaptchaException</span>
  64. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.result_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineResults</span>
  65. <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
  66. <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
  67. <span class="n">logger</span><span class="p">:</span> <span class="n">logging</span><span class="o">.</span><span class="n">Logger</span>
  68. <span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
  69. <span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
  70. <span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="s1">&#39;https://lite.duckduckgo.com/lite/&#39;</span><span class="p">,</span>
  71. <span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s1">&#39;Q12805&#39;</span><span class="p">,</span>
  72. <span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  73. <span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  74. <span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s1">&#39;HTML&#39;</span><span class="p">,</span>
  75. <span class="p">}</span>
  76. <span class="n">send_accept_language_header</span> <span class="o">=</span> <span class="kc">True</span>
  77. <span class="sd">&quot;&quot;&quot;DuckDuckGo-Lite tries to guess user&#39;s preferred language from the HTTP</span>
  78. <span class="sd">``Accept-Language``. Optional the user can select a region filter (but not a</span>
  79. <span class="sd">language).</span>
  80. <span class="sd">&quot;&quot;&quot;</span>
  81. <span class="c1"># engine dependent config</span>
  82. <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>
  83. <span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
  84. <span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
  85. <span class="n">safesearch</span> <span class="o">=</span> <span class="kc">True</span> <span class="c1"># user can&#39;t select but the results are filtered</span>
  86. <span class="n">url</span> <span class="o">=</span> <span class="s2">&quot;https://html.duckduckgo.com/html&quot;</span>
  87. <span class="n">time_range_dict</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;day&#39;</span><span class="p">:</span> <span class="s1">&#39;d&#39;</span><span class="p">,</span> <span class="s1">&#39;week&#39;</span><span class="p">:</span> <span class="s1">&#39;w&#39;</span><span class="p">,</span> <span class="s1">&#39;month&#39;</span><span class="p">:</span> <span class="s1">&#39;m&#39;</span><span class="p">,</span> <span class="s1">&#39;year&#39;</span><span class="p">:</span> <span class="s1">&#39;y&#39;</span><span class="p">}</span>
  88. <span class="n">form_data</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;v&#39;</span><span class="p">:</span> <span class="s1">&#39;l&#39;</span><span class="p">,</span> <span class="s1">&#39;api&#39;</span><span class="p">:</span> <span class="s1">&#39;d.js&#39;</span><span class="p">,</span> <span class="s1">&#39;o&#39;</span><span class="p">:</span> <span class="s1">&#39;json&#39;</span><span class="p">}</span>
  89. <span class="n">__CACHE</span> <span class="o">=</span> <span class="p">[]</span>
  90. <span class="k">def</span><span class="w"> </span><span class="nf">_cache_key</span><span class="p">(</span><span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">region</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
  91. <span class="k">return</span> <span class="s1">&#39;SearXNG_ddg_web_vqd&#39;</span> <span class="o">+</span> <span class="n">redislib</span><span class="o">.</span><span class="n">secret_hash</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">query</span><span class="si">}</span><span class="s2">//</span><span class="si">{</span><span class="n">region</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
  92. <div class="viewcode-block" id="cache_vqd">
  93. <a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.cache_vqd">[docs]</a>
  94. <span class="k">def</span><span class="w"> </span><span class="nf">cache_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">region</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">value</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
  95. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Caches a ``vqd`` value from a query.&quot;&quot;&quot;</span>
  96. <span class="n">c</span> <span class="o">=</span> <span class="n">redisdb</span><span class="o">.</span><span class="n">client</span><span class="p">()</span>
  97. <span class="k">if</span> <span class="n">c</span><span class="p">:</span>
  98. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;VALKEY cache vqd value: </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">value</span><span class="p">,</span> <span class="n">region</span><span class="p">)</span>
  99. <span class="n">c</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">_cache_key</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">region</span><span class="p">),</span> <span class="n">value</span><span class="p">,</span> <span class="n">ex</span><span class="o">=</span><span class="mi">600</span><span class="p">)</span>
  100. <span class="k">else</span><span class="p">:</span>
  101. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;MEM cache vqd value: </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">value</span><span class="p">,</span> <span class="n">region</span><span class="p">)</span>
  102. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">__CACHE</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">100</span><span class="p">:</span> <span class="c1"># cache vqd from last 100 queries</span>
  103. <span class="n">__CACHE</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
  104. <span class="n">__CACHE</span><span class="o">.</span><span class="n">append</span><span class="p">((</span><span class="n">_cache_key</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">region</span><span class="p">),</span> <span class="n">value</span><span class="p">))</span></div>
  105. <div class="viewcode-block" id="get_vqd">
  106. <a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.get_vqd">[docs]</a>
  107. <span class="k">def</span><span class="w"> </span><span class="nf">get_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">region</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">force_request</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">):</span>
  108. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the ``vqd`` that fits to the *query*.</span>
  109. <span class="sd"> :param query: The query term</span>
  110. <span class="sd"> :param region: DDG&#39;s region code</span>
  111. <span class="sd"> :param force_request: force a request to get a vqd value from DDG</span>
  112. <span class="sd"> TL;DR; the ``vqd`` value is needed to pass DDG&#39;s bot protection and is used</span>
  113. <span class="sd"> by all request to DDG:</span>
  114. <span class="sd"> - DuckDuckGo Lite: ``https://lite.duckduckgo.com/lite`` (POST form data)</span>
  115. <span class="sd"> - DuckDuckGo Web: ``https://links.duckduckgo.com/d.js?q=...&amp;vqd=...``</span>
  116. <span class="sd"> - DuckDuckGo Images: ``https://duckduckgo.com/i.js??q=...&amp;vqd=...``</span>
  117. <span class="sd"> - DuckDuckGo Videos: ``https://duckduckgo.com/v.js??q=...&amp;vqd=...``</span>
  118. <span class="sd"> - DuckDuckGo News: ``https://duckduckgo.com/news.js??q=...&amp;vqd=...``</span>
  119. <span class="sd"> DDG&#39;s bot detection is sensitive to the ``vqd`` value. For some search terms</span>
  120. <span class="sd"> (such as extremely long search terms that are often sent by bots), no ``vqd``</span>
  121. <span class="sd"> value can be determined.</span>
  122. <span class="sd"> If SearXNG cannot determine a ``vqd`` value, then no request should go out</span>
  123. <span class="sd"> to DDG.</span>
  124. <span class="sd"> .. attention::</span>
  125. <span class="sd"> A request with a wrong ``vqd`` value leads to DDG temporarily putting</span>
  126. <span class="sd"> SearXNG&#39;s IP on a block list.</span>
  127. <span class="sd"> Requests from IPs in this block list run into timeouts. Not sure, but it</span>
  128. <span class="sd"> seems the block list is a sliding window: to get my IP rid from the bot list</span>
  129. <span class="sd"> I had to cool down my IP for 1h (send no requests from that IP to DDG).</span>
  130. <span class="sd"> &quot;&quot;&quot;</span>
  131. <span class="n">key</span> <span class="o">=</span> <span class="n">_cache_key</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">region</span><span class="p">)</span>
  132. <span class="n">c</span> <span class="o">=</span> <span class="n">redisdb</span><span class="o">.</span><span class="n">client</span><span class="p">()</span>
  133. <span class="k">if</span> <span class="n">c</span><span class="p">:</span>
  134. <span class="n">value</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
  135. <span class="k">if</span> <span class="n">value</span> <span class="ow">or</span> <span class="n">value</span> <span class="o">==</span> <span class="sa">b</span><span class="s1">&#39;&#39;</span><span class="p">:</span>
  136. <span class="n">value</span> <span class="o">=</span> <span class="n">value</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">&#39;utf-8&#39;</span><span class="p">)</span> <span class="c1"># type: ignore</span>
  137. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;re-use CACHED vqd value: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
  138. <span class="k">return</span> <span class="n">value</span>
  139. <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">__CACHE</span><span class="p">:</span>
  140. <span class="k">if</span> <span class="n">k</span> <span class="o">==</span> <span class="n">key</span><span class="p">:</span>
  141. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;MEM re-use CACHED vqd value: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
  142. <span class="k">return</span> <span class="n">value</span>
  143. <span class="k">if</span> <span class="n">force_request</span><span class="p">:</span>
  144. <span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="sa">f</span><span class="s1">&#39;https://duckduckgo.com/?q=</span><span class="si">{</span><span class="n">quote_plus</span><span class="p">(</span><span class="n">query</span><span class="p">)</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">)</span>
  145. <span class="k">if</span> <span class="n">resp</span><span class="o">.</span><span class="n">status_code</span> <span class="o">==</span> <span class="mi">200</span><span class="p">:</span> <span class="c1"># type: ignore</span>
  146. <span class="n">value</span> <span class="o">=</span> <span class="n">extr</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">,</span> <span class="s1">&#39;vqd=&quot;&#39;</span><span class="p">,</span> <span class="s1">&#39;&quot;&#39;</span><span class="p">)</span> <span class="c1"># type: ignore</span>
  147. <span class="k">if</span> <span class="n">value</span><span class="p">:</span>
  148. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;vqd value from DDG request: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
  149. <span class="n">cache_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">region</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
  150. <span class="k">return</span> <span class="n">value</span>
  151. <span class="k">return</span> <span class="kc">None</span></div>
  152. <div class="viewcode-block" id="get_ddg_lang">
  153. <a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.get_ddg_lang">[docs]</a>
  154. <span class="k">def</span><span class="w"> </span><span class="nf">get_ddg_lang</span><span class="p">(</span><span class="n">eng_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">,</span> <span class="n">sxng_locale</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s1">&#39;en_US&#39;</span><span class="p">):</span>
  155. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Get DuckDuckGo&#39;s language identifier from SearXNG&#39;s locale.</span>
  156. <span class="sd"> DuckDuckGo defines its languages by region codes (see</span>
  157. <span class="sd"> :py:obj:`fetch_traits`).</span>
  158. <span class="sd"> To get region and language of a DDG service use:</span>
  159. <span class="sd"> .. code: python</span>
  160. <span class="sd"> eng_region = traits.get_region(params[&#39;searxng_locale&#39;], traits.all_locale)</span>
  161. <span class="sd"> eng_lang = get_ddg_lang(traits, params[&#39;searxng_locale&#39;])</span>
  162. <span class="sd"> It might confuse, but the ``l`` value of the cookie is what SearXNG calls</span>
  163. <span class="sd"> the *region*:</span>
  164. <span class="sd"> .. code:: python</span>
  165. <span class="sd"> # !ddi paris :es-AR --&gt; {&#39;ad&#39;: &#39;es_AR&#39;, &#39;ah&#39;: &#39;ar-es&#39;, &#39;l&#39;: &#39;ar-es&#39;}</span>
  166. <span class="sd"> params[&#39;cookies&#39;][&#39;ad&#39;] = eng_lang</span>
  167. <span class="sd"> params[&#39;cookies&#39;][&#39;ah&#39;] = eng_region</span>
  168. <span class="sd"> params[&#39;cookies&#39;][&#39;l&#39;] = eng_region</span>
  169. <span class="sd"> .. hint::</span>
  170. <span class="sd"> `DDG-lite &lt;https://lite.duckduckgo.com/lite&gt;`__ and the *no Javascript*</span>
  171. <span class="sd"> page https://html.duckduckgo.com/html do not offer a language selection</span>
  172. <span class="sd"> to the user, only a region can be selected by the user (``eng_region``</span>
  173. <span class="sd"> from the example above). DDG-lite and *no Javascript* store the selected</span>
  174. <span class="sd"> region in a cookie::</span>
  175. <span class="sd"> params[&#39;cookies&#39;][&#39;kl&#39;] = eng_region # &#39;ar-es&#39;</span>
  176. <span class="sd"> &quot;&quot;&quot;</span>
  177. <span class="k">return</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;lang_region&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> <span class="c1"># type: ignore</span>
  178. <span class="n">sxng_locale</span><span class="p">,</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">get_language</span><span class="p">(</span><span class="n">sxng_locale</span><span class="p">,</span> <span class="n">default</span><span class="p">)</span>
  179. <span class="p">)</span></div>
  180. <span class="n">ddg_reg_map</span> <span class="o">=</span> <span class="p">{</span>
  181. <span class="s1">&#39;tw-tzh&#39;</span><span class="p">:</span> <span class="s1">&#39;zh_TW&#39;</span><span class="p">,</span>
  182. <span class="s1">&#39;hk-tzh&#39;</span><span class="p">:</span> <span class="s1">&#39;zh_HK&#39;</span><span class="p">,</span>
  183. <span class="s1">&#39;ct-ca&#39;</span><span class="p">:</span> <span class="s1">&#39;skip&#39;</span><span class="p">,</span> <span class="c1"># ct-ca and es-ca both map to ca_ES</span>
  184. <span class="s1">&#39;es-ca&#39;</span><span class="p">:</span> <span class="s1">&#39;ca_ES&#39;</span><span class="p">,</span>
  185. <span class="s1">&#39;id-en&#39;</span><span class="p">:</span> <span class="s1">&#39;id_ID&#39;</span><span class="p">,</span>
  186. <span class="s1">&#39;no-no&#39;</span><span class="p">:</span> <span class="s1">&#39;nb_NO&#39;</span><span class="p">,</span>
  187. <span class="s1">&#39;jp-jp&#39;</span><span class="p">:</span> <span class="s1">&#39;ja_JP&#39;</span><span class="p">,</span>
  188. <span class="s1">&#39;kr-kr&#39;</span><span class="p">:</span> <span class="s1">&#39;ko_KR&#39;</span><span class="p">,</span>
  189. <span class="s1">&#39;xa-ar&#39;</span><span class="p">:</span> <span class="s1">&#39;ar_SA&#39;</span><span class="p">,</span>
  190. <span class="s1">&#39;sl-sl&#39;</span><span class="p">:</span> <span class="s1">&#39;sl_SI&#39;</span><span class="p">,</span>
  191. <span class="s1">&#39;th-en&#39;</span><span class="p">:</span> <span class="s1">&#39;th_TH&#39;</span><span class="p">,</span>
  192. <span class="s1">&#39;vn-en&#39;</span><span class="p">:</span> <span class="s1">&#39;vi_VN&#39;</span><span class="p">,</span>
  193. <span class="p">}</span>
  194. <span class="n">ddg_lang_map</span> <span class="o">=</span> <span class="p">{</span>
  195. <span class="c1"># use ar --&gt; ar_EG (Egypt&#39;s arabic)</span>
  196. <span class="s2">&quot;ar_DZ&quot;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  197. <span class="s2">&quot;ar_JO&quot;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  198. <span class="s2">&quot;ar_SA&quot;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  199. <span class="c1"># use bn --&gt; bn_BD</span>
  200. <span class="s1">&#39;bn_IN&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  201. <span class="c1"># use de --&gt; de_DE</span>
  202. <span class="s1">&#39;de_CH&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  203. <span class="c1"># use en --&gt; en_US,</span>
  204. <span class="s1">&#39;en_AU&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  205. <span class="s1">&#39;en_CA&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  206. <span class="s1">&#39;en_GB&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  207. <span class="c1"># Esperanto</span>
  208. <span class="s1">&#39;eo_XX&#39;</span><span class="p">:</span> <span class="s1">&#39;eo&#39;</span><span class="p">,</span>
  209. <span class="c1"># use es --&gt; es_ES,</span>
  210. <span class="s1">&#39;es_AR&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  211. <span class="s1">&#39;es_CL&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  212. <span class="s1">&#39;es_CO&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  213. <span class="s1">&#39;es_CR&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  214. <span class="s1">&#39;es_EC&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  215. <span class="s1">&#39;es_MX&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  216. <span class="s1">&#39;es_PE&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  217. <span class="s1">&#39;es_UY&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  218. <span class="s1">&#39;es_VE&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  219. <span class="c1"># use fr --&gt; rf_FR</span>
  220. <span class="s1">&#39;fr_CA&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  221. <span class="s1">&#39;fr_CH&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  222. <span class="s1">&#39;fr_BE&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  223. <span class="c1"># use nl --&gt; nl_NL</span>
  224. <span class="s1">&#39;nl_BE&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  225. <span class="c1"># use pt --&gt; pt_PT</span>
  226. <span class="s1">&#39;pt_BR&#39;</span><span class="p">:</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">,</span>
  227. <span class="c1"># skip these languages</span>
  228. <span class="s1">&#39;od_IN&#39;</span><span class="p">:</span> <span class="s1">&#39;skip&#39;</span><span class="p">,</span>
  229. <span class="s1">&#39;io_XX&#39;</span><span class="p">:</span> <span class="s1">&#39;skip&#39;</span><span class="p">,</span>
  230. <span class="s1">&#39;tokipona_XX&#39;</span><span class="p">:</span> <span class="s1">&#39;skip&#39;</span><span class="p">,</span>
  231. <span class="p">}</span>
  232. <span class="k">def</span><span class="w"> </span><span class="nf">quote_ddg_bangs</span><span class="p">(</span><span class="n">query</span><span class="p">):</span>
  233. <span class="c1"># quote ddg bangs</span>
  234. <span class="n">query_parts</span> <span class="o">=</span> <span class="p">[]</span>
  235. <span class="c1"># for val in re.split(r&#39;(\s+)&#39;, query):</span>
  236. <span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;(\s+)&#39;</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span>
  237. <span class="k">if</span> <span class="ow">not</span> <span class="n">val</span><span class="o">.</span><span class="n">strip</span><span class="p">():</span>
  238. <span class="k">continue</span>
  239. <span class="k">if</span> <span class="n">val</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;!&#39;</span><span class="p">)</span> <span class="ow">and</span> <span class="n">external_bang</span><span class="o">.</span><span class="n">get_node</span><span class="p">(</span><span class="n">external_bang</span><span class="o">.</span><span class="n">EXTERNAL_BANGS</span><span class="p">,</span> <span class="n">val</span><span class="p">[</span><span class="mi">1</span><span class="p">:]):</span>
  240. <span class="n">val</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;&#39;</span><span class="si">{</span><span class="n">val</span><span class="si">}</span><span class="s2">&#39;&quot;</span>
  241. <span class="n">query_parts</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">val</span><span class="p">)</span>
  242. <span class="k">return</span> <span class="s1">&#39; &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">query_parts</span><span class="p">)</span>
  243. <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>
  244. <span class="n">query</span> <span class="o">=</span> <span class="n">quote_ddg_bangs</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
  245. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">query</span><span class="p">)</span> <span class="o">&gt;=</span> <span class="mi">500</span><span class="p">:</span>
  246. <span class="c1"># DDG does not accept queries with more than 499 chars</span>
  247. <span class="n">params</span><span class="p">[</span><span class="s2">&quot;url&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
  248. <span class="k">return</span>
  249. <span class="c1"># Advanced search syntax ends in CAPTCHA</span>
  250. <span class="c1"># https://duckduckgo.com/duckduckgo-help-pages/results/syntax/</span>
  251. <span class="n">query</span> <span class="o">=</span> <span class="s2">&quot; &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
  252. <span class="p">[</span>
  253. <span class="n">x</span><span class="o">.</span><span class="n">removeprefix</span><span class="p">(</span><span class="s2">&quot;site:&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">removeprefix</span><span class="p">(</span><span class="s2">&quot;intitle:&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">removeprefix</span><span class="p">(</span><span class="s2">&quot;inurl:&quot;</span><span class="p">)</span><span class="o">.</span><span class="n">removeprefix</span><span class="p">(</span><span class="s2">&quot;filetype:&quot;</span><span class="p">)</span>
  254. <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">query</span><span class="o">.</span><span class="n">split</span><span class="p">()</span>
  255. <span class="p">]</span>
  256. <span class="p">)</span>
  257. <span class="n">eng_region</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">get_region</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;searxng_locale&#39;</span><span class="p">],</span> <span class="n">traits</span><span class="o">.</span><span class="n">all_locale</span><span class="p">)</span> <span class="c1"># type: ignore</span>
  258. <span class="k">if</span> <span class="n">eng_region</span> <span class="o">==</span> <span class="s2">&quot;wt-wt&quot;</span><span class="p">:</span>
  259. <span class="c1"># https://html.duckduckgo.com/html sets an empty value for &quot;all&quot;.</span>
  260. <span class="n">eng_region</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
  261. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;kl&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_region</span>
  262. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">][</span><span class="s1">&#39;kl&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_region</span>
  263. <span class="c1"># eng_lang = get_ddg_lang(traits, params[&#39;searxng_locale&#39;])</span>
  264. <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="n">url</span>
  265. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;method&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;POST&#39;</span>
  266. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;q&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">query</span>
  267. <span class="c1"># The API is not documented, so we do some reverse engineering and emulate</span>
  268. <span class="c1"># what https://html.duckduckgo.com/html does when you press &quot;next Page&quot; link</span>
  269. <span class="c1"># again and again ..</span>
  270. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">][</span><span class="s1">&#39;Content-Type&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;application/x-www-form-urlencoded&#39;</span>
  271. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">][</span><span class="s1">&#39;Sec-Fetch-Dest&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;document&quot;</span>
  272. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">][</span><span class="s1">&#39;Sec-Fetch-Mode&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;navigate&quot;</span> <span class="c1"># at least this one is used by ddg&#39;s bot detection</span>
  273. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">][</span><span class="s1">&#39;Sec-Fetch-Site&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;same-origin&quot;</span>
  274. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">][</span><span class="s1">&#39;Sec-Fetch-User&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;?1&quot;</span>
  275. <span class="c1"># Form of the initial search page does have empty values in the form</span>
  276. <span class="k">if</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>
  277. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;b&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
  278. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;df&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  279. <span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;time_range&#39;</span><span class="p">]</span> <span class="ow">in</span> <span class="n">time_range_dict</span><span class="p">:</span>
  280. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;df&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">time_range_dict</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>
  281. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">][</span><span class="s1">&#39;df&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">time_range_dict</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>
  282. <span class="k">if</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">2</span><span class="p">:</span>
  283. <span class="c1"># second page does have an offset of 20</span>
  284. <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">20</span>
  285. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;s&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span>
  286. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;dc&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span> <span class="o">+</span> <span class="mi">1</span>
  287. <span class="k">elif</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;pageno&#39;</span><span class="p">]</span> <span class="o">&gt;</span> <span class="mi">2</span><span class="p">:</span>
  288. <span class="c1"># third and following pages do have an offset of 20 + n*50</span>
  289. <span class="n">offset</span> <span class="o">=</span> <span class="mi">20</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">2</span><span class="p">)</span> <span class="o">*</span> <span class="mi">50</span>
  290. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;s&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span>
  291. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;dc&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span> <span class="o">+</span> <span class="mi">1</span>
  292. <span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;pageno&#39;</span><span class="p">]</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
  293. <span class="c1"># initial page does not have these additional data in the input form</span>
  294. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;o&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;o&#39;</span><span class="p">,</span> <span class="s1">&#39;json&#39;</span><span class="p">)</span>
  295. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;api&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;api&#39;</span><span class="p">,</span> <span class="s1">&#39;d.js&#39;</span><span class="p">)</span>
  296. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;nextParams&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;nextParams&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">)</span>
  297. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;v&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;v&#39;</span><span class="p">,</span> <span class="s1">&#39;l&#39;</span><span class="p">)</span>
  298. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">][</span><span class="s1">&#39;Referer&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">url</span>
  299. <span class="n">vqd</span> <span class="o">=</span> <span class="n">get_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">eng_region</span><span class="p">,</span> <span class="n">force_request</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
  300. <span class="c1"># Certain conditions must be met in order to call up one of the</span>
  301. <span class="c1"># following pages ...</span>
  302. <span class="k">if</span> <span class="n">vqd</span><span class="p">:</span>
  303. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;vqd&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">vqd</span> <span class="c1"># follow up pages / requests needs a vqd argument</span>
  304. <span class="k">else</span><span class="p">:</span>
  305. <span class="c1"># Don&#39;t try to call follow up pages without a vqd value. DDG</span>
  306. <span class="c1"># recognizes this as a request from a bot. This lowers the</span>
  307. <span class="c1"># reputation of the SearXNG IP and DDG starts to activate CAPTCHAs.</span>
  308. <span class="n">params</span><span class="p">[</span><span class="s2">&quot;url&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
  309. <span class="k">return</span>
  310. <span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;searxng_locale&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">&quot;zh&quot;</span><span class="p">):</span>
  311. <span class="c1"># Some locales (at least China) do not have a &quot;next page&quot; button and ddg</span>
  312. <span class="c1"># will return a HTTP/2 403 Forbidden for a request of such a page.</span>
  313. <span class="n">params</span><span class="p">[</span><span class="s2">&quot;url&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
  314. <span class="k">return</span>
  315. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;param data: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">])</span>
  316. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;param cookies: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">])</span>
  317. <div class="viewcode-block" id="is_ddg_captcha">
  318. <a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.is_ddg_captcha">[docs]</a>
  319. <span class="k">def</span><span class="w"> </span><span class="nf">is_ddg_captcha</span><span class="p">(</span><span class="n">dom</span><span class="p">):</span>
  320. <span class="w"> </span><span class="sd">&quot;&quot;&quot;In case of CAPTCHA ddg response its own *not a Robot* dialog and is not</span>
  321. <span class="sd"> redirected to a CAPTCHA page.&quot;&quot;&quot;</span>
  322. <span class="k">return</span> <span class="nb">bool</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s2">&quot;//form[@id=&#39;challenge-form&#39;]&quot;</span><span class="p">))</span></div>
  323. <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> <span class="o">-&gt;</span> <span class="n">EngineResults</span><span class="p">:</span>
  324. <span class="n">results</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
  325. <span class="k">if</span> <span class="n">resp</span><span class="o">.</span><span class="n">status_code</span> <span class="o">==</span> <span class="mi">303</span><span class="p">:</span>
  326. <span class="k">return</span> <span class="n">results</span>
  327. <span class="n">doc</span> <span class="o">=</span> <span class="n">lxml</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>
  328. <span class="k">if</span> <span class="n">is_ddg_captcha</span><span class="p">(</span><span class="n">doc</span><span class="p">):</span>
  329. <span class="c1"># set suspend time to zero is OK --&gt; ddg does not block the IP</span>
  330. <span class="k">raise</span> <span class="n">SearxEngineCaptchaException</span><span class="p">(</span><span class="n">suspended_time</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">message</span><span class="o">=</span><span class="sa">f</span><span class="s2">&quot;CAPTCHA (</span><span class="si">{</span><span class="n">resp</span><span class="o">.</span><span class="n">search_params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;kl&#39;</span><span class="p">)</span><span class="si">}</span><span class="s2">)&quot;</span><span class="p">)</span>
  331. <span class="n">form</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="s1">&#39;//input[@name=&quot;vqd&quot;]/..&#39;</span><span class="p">)</span>
  332. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">form</span><span class="p">):</span>
  333. <span class="c1"># some locales (at least China) does not have a &quot;next page&quot; button</span>
  334. <span class="n">form</span> <span class="o">=</span> <span class="n">form</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
  335. <span class="n">form_vqd</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">form</span><span class="p">,</span> <span class="s1">&#39;//input[@name=&quot;vqd&quot;]/@value&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
  336. <span class="n">cache_vqd</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">search_params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;q&#39;</span><span class="p">],</span> <span class="n">resp</span><span class="o">.</span><span class="n">search_params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">][</span><span class="s1">&#39;kl&#39;</span><span class="p">],</span> <span class="n">form_vqd</span><span class="p">)</span>
  337. <span class="c1"># just select &quot;web-result&quot; and ignore results of class &quot;result--ad result--ad--small&quot;</span>
  338. <span class="k">for</span> <span class="n">div_result</span> <span class="ow">in</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="s1">&#39;//div[@id=&quot;links&quot;]/div[contains(@class, &quot;web-result&quot;)]&#39;</span><span class="p">):</span>
  339. <span class="n">item</span> <span class="o">=</span> <span class="p">{}</span>
  340. <span class="n">title</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">div_result</span><span class="p">,</span> <span class="s1">&#39;.//h2/a&#39;</span><span class="p">)</span>
  341. <span class="k">if</span> <span class="ow">not</span> <span class="n">title</span><span class="p">:</span>
  342. <span class="c1"># this is the &quot;No results.&quot; item in the result list</span>
  343. <span class="k">continue</span>
  344. <span class="n">item</span><span class="p">[</span><span class="s2">&quot;title&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">title</span><span class="p">)</span>
  345. <span class="n">item</span><span class="p">[</span><span class="s2">&quot;url&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">div_result</span><span class="p">,</span> <span class="s1">&#39;.//h2/a/@href&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
  346. <span class="n">item</span><span class="p">[</span><span class="s2">&quot;content&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">div_result</span><span class="p">,</span> <span class="s1">&#39;.//a[contains(@class, &quot;result__snippet&quot;)]&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">])</span>
  347. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">item</span><span class="p">)</span>
  348. <span class="n">zero_click_info_xpath</span> <span class="o">=</span> <span class="s1">&#39;//div[@id=&quot;zero_click_abstract&quot;]&#39;</span>
  349. <span class="n">zero_click</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="n">zero_click_info_xpath</span><span class="p">))</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="c1"># type: ignore</span>
  350. <span class="k">if</span> <span class="n">zero_click</span> <span class="ow">and</span> <span class="p">(</span>
  351. <span class="s2">&quot;Your IP address is&quot;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">zero_click</span>
  352. <span class="ow">and</span> <span class="s2">&quot;Your user agent:&quot;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">zero_click</span>
  353. <span class="ow">and</span> <span class="s2">&quot;URL Decoded:&quot;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">zero_click</span>
  354. <span class="p">):</span>
  355. <span class="n">results</span><span class="o">.</span><span class="n">add</span><span class="p">(</span>
  356. <span class="n">results</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">Answer</span><span class="p">(</span>
  357. <span class="n">answer</span><span class="o">=</span><span class="n">zero_click</span><span class="p">,</span>
  358. <span class="n">url</span><span class="o">=</span><span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="s1">&#39;//div[@id=&quot;zero_click_abstract&quot;]/a/@href&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span>
  359. <span class="p">)</span>
  360. <span class="p">)</span>
  361. <span class="k">return</span> <span class="n">results</span>
  362. <div class="viewcode-block" id="fetch_traits">
  363. <a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.fetch_traits">[docs]</a>
  364. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
  365. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Fetch languages &amp; regions from DuckDuckGo.</span>
  366. <span class="sd"> SearXNG&#39;s ``all`` locale maps DuckDuckGo&#39;s &quot;Alle regions&quot; (``wt-wt``).</span>
  367. <span class="sd"> DuckDuckGo&#39;s language &quot;Browsers preferred language&quot; (``wt_WT``) makes no</span>
  368. <span class="sd"> sense in a SearXNG request since SearXNG&#39;s ``all`` will not add a</span>
  369. <span class="sd"> ``Accept-Language`` HTTP header. The value in ``engine_traits.all_locale``</span>
  370. <span class="sd"> is ``wt-wt`` (the region).</span>
  371. <span class="sd"> Beside regions DuckDuckGo also defines its languages by region codes. By</span>
  372. <span class="sd"> example these are the english languages in DuckDuckGo:</span>
  373. <span class="sd"> - en_US</span>
  374. <span class="sd"> - en_AU</span>
  375. <span class="sd"> - en_CA</span>
  376. <span class="sd"> - en_GB</span>
  377. <span class="sd"> The function :py:obj:`get_ddg_lang` evaluates DuckDuckGo&#39;s language from</span>
  378. <span class="sd"> SearXNG&#39;s locale.</span>
  379. <span class="sd"> &quot;&quot;&quot;</span>
  380. <span class="c1"># pylint: disable=too-many-branches, too-many-statements, disable=import-outside-toplevel</span>
  381. <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="n">js_variable_to_python</span>
  382. <span class="c1"># fetch regions</span>
  383. <span class="n">engine_traits</span><span class="o">.</span><span class="n">all_locale</span> <span class="o">=</span> <span class="s1">&#39;wt-wt&#39;</span>
  384. <span class="c1"># updated from u661.js to u.7669f071a13a7daa57cb / should be updated automatically?</span>
  385. <span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s1">&#39;https://duckduckgo.com/dist/util/u.7669f071a13a7daa57cb.js&#39;</span><span class="p">)</span>
  386. <span class="k">if</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">ok</span><span class="p">:</span> <span class="c1"># type: ignore</span>
  387. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: response from DuckDuckGo is not OK.&quot;</span><span class="p">)</span>
  388. <span class="n">js_code</span> <span class="o">=</span> <span class="n">extr</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">,</span> <span class="s1">&#39;regions:&#39;</span><span class="p">,</span> <span class="s1">&#39;,snippetLengths&#39;</span><span class="p">)</span> <span class="c1"># type: ignore</span>
  389. <span class="n">regions</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">js_code</span><span class="p">)</span>
  390. <span class="k">for</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">regions</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
  391. <span class="k">if</span> <span class="n">eng_tag</span> <span class="o">==</span> <span class="s1">&#39;wt-wt&#39;</span><span class="p">:</span>
  392. <span class="n">engine_traits</span><span class="o">.</span><span class="n">all_locale</span> <span class="o">=</span> <span class="s1">&#39;wt-wt&#39;</span>
  393. <span class="k">continue</span>
  394. <span class="n">region</span> <span class="o">=</span> <span class="n">ddg_reg_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">eng_tag</span><span class="p">)</span>
  395. <span class="k">if</span> <span class="n">region</span> <span class="o">==</span> <span class="s1">&#39;skip&#39;</span><span class="p">:</span>
  396. <span class="k">continue</span>
  397. <span class="k">if</span> <span class="ow">not</span> <span class="n">region</span><span class="p">:</span>
  398. <span class="n">eng_territory</span><span class="p">,</span> <span class="n">eng_lang</span> <span class="o">=</span> <span class="n">eng_tag</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;-&#39;</span><span class="p">)</span>
  399. <span class="n">region</span> <span class="o">=</span> <span class="n">eng_lang</span> <span class="o">+</span> <span class="s1">&#39;_&#39;</span> <span class="o">+</span> <span class="n">eng_territory</span><span class="o">.</span><span class="n">upper</span><span class="p">()</span>
  400. <span class="k">try</span><span class="p">:</span>
  401. <span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">locales</span><span class="o">.</span><span class="n">region_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">region</span><span class="p">))</span>
  402. <span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span>
  403. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: </span><span class="si">%s</span><span class="s2"> (</span><span class="si">%s</span><span class="s2">) -&gt; </span><span class="si">%s</span><span class="s2"> is unknown by babel&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="n">region</span><span class="p">))</span>
  404. <span class="k">continue</span>
  405. <span class="n">conflict</span> <span class="o">=</span> <span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_tag</span><span class="p">)</span>
  406. <span class="k">if</span> <span class="n">conflict</span><span class="p">:</span>
  407. <span class="k">if</span> <span class="n">conflict</span> <span class="o">!=</span> <span class="n">eng_tag</span><span class="p">:</span>
  408. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;CONFLICT: babel </span><span class="si">%s</span><span class="s2"> --&gt; </span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">sxng_tag</span><span class="p">,</span> <span class="n">conflict</span><span class="p">,</span> <span class="n">eng_tag</span><span class="p">))</span>
  409. <span class="k">continue</span>
  410. <span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="p">[</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_tag</span>
  411. <span class="c1"># fetch languages</span>
  412. <span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;lang_region&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
  413. <span class="n">js_code</span> <span class="o">=</span> <span class="n">extr</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">,</span> <span class="s1">&#39;languages:&#39;</span><span class="p">,</span> <span class="s1">&#39;,regions&#39;</span><span class="p">)</span> <span class="c1"># type: ignore</span>
  414. <span class="n">languages</span> <span class="o">=</span> <span class="n">js_variable_to_python</span><span class="p">(</span><span class="n">js_code</span><span class="p">)</span>
  415. <span class="k">for</span> <span class="n">eng_lang</span><span class="p">,</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">languages</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
  416. <span class="k">if</span> <span class="n">eng_lang</span> <span class="o">==</span> <span class="s1">&#39;wt_WT&#39;</span><span class="p">:</span>
  417. <span class="k">continue</span>
  418. <span class="n">babel_tag</span> <span class="o">=</span> <span class="n">ddg_lang_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">eng_lang</span><span class="p">,</span> <span class="n">eng_lang</span><span class="p">)</span>
  419. <span class="k">if</span> <span class="n">babel_tag</span> <span class="o">==</span> <span class="s1">&#39;skip&#39;</span><span class="p">:</span>
  420. <span class="k">continue</span>
  421. <span class="k">try</span><span class="p">:</span>
  422. <span class="k">if</span> <span class="n">babel_tag</span> <span class="o">==</span> <span class="s1">&#39;lang_region&#39;</span><span class="p">:</span>
  423. <span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">locales</span><span class="o">.</span><span class="n">region_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">eng_lang</span><span class="p">))</span>
  424. <span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;lang_region&#39;</span><span class="p">][</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_lang</span>
  425. <span class="k">continue</span>
  426. <span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">locales</span><span class="o">.</span><span class="n">language_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">babel_tag</span><span class="p">))</span>
  427. <span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span>
  428. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: language </span><span class="si">%s</span><span class="s2"> (</span><span class="si">%s</span><span class="s2">) is unknown by babel&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">eng_lang</span><span class="p">))</span>
  429. <span class="k">continue</span>
  430. <span class="n">conflict</span> <span class="o">=</span> <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_tag</span><span class="p">)</span>
  431. <span class="k">if</span> <span class="n">conflict</span><span class="p">:</span>
  432. <span class="k">if</span> <span class="n">conflict</span> <span class="o">!=</span> <span class="n">eng_lang</span><span class="p">:</span>
  433. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;CONFLICT: babel </span><span class="si">%s</span><span class="s2"> --&gt; </span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">sxng_tag</span><span class="p">,</span> <span class="n">conflict</span><span class="p">,</span> <span class="n">eng_lang</span><span class="p">))</span>
  434. <span class="k">continue</span>
  435. <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_lang</span></div>
  436. </pre></div>
  437. <div class="clearer"></div>
  438. </div>
  439. </div>
  440. </div>
  441. <span id="sidebar-top"></span>
  442. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  443. <div class="sphinxsidebarwrapper">
  444. <p class="logo"><a href="../../../index.html">
  445. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  446. </a></p>
  447. <h3><a href="../../../index.html">Table of Contents</a></h3>
  448. <ul>
  449. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  450. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  451. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  452. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  453. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  454. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  455. </ul>
  456. <h3>Project Links</h3>
  457. <ul>
  458. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  459. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  460. <li><a href="https://searx.space">Public instances</a>
  461. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  462. </ul><h3>Navigation</h3>
  463. <ul>
  464. <li><a href="../../../index.html">Overview</a>
  465. <ul>
  466. <li><a href="../../index.html">Module code</a>
  467. <ul>
  468. <li><a href="../engines.html">searx.engines</a>
  469. </ul>
  470. </li></ul>
  471. </li>
  472. </ul>
  473. </li>
  474. </ul>
  475. <search id="searchbox" style="display: none" role="search">
  476. <h3 id="searchlabel">Quick search</h3>
  477. <div class="searchformwrapper">
  478. <form class="search" action="../../../search.html" method="get">
  479. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  480. <input type="submit" value="Go" />
  481. </form>
  482. </div>
  483. </search>
  484. <script>document.getElementById('searchbox').style.display = "block"</script>
  485. </div>
  486. </div>
  487. <div class="clearer"></div>
  488. </div>
  489. <div class="footer" role="contentinfo">
  490. &#169; Copyright SearXNG team.
  491. </div>
  492. </body>
  493. </html>