google.html 67 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657
  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.google &#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.google</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.google</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;This is the implementation of the Google WEB engine. Some of this</span>
  39. <span class="sd">implementations (manly the :py:obj:`get_google_info`) are shared by other</span>
  40. <span class="sd">engines:</span>
  41. <span class="sd">- :ref:`google images engine`</span>
  42. <span class="sd">- :ref:`google news engine`</span>
  43. <span class="sd">- :ref:`google videos engine`</span>
  44. <span class="sd">- :ref:`google scholar engine`</span>
  45. <span class="sd">- :ref:`google autocomplete`</span>
  46. <span class="sd">&quot;&quot;&quot;</span>
  47. <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>
  48. <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>
  49. <span class="kn">import</span><span class="w"> </span><span class="nn">re</span>
  50. <span class="kn">import</span><span class="w"> </span><span class="nn">random</span>
  51. <span class="kn">import</span><span class="w"> </span><span class="nn">string</span>
  52. <span class="kn">import</span><span class="w"> </span><span class="nn">time</span>
  53. <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">urlencode</span>
  54. <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>
  55. <span class="kn">import</span><span class="w"> </span><span class="nn">babel</span>
  56. <span class="kn">import</span><span class="w"> </span><span class="nn">babel.core</span>
  57. <span class="kn">import</span><span class="w"> </span><span class="nn">babel.languages</span>
  58. <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">extract_text</span><span class="p">,</span> <span class="n">eval_xpath</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">,</span> <span class="n">eval_xpath_getindex</span>
  59. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.locales</span><span class="w"> </span><span class="kn">import</span> <span class="n">language_tag</span><span class="p">,</span> <span class="n">region_tag</span><span class="p">,</span> <span class="n">get_official_locales</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.exceptions</span><span class="w"> </span><span class="kn">import</span> <span class="n">SearxEngineCaptchaException</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.result_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineResults</span>
  64. <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
  65. <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
  66. <span class="n">logger</span><span class="p">:</span> <span class="n">logging</span><span class="o">.</span><span class="n">Logger</span>
  67. <span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
  68. <span class="c1"># about</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://www.google.com&#39;</span><span class="p">,</span>
  71. <span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s1">&#39;Q9366&#39;</span><span class="p">,</span>
  72. <span class="s2">&quot;official_api_documentation&quot;</span><span class="p">:</span> <span class="s1">&#39;https://developers.google.com/custom-search/&#39;</span><span class="p">,</span>
  73. <span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  74. <span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  75. <span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s1">&#39;HTML&#39;</span><span class="p">,</span>
  76. <span class="p">}</span>
  77. <span class="c1"># engine dependent config</span>
  78. <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>
  79. <span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
  80. <span class="n">max_page</span> <span class="o">=</span> <span class="mi">50</span>
  81. <span class="sd">&quot;&quot;&quot;`Google max 50 pages`_</span>
  82. <span class="sd">.. _Google max 50 pages: https://github.com/searxng/searxng/issues/2982</span>
  83. <span class="sd">&quot;&quot;&quot;</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>
  86. <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>
  87. <span class="c1"># Filter results. 0: None, 1: Moderate, 2: Strict</span>
  88. <span class="n">filter_mapping</span> <span class="o">=</span> <span class="p">{</span><span class="mi">0</span><span class="p">:</span> <span class="s1">&#39;off&#39;</span><span class="p">,</span> <span class="mi">1</span><span class="p">:</span> <span class="s1">&#39;medium&#39;</span><span class="p">,</span> <span class="mi">2</span><span class="p">:</span> <span class="s1">&#39;high&#39;</span><span class="p">}</span>
  89. <span class="c1"># specific xpath variables</span>
  90. <span class="c1"># ------------------------</span>
  91. <span class="c1"># Suggestions are links placed in a *card-section*, we extract only the text</span>
  92. <span class="c1"># from the links not the links itself.</span>
  93. <span class="n">suggestion_xpath</span> <span class="o">=</span> <span class="s1">&#39;//div[contains(@class, &quot;EIaa9b&quot;)]//a&#39;</span>
  94. <span class="n">_arcid_range</span> <span class="o">=</span> <span class="n">string</span><span class="o">.</span><span class="n">ascii_letters</span> <span class="o">+</span> <span class="n">string</span><span class="o">.</span><span class="n">digits</span> <span class="o">+</span> <span class="s2">&quot;_-&quot;</span>
  95. <span class="n">_arcid_random</span><span class="p">:</span> <span class="nb">tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">int</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="kc">None</span>
  96. <div class="viewcode-block" id="ui_async">
  97. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google.ui_async">[docs]</a>
  98. <span class="k">def</span><span class="w"> </span><span class="nf">ui_async</span><span class="p">(</span><span class="n">start</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  99. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Format of the response from UI&#39;s async request.</span>
  100. <span class="sd"> - ``arc_id:&lt;...&gt;,use_ac:true,_fmt:prog``</span>
  101. <span class="sd"> The arc_id is random generated every hour.</span>
  102. <span class="sd"> &quot;&quot;&quot;</span>
  103. <span class="k">global</span> <span class="n">_arcid_random</span> <span class="c1"># pylint: disable=global-statement</span>
  104. <span class="n">use_ac</span> <span class="o">=</span> <span class="s2">&quot;use_ac:true&quot;</span>
  105. <span class="c1"># _fmt:html returns a HTTP 500 when user search for celebrities like</span>
  106. <span class="c1"># &#39;!google natasha allegri&#39; or &#39;!google chris evans&#39;</span>
  107. <span class="n">_fmt</span> <span class="o">=</span> <span class="s2">&quot;_fmt:prog&quot;</span>
  108. <span class="c1"># create a new random arc_id every hour</span>
  109. <span class="k">if</span> <span class="ow">not</span> <span class="n">_arcid_random</span> <span class="ow">or</span> <span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">())</span> <span class="o">-</span> <span class="n">_arcid_random</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> <span class="o">&gt;</span> <span class="mi">3600</span><span class="p">:</span>
  110. <span class="n">_arcid_random</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">choices</span><span class="p">(</span><span class="n">_arcid_range</span><span class="p">,</span> <span class="n">k</span><span class="o">=</span><span class="mi">23</span><span class="p">)),</span> <span class="nb">int</span><span class="p">(</span><span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()))</span>
  111. <span class="n">arc_id</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;arc_id:srp_</span><span class="si">{</span><span class="n">_arcid_random</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s2">_1</span><span class="si">{</span><span class="n">start</span><span class="si">:</span><span class="s2">02</span><span class="si">}</span><span class="s2">&quot;</span>
  112. <span class="k">return</span> <span class="s2">&quot;,&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">arc_id</span><span class="p">,</span> <span class="n">use_ac</span><span class="p">,</span> <span class="n">_fmt</span><span class="p">])</span></div>
  113. <div class="viewcode-block" id="get_google_info">
  114. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google.get_google_info">[docs]</a>
  115. <span class="k">def</span><span class="w"> </span><span class="nf">get_google_info</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">eng_traits</span><span class="p">):</span>
  116. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Composing various (language) properties for the google engines (:ref:`google</span>
  117. <span class="sd"> API`).</span>
  118. <span class="sd"> This function is called by the various google engines (:ref:`google web</span>
  119. <span class="sd"> engine`, :ref:`google images engine`, :ref:`google news engine` and</span>
  120. <span class="sd"> :ref:`google videos engine`).</span>
  121. <span class="sd"> :param dict param: Request parameters of the engine. At least</span>
  122. <span class="sd"> a ``searxng_locale`` key should be in the dictionary.</span>
  123. <span class="sd"> :param eng_traits: Engine&#39;s traits fetched from google preferences</span>
  124. <span class="sd"> (:py:obj:`searx.enginelib.traits.EngineTraits`)</span>
  125. <span class="sd"> :rtype: dict</span>
  126. <span class="sd"> :returns:</span>
  127. <span class="sd"> Py-Dictionary with the key/value pairs:</span>
  128. <span class="sd"> language:</span>
  129. <span class="sd"> The language code that is used by google (e.g. ``lang_en`` or</span>
  130. <span class="sd"> ``lang_zh-TW``)</span>
  131. <span class="sd"> country:</span>
  132. <span class="sd"> The country code that is used by google (e.g. ``US`` or ``TW``)</span>
  133. <span class="sd"> locale:</span>
  134. <span class="sd"> A instance of :py:obj:`babel.core.Locale` build from the</span>
  135. <span class="sd"> ``searxng_locale`` value.</span>
  136. <span class="sd"> subdomain:</span>
  137. <span class="sd"> Google subdomain :py:obj:`google_domains` that fits to the country</span>
  138. <span class="sd"> code.</span>
  139. <span class="sd"> params:</span>
  140. <span class="sd"> Py-Dictionary with additional request arguments (can be passed to</span>
  141. <span class="sd"> :py:func:`urllib.parse.urlencode`).</span>
  142. <span class="sd"> - ``hl`` parameter: specifies the interface language of user interface.</span>
  143. <span class="sd"> - ``lr`` parameter: restricts search results to documents written in</span>
  144. <span class="sd"> a particular language.</span>
  145. <span class="sd"> - ``cr`` parameter: restricts search results to documents</span>
  146. <span class="sd"> originating in a particular country.</span>
  147. <span class="sd"> - ``ie`` parameter: sets the character encoding scheme that should</span>
  148. <span class="sd"> be used to interpret the query string (&#39;utf8&#39;).</span>
  149. <span class="sd"> - ``oe`` parameter: sets the character encoding scheme that should</span>
  150. <span class="sd"> be used to decode the XML result (&#39;utf8&#39;).</span>
  151. <span class="sd"> headers:</span>
  152. <span class="sd"> Py-Dictionary with additional HTTP headers (can be passed to</span>
  153. <span class="sd"> request&#39;s headers)</span>
  154. <span class="sd"> - ``Accept: &#39;*/*``</span>
  155. <span class="sd"> &quot;&quot;&quot;</span>
  156. <span class="n">ret_val</span> <span class="o">=</span> <span class="p">{</span>
  157. <span class="s1">&#39;language&#39;</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
  158. <span class="s1">&#39;country&#39;</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
  159. <span class="s1">&#39;subdomain&#39;</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
  160. <span class="s1">&#39;params&#39;</span><span class="p">:</span> <span class="p">{},</span>
  161. <span class="s1">&#39;headers&#39;</span><span class="p">:</span> <span class="p">{},</span>
  162. <span class="s1">&#39;cookies&#39;</span><span class="p">:</span> <span class="p">{},</span>
  163. <span class="s1">&#39;locale&#39;</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
  164. <span class="p">}</span>
  165. <span class="n">sxng_locale</span> <span class="o">=</span> <span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;searxng_locale&#39;</span><span class="p">,</span> <span class="s1">&#39;all&#39;</span><span class="p">)</span>
  166. <span class="k">try</span><span class="p">:</span>
  167. <span class="n">locale</span> <span class="o">=</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">sxng_locale</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s1">&#39;-&#39;</span><span class="p">)</span>
  168. <span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">core</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span>
  169. <span class="n">locale</span> <span class="o">=</span> <span class="kc">None</span>
  170. <span class="n">eng_lang</span> <span class="o">=</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="s1">&#39;lang_en&#39;</span><span class="p">)</span>
  171. <span class="n">lang_code</span> <span class="o">=</span> <span class="n">eng_lang</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;_&#39;</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="c1"># lang_zh-TW --&gt; zh-TW / lang_en --&gt; en</span>
  172. <span class="n">country</span> <span class="o">=</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">get_region</span><span class="p">(</span><span class="n">sxng_locale</span><span class="p">,</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">all_locale</span><span class="p">)</span>
  173. <span class="c1"># Test zh_hans &amp; zh_hant --&gt; in the topmost links in the result list of list</span>
  174. <span class="c1"># TW and HK you should a find wiktionary.org zh_hant link. In the result</span>
  175. <span class="c1"># list of zh-CN should not be no hant link instead you should find</span>
  176. <span class="c1"># zh.m.wikipedia.org/zh somewhere in the top.</span>
  177. <span class="c1"># &#39;!go 日 :zh-TW&#39; --&gt; https://zh.m.wiktionary.org/zh-hant/%E6%97%A5</span>
  178. <span class="c1"># &#39;!go 日 :zh-CN&#39; --&gt; https://zh.m.wikipedia.org/zh/%E6%97%A5</span>
  179. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;language&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_lang</span>
  180. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;country&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">country</span>
  181. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;locale&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">locale</span>
  182. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;subdomain&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;supported_domains&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">country</span><span class="o">.</span><span class="n">upper</span><span class="p">(),</span> <span class="s1">&#39;www.google.com&#39;</span><span class="p">)</span>
  183. <span class="c1"># hl parameter:</span>
  184. <span class="c1"># The hl parameter specifies the interface language (host language) of</span>
  185. <span class="c1"># your user interface. To improve the performance and the quality of your</span>
  186. <span class="c1"># search results, you are strongly encouraged to set this parameter</span>
  187. <span class="c1"># explicitly.</span>
  188. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results#hlsp</span>
  189. <span class="c1"># The Interface Language:</span>
  190. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages</span>
  191. <span class="c1"># https://github.com/searxng/searxng/issues/2515#issuecomment-1607150817</span>
  192. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">][</span><span class="s1">&#39;hl&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">&#39;</span><span class="si">{</span><span class="n">lang_code</span><span class="si">}</span><span class="s1">-</span><span class="si">{</span><span class="n">country</span><span class="si">}</span><span class="s1">&#39;</span>
  193. <span class="c1"># lr parameter:</span>
  194. <span class="c1"># The lr (language restrict) parameter restricts search results to</span>
  195. <span class="c1"># documents written in a particular language.</span>
  196. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results#lrsp</span>
  197. <span class="c1"># Language Collection Values:</span>
  198. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results_appendices#languageCollections</span>
  199. <span class="c1">#</span>
  200. <span class="c1"># To select &#39;all&#39; languages an empty &#39;lr&#39; value is used.</span>
  201. <span class="c1">#</span>
  202. <span class="c1"># Different to other google services, Google Scholar supports to select more</span>
  203. <span class="c1"># than one language. The languages are separated by a pipe &#39;|&#39; (logical OR).</span>
  204. <span class="c1"># By example: &amp;lr=lang_zh-TW%7Clang_de selects articles written in</span>
  205. <span class="c1"># traditional chinese OR german language.</span>
  206. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">][</span><span class="s1">&#39;lr&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_lang</span>
  207. <span class="k">if</span> <span class="n">sxng_locale</span> <span class="o">==</span> <span class="s1">&#39;all&#39;</span><span class="p">:</span>
  208. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">][</span><span class="s1">&#39;lr&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  209. <span class="c1"># cr parameter:</span>
  210. <span class="c1"># The cr parameter restricts search results to documents originating in a</span>
  211. <span class="c1"># particular country.</span>
  212. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results#crsp</span>
  213. <span class="c1"># specify a region (country) only if a region is given in the selected</span>
  214. <span class="c1"># locale --&gt; https://github.com/searxng/searxng/issues/2672</span>
  215. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">][</span><span class="s1">&#39;cr&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  216. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">sxng_locale</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;-&#39;</span><span class="p">))</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
  217. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">][</span><span class="s1">&#39;cr&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;country&#39;</span> <span class="o">+</span> <span class="n">country</span>
  218. <span class="c1"># gl parameter: (mandatory by Google News)</span>
  219. <span class="c1"># The gl parameter value is a two-letter country code. For WebSearch</span>
  220. <span class="c1"># results, the gl parameter boosts search results whose country of origin</span>
  221. <span class="c1"># matches the parameter value. See the Country Codes section for a list of</span>
  222. <span class="c1"># valid values.</span>
  223. <span class="c1"># Specifying a gl parameter value in WebSearch requests should improve the</span>
  224. <span class="c1"># relevance of results. This is particularly true for international</span>
  225. <span class="c1"># customers and, even more specifically, for customers in English-speaking</span>
  226. <span class="c1"># countries other than the United States.</span>
  227. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results#glsp</span>
  228. <span class="c1"># https://github.com/searxng/searxng/issues/2515#issuecomment-1606294635</span>
  229. <span class="c1"># ret_val[&#39;params&#39;][&#39;gl&#39;] = country</span>
  230. <span class="c1"># ie parameter:</span>
  231. <span class="c1"># The ie parameter sets the character encoding scheme that should be used</span>
  232. <span class="c1"># to interpret the query string. The default ie value is latin1.</span>
  233. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results#iesp</span>
  234. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">][</span><span class="s1">&#39;ie&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;utf8&#39;</span>
  235. <span class="c1"># oe parameter:</span>
  236. <span class="c1"># The oe parameter sets the character encoding scheme that should be used</span>
  237. <span class="c1"># to decode the XML result. The default oe value is latin1.</span>
  238. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results#oesp</span>
  239. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">][</span><span class="s1">&#39;oe&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;utf8&#39;</span>
  240. <span class="c1"># num parameter:</span>
  241. <span class="c1"># The num parameter identifies the number of search results to return.</span>
  242. <span class="c1"># The default num value is 10, and the maximum value is 20. If you request</span>
  243. <span class="c1"># more than 20 results, only 20 results will be returned.</span>
  244. <span class="c1"># https://developers.google.com/custom-search/docs/xml_results#numsp</span>
  245. <span class="c1"># HINT: seems to have no effect (tested in google WEB &amp; Images)</span>
  246. <span class="c1"># ret_val[&#39;params&#39;][&#39;num&#39;] = 20</span>
  247. <span class="c1"># HTTP headers</span>
  248. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">][</span><span class="s1">&#39;Accept&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;*/*&#39;</span>
  249. <span class="c1"># Cookies</span>
  250. <span class="c1"># - https://github.com/searxng/searxng/pull/1679#issuecomment-1235432746</span>
  251. <span class="c1"># - https://github.com/searxng/searxng/issues/1555</span>
  252. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">][</span><span class="s1">&#39;CONSENT&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s2">&quot;YES+&quot;</span>
  253. <span class="k">return</span> <span class="n">ret_val</span></div>
  254. <span class="k">def</span><span class="w"> </span><span class="nf">detect_google_sorry</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
  255. <span class="k">if</span> <span class="n">resp</span><span class="o">.</span><span class="n">url</span><span class="o">.</span><span class="n">host</span> <span class="o">==</span> <span class="s1">&#39;sorry.google.com&#39;</span> <span class="ow">or</span> <span class="n">resp</span><span class="o">.</span><span class="n">url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;/sorry&#39;</span><span class="p">):</span>
  256. <span class="k">raise</span> <span class="n">SearxEngineCaptchaException</span><span class="p">()</span>
  257. <div class="viewcode-block" id="request">
  258. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google.request">[docs]</a>
  259. <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>
  260. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Google search request&quot;&quot;&quot;</span>
  261. <span class="c1"># pylint: disable=line-too-long</span>
  262. <span class="n">start</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">10</span>
  263. <span class="n">str_async</span> <span class="o">=</span> <span class="n">ui_async</span><span class="p">(</span><span class="n">start</span><span class="p">)</span>
  264. <span class="n">google_info</span> <span class="o">=</span> <span class="n">get_google_info</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">traits</span><span class="p">)</span>
  265. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;ARC_ID: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">str_async</span><span class="p">)</span>
  266. <span class="c1"># https://www.google.de/search?q=corona&amp;hl=de&amp;lr=lang_de&amp;start=0&amp;tbs=qdr%3Ad&amp;safe=medium</span>
  267. <span class="n">query_url</span> <span class="o">=</span> <span class="p">(</span>
  268. <span class="s1">&#39;https://&#39;</span>
  269. <span class="o">+</span> <span class="n">google_info</span><span class="p">[</span><span class="s1">&#39;subdomain&#39;</span><span class="p">]</span>
  270. <span class="o">+</span> <span class="s1">&#39;/search&#39;</span>
  271. <span class="o">+</span> <span class="s2">&quot;?&quot;</span>
  272. <span class="o">+</span> <span class="n">urlencode</span><span class="p">(</span>
  273. <span class="p">{</span>
  274. <span class="s1">&#39;q&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
  275. <span class="o">**</span><span class="n">google_info</span><span class="p">[</span><span class="s1">&#39;params&#39;</span><span class="p">],</span>
  276. <span class="s1">&#39;filter&#39;</span><span class="p">:</span> <span class="s1">&#39;0&#39;</span><span class="p">,</span>
  277. <span class="s1">&#39;start&#39;</span><span class="p">:</span> <span class="n">start</span><span class="p">,</span>
  278. <span class="c1"># &#39;vet&#39;: &#39;12ahUKEwik3ZbIzfn7AhXMX_EDHbUDBh0QxK8CegQIARAC..i&#39;,</span>
  279. <span class="c1"># &#39;ved&#39;: &#39;2ahUKEwik3ZbIzfn7AhXMX_EDHbUDBh0Q_skCegQIARAG&#39;,</span>
  280. <span class="c1"># &#39;cs&#39; : 1,</span>
  281. <span class="c1"># &#39;sa&#39;: &#39;N&#39;,</span>
  282. <span class="c1"># &#39;yv&#39;: 3,</span>
  283. <span class="c1"># &#39;prmd&#39;: &#39;vin&#39;,</span>
  284. <span class="c1"># &#39;ei&#39;: &#39;GASaY6TxOcy_xc8PtYeY6AE&#39;,</span>
  285. <span class="c1"># &#39;sa&#39;: &#39;N&#39;,</span>
  286. <span class="c1"># &#39;sstk&#39;: &#39;AcOHfVkD7sWCSAheZi-0tx_09XDO55gTWY0JNq3_V26cNN-c8lfD45aZYPI8s_Bqp8s57AHz5pxchDtAGCA_cikAWSjy9kw3kgg&#39;</span>
  287. <span class="c1"># formally known as use_mobile_ui</span>
  288. <span class="s1">&#39;asearch&#39;</span><span class="p">:</span> <span class="s1">&#39;arc&#39;</span><span class="p">,</span>
  289. <span class="s1">&#39;async&#39;</span><span class="p">:</span> <span class="n">str_async</span><span class="p">,</span>
  290. <span class="p">}</span>
  291. <span class="p">)</span>
  292. <span class="p">)</span>
  293. <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>
  294. <span class="n">query_url</span> <span class="o">+=</span> <span class="s1">&#39;&amp;&#39;</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">({</span><span class="s1">&#39;tbs&#39;</span><span class="p">:</span> <span class="s1">&#39;qdr:&#39;</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>
  295. <span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;safesearch&#39;</span><span class="p">]:</span>
  296. <span class="n">query_url</span> <span class="o">+=</span> <span class="s1">&#39;&amp;&#39;</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">({</span><span class="s1">&#39;safe&#39;</span><span class="p">:</span> <span class="n">filter_mapping</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;safesearch&#39;</span><span class="p">]]})</span>
  297. <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">query_url</span>
  298. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">google_info</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">]</span>
  299. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">google_info</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">])</span>
  300. <span class="k">return</span> <span class="n">params</span></div>
  301. <span class="c1"># =26;[3,&quot;dimg_ZNMiZPCqE4apxc8P3a2tuAQ_137&quot;]a87;data:image/jpeg;base64,/9j/4AAQSkZJRgABA</span>
  302. <span class="c1"># ...6T+9Nl4cnD+gr9OK8I56/tX3l86nWYw//2Q==26;</span>
  303. <span class="n">RE_DATA_IMAGE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;&quot;(dimg_[^&quot;]*)&quot;[^;]*;(data:image[^;]*;[^;]*);&#39;</span><span class="p">)</span>
  304. <span class="n">RE_DATA_IMAGE_end</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;&quot;(dimg_[^&quot;]*)&quot;[^;]*;(data:image[^;]*;[^;]*)$&#39;</span><span class="p">)</span>
  305. <span class="k">def</span><span class="w"> </span><span class="nf">parse_data_images</span><span class="p">(</span><span class="n">text</span><span class="p">:</span> <span class="nb">str</span><span class="p">):</span>
  306. <span class="n">data_image_map</span> <span class="o">=</span> <span class="p">{}</span>
  307. <span class="k">for</span> <span class="n">img_id</span><span class="p">,</span> <span class="n">data_image</span> <span class="ow">in</span> <span class="n">RE_DATA_IMAGE</span><span class="o">.</span><span class="n">findall</span><span class="p">(</span><span class="n">text</span><span class="p">):</span>
  308. <span class="n">end_pos</span> <span class="o">=</span> <span class="n">data_image</span><span class="o">.</span><span class="n">rfind</span><span class="p">(</span><span class="s1">&#39;=&#39;</span><span class="p">)</span>
  309. <span class="k">if</span> <span class="n">end_pos</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
  310. <span class="n">data_image</span> <span class="o">=</span> <span class="n">data_image</span><span class="p">[:</span> <span class="n">end_pos</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span>
  311. <span class="n">data_image_map</span><span class="p">[</span><span class="n">img_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">data_image</span>
  312. <span class="n">last</span> <span class="o">=</span> <span class="n">RE_DATA_IMAGE_end</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="n">text</span><span class="p">)</span>
  313. <span class="k">if</span> <span class="n">last</span><span class="p">:</span>
  314. <span class="n">data_image_map</span><span class="p">[</span><span class="n">last</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">)]</span> <span class="o">=</span> <span class="n">last</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
  315. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;data:image objects --&gt; </span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="nb">list</span><span class="p">(</span><span class="n">data_image_map</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span>
  316. <span class="k">return</span> <span class="n">data_image_map</span>
  317. <div class="viewcode-block" id="response">
  318. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google.response">[docs]</a>
  319. <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>
  320. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Get response from google&#39;s search request&quot;&quot;&quot;</span>
  321. <span class="c1"># pylint: disable=too-many-branches, too-many-statements</span>
  322. <span class="n">detect_google_sorry</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span>
  323. <span class="n">data_image_map</span> <span class="o">=</span> <span class="n">parse_data_images</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</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="c1"># convert the text to dom</span>
  326. <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>
  327. <span class="c1"># results --&gt; answer</span>
  328. <span class="n">answer_list</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">&#39;//div[contains(@class, &quot;LGOjhe&quot;)]&#39;</span><span class="p">)</span>
  329. <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">answer_list</span><span class="p">:</span>
  330. <span class="k">for</span> <span class="n">bubble</span> <span class="ow">in</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">item</span><span class="p">,</span> <span class="s1">&#39;.//div[@class=&quot;nnFGuf&quot;]&#39;</span><span class="p">):</span>
  331. <span class="n">bubble</span><span class="o">.</span><span class="n">drop_tree</span><span class="p">()</span>
  332. <span class="n">results</span><span class="o">.</span><span class="n">add</span><span class="p">(</span>
  333. <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>
  334. <span class="n">answer</span><span class="o">=</span><span class="n">extract_text</span><span class="p">(</span><span class="n">item</span><span class="p">),</span>
  335. <span class="n">url</span><span class="o">=</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">item</span><span class="p">,</span> <span class="s1">&#39;../..//a/@href&#39;</span><span class="p">)</span> <span class="o">+</span> <span class="p">[</span><span class="kc">None</span><span class="p">])[</span><span class="mi">0</span><span class="p">],</span>
  336. <span class="p">)</span>
  337. <span class="p">)</span>
  338. <span class="c1"># parse results</span>
  339. <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(@jscontroller, &quot;SC7lYd&quot;)]&#39;</span><span class="p">):</span>
  340. <span class="c1"># pylint: disable=too-many-nested-blocks</span>
  341. <span class="k">try</span><span class="p">:</span>
  342. <span class="n">title_tag</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;.//a/h3[1]&#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>
  343. <span class="k">if</span> <span class="n">title_tag</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  344. <span class="c1"># this not one of the common google results *section*</span>
  345. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;ignoring item from the result_xpath list: missing title&#39;</span><span class="p">)</span>
  346. <span class="k">continue</span>
  347. <span class="n">title</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">title_tag</span><span class="p">)</span>
  348. <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;.//a[h3]/@href&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
  349. <span class="k">if</span> <span class="n">url</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  350. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;ignoring item from the result_xpath list: missing url of title &quot;</span><span class="si">%s</span><span class="s1">&quot;&#39;</span><span class="p">,</span> <span class="n">title</span><span class="p">)</span>
  351. <span class="k">continue</span>
  352. <span class="n">content_nodes</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">&#39;.//div[contains(@data-sncf, &quot;1&quot;)]&#39;</span><span class="p">)</span>
  353. <span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="n">content_nodes</span><span class="p">:</span>
  354. <span class="k">for</span> <span class="n">script</span> <span class="ow">in</span> <span class="n">item</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s2">&quot;.//script&quot;</span><span class="p">):</span>
  355. <span class="n">script</span><span class="o">.</span><span class="n">getparent</span><span class="p">()</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">script</span><span class="p">)</span>
  356. <span class="n">content</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">content_nodes</span><span class="p">)</span>
  357. <span class="k">if</span> <span class="ow">not</span> <span class="n">content</span><span class="p">:</span>
  358. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;ignoring item from the result_xpath list: missing content of title &quot;</span><span class="si">%s</span><span class="s1">&quot;&#39;</span><span class="p">,</span> <span class="n">title</span><span class="p">)</span>
  359. <span class="k">continue</span>
  360. <span class="n">thumbnail</span> <span class="o">=</span> <span class="n">content_nodes</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">&#39;.//img/@src&#39;</span><span class="p">)</span>
  361. <span class="k">if</span> <span class="n">thumbnail</span><span class="p">:</span>
  362. <span class="n">thumbnail</span> <span class="o">=</span> <span class="n">thumbnail</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
  363. <span class="k">if</span> <span class="n">thumbnail</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;data:image&#39;</span><span class="p">):</span>
  364. <span class="n">img_id</span> <span class="o">=</span> <span class="n">content_nodes</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">&#39;.//img/@id&#39;</span><span class="p">)</span>
  365. <span class="k">if</span> <span class="n">img_id</span><span class="p">:</span>
  366. <span class="n">thumbnail</span> <span class="o">=</span> <span class="n">data_image_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">img_id</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
  367. <span class="k">else</span><span class="p">:</span>
  368. <span class="n">thumbnail</span> <span class="o">=</span> <span class="kc">None</span>
  369. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">&#39;url&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span> <span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span> <span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span> <span class="s1">&#39;thumbnail&#39;</span><span class="p">:</span> <span class="n">thumbnail</span><span class="p">})</span>
  370. <span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span>
  371. <span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">exc_info</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
  372. <span class="k">continue</span>
  373. <span class="c1"># parse suggestion</span>
  374. <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="n">suggestion_xpath</span><span class="p">):</span>
  375. <span class="c1"># append suggestion</span>
  376. <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>
  377. <span class="c1"># return results</span>
  378. <span class="k">return</span> <span class="n">results</span></div>
  379. <span class="c1"># get supported languages from their site</span>
  380. <span class="n">skip_countries</span> <span class="o">=</span> <span class="p">[</span>
  381. <span class="c1"># official language of google-country not in google-languages</span>
  382. <span class="s1">&#39;AL&#39;</span><span class="p">,</span> <span class="c1"># Albanien (sq)</span>
  383. <span class="s1">&#39;AZ&#39;</span><span class="p">,</span> <span class="c1"># Aserbaidschan (az)</span>
  384. <span class="s1">&#39;BD&#39;</span><span class="p">,</span> <span class="c1"># Bangladesch (bn)</span>
  385. <span class="s1">&#39;BN&#39;</span><span class="p">,</span> <span class="c1"># Brunei Darussalam (ms)</span>
  386. <span class="s1">&#39;BT&#39;</span><span class="p">,</span> <span class="c1"># Bhutan (dz)</span>
  387. <span class="s1">&#39;ET&#39;</span><span class="p">,</span> <span class="c1"># Äthiopien (am)</span>
  388. <span class="s1">&#39;GE&#39;</span><span class="p">,</span> <span class="c1"># Georgien (ka, os)</span>
  389. <span class="s1">&#39;GL&#39;</span><span class="p">,</span> <span class="c1"># Grönland (kl)</span>
  390. <span class="s1">&#39;KH&#39;</span><span class="p">,</span> <span class="c1"># Kambodscha (km)</span>
  391. <span class="s1">&#39;LA&#39;</span><span class="p">,</span> <span class="c1"># Laos (lo)</span>
  392. <span class="s1">&#39;LK&#39;</span><span class="p">,</span> <span class="c1"># Sri Lanka (si, ta)</span>
  393. <span class="s1">&#39;ME&#39;</span><span class="p">,</span> <span class="c1"># Montenegro (sr)</span>
  394. <span class="s1">&#39;MK&#39;</span><span class="p">,</span> <span class="c1"># Nordmazedonien (mk, sq)</span>
  395. <span class="s1">&#39;MM&#39;</span><span class="p">,</span> <span class="c1"># Myanmar (my)</span>
  396. <span class="s1">&#39;MN&#39;</span><span class="p">,</span> <span class="c1"># Mongolei (mn)</span>
  397. <span class="s1">&#39;MV&#39;</span><span class="p">,</span> <span class="c1"># Malediven (dv) // dv_MV is unknown by babel</span>
  398. <span class="s1">&#39;MY&#39;</span><span class="p">,</span> <span class="c1"># Malaysia (ms)</span>
  399. <span class="s1">&#39;NP&#39;</span><span class="p">,</span> <span class="c1"># Nepal (ne)</span>
  400. <span class="s1">&#39;TJ&#39;</span><span class="p">,</span> <span class="c1"># Tadschikistan (tg)</span>
  401. <span class="s1">&#39;TM&#39;</span><span class="p">,</span> <span class="c1"># Turkmenistan (tk)</span>
  402. <span class="s1">&#39;UZ&#39;</span><span class="p">,</span> <span class="c1"># Usbekistan (uz)</span>
  403. <span class="p">]</span>
  404. <div class="viewcode-block" id="fetch_traits">
  405. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google.fetch_traits">[docs]</a>
  406. <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> <span class="n">add_domains</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
  407. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Fetch languages from Google.&quot;&quot;&quot;</span>
  408. <span class="c1"># pylint: disable=import-outside-toplevel, too-many-branches</span>
  409. <span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;supported_domains&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
  410. <span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s1">&#39;https://www.google.com/preferences&#39;</span><span class="p">)</span>
  411. <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>
  412. <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">&quot;Response from Google&#39;s preferences is not OK.&quot;</span><span class="p">)</span>
  413. <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="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;&lt;?xml version=&quot;1.0&quot; encoding=&quot;UTF-8&quot;?&gt;&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">))</span>
  414. <span class="c1"># supported language codes</span>
  415. <span class="n">lang_map</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;no&#39;</span><span class="p">:</span> <span class="s1">&#39;nb&#39;</span><span class="p">}</span>
  416. <span class="k">for</span> <span class="n">x</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="s2">&quot;//select[@name=&#39;hl&#39;]/option&quot;</span><span class="p">):</span>
  417. <span class="n">eng_lang</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;value&quot;</span><span class="p">)</span>
  418. <span class="k">try</span><span class="p">:</span>
  419. <span class="n">locale</span> <span class="o">=</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">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> <span class="n">sep</span><span class="o">=</span><span class="s1">&#39;-&#39;</span><span class="p">)</span>
  420. <span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span>
  421. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;INFO: google UI 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">eng_lang</span><span class="p">,</span> <span class="n">x</span><span class="o">.</span><span class="n">text</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><span class="o">.</span><span class="n">strip</span><span class="p">()))</span>
  422. <span class="k">continue</span>
  423. <span class="n">sxng_lang</span> <span class="o">=</span> <span class="n">language_tag</span><span class="p">(</span><span class="n">locale</span><span class="p">)</span>
  424. <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_lang</span><span class="p">)</span>
  425. <span class="k">if</span> <span class="n">conflict</span><span class="p">:</span>
  426. <span class="k">if</span> <span class="n">conflict</span> <span class="o">!=</span> <span class="n">eng_lang</span><span class="p">:</span>
  427. <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_lang</span><span class="p">,</span> <span class="n">conflict</span><span class="p">,</span> <span class="n">eng_lang</span><span class="p">))</span>
  428. <span class="k">continue</span>
  429. <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="n">sxng_lang</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;lang_&#39;</span> <span class="o">+</span> <span class="n">eng_lang</span>
  430. <span class="c1"># alias languages</span>
  431. <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="s1">&#39;zh&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;lang_zh-CN&#39;</span>
  432. <span class="c1"># supported region codes</span>
  433. <span class="k">for</span> <span class="n">x</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="s2">&quot;//select[@name=&#39;gl&#39;]/option&quot;</span><span class="p">):</span>
  434. <span class="n">eng_country</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;value&quot;</span><span class="p">)</span>
  435. <span class="k">if</span> <span class="n">eng_country</span> <span class="ow">in</span> <span class="n">skip_countries</span><span class="p">:</span>
  436. <span class="k">continue</span>
  437. <span class="k">if</span> <span class="n">eng_country</span> <span class="o">==</span> <span class="s1">&#39;ZZ&#39;</span><span class="p">:</span>
  438. <span class="n">engine_traits</span><span class="o">.</span><span class="n">all_locale</span> <span class="o">=</span> <span class="s1">&#39;ZZ&#39;</span>
  439. <span class="k">continue</span>
  440. <span class="n">sxng_locales</span> <span class="o">=</span> <span class="n">get_official_locales</span><span class="p">(</span><span class="n">eng_country</span><span class="p">,</span> <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="o">.</span><span class="n">keys</span><span class="p">(),</span> <span class="n">regional</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
  441. <span class="k">if</span> <span class="ow">not</span> <span class="n">sxng_locales</span><span class="p">:</span>
  442. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: can&#39;t map from google country </span><span class="si">%s</span><span class="s2"> (</span><span class="si">%s</span><span class="s2">) to a babel region.&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">x</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;data-name&#39;</span><span class="p">),</span> <span class="n">eng_country</span><span class="p">))</span>
  443. <span class="k">continue</span>
  444. <span class="k">for</span> <span class="n">sxng_locale</span> <span class="ow">in</span> <span class="n">sxng_locales</span><span class="p">:</span>
  445. <span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="p">[</span><span class="n">region_tag</span><span class="p">(</span><span class="n">sxng_locale</span><span class="p">)]</span> <span class="o">=</span> <span class="n">eng_country</span>
  446. <span class="c1"># alias regions</span>
  447. <span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="p">[</span><span class="s1">&#39;zh-CN&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;HK&#39;</span>
  448. <span class="c1"># supported domains</span>
  449. <span class="k">if</span> <span class="n">add_domains</span><span class="p">:</span>
  450. <span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s1">&#39;https://www.google.com/supported_domains&#39;</span><span class="p">)</span>
  451. <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>
  452. <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">&quot;Response from https://www.google.com/supported_domains is not OK.&quot;</span><span class="p">)</span>
  453. <span class="k">for</span> <span class="n">domain</span> <span class="ow">in</span> <span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">split</span><span class="p">():</span> <span class="c1"># type: ignore</span>
  454. <span class="n">domain</span> <span class="o">=</span> <span class="n">domain</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
  455. <span class="k">if</span> <span class="ow">not</span> <span class="n">domain</span> <span class="ow">or</span> <span class="n">domain</span> <span class="ow">in</span> <span class="p">[</span>
  456. <span class="s1">&#39;.google.com&#39;</span><span class="p">,</span>
  457. <span class="p">]:</span>
  458. <span class="k">continue</span>
  459. <span class="n">region</span> <span class="o">=</span> <span class="n">domain</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;.&#39;</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">upper</span><span class="p">()</span>
  460. <span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;supported_domains&#39;</span><span class="p">][</span><span class="n">region</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;www&#39;</span> <span class="o">+</span> <span class="n">domain</span> <span class="c1"># type: ignore</span>
  461. <span class="k">if</span> <span class="n">region</span> <span class="o">==</span> <span class="s1">&#39;HK&#39;</span><span class="p">:</span>
  462. <span class="c1"># There is no google.cn, we use .com.hk for zh-CN</span>
  463. <span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;supported_domains&#39;</span><span class="p">][</span><span class="s1">&#39;CN&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;www&#39;</span> <span class="o">+</span> <span class="n">domain</span> <span class="c1"># type: ignore</span></div>
  464. </pre></div>
  465. <div class="clearer"></div>
  466. </div>
  467. </div>
  468. </div>
  469. <span id="sidebar-top"></span>
  470. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  471. <div class="sphinxsidebarwrapper">
  472. <p class="logo"><a href="../../../index.html">
  473. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  474. </a></p>
  475. <h3><a href="../../../index.html">Table of Contents</a></h3>
  476. <ul>
  477. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  478. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  479. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  480. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  481. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  482. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  483. </ul>
  484. <h3>Project Links</h3>
  485. <ul>
  486. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  487. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  488. <li><a href="https://searx.space">Public instances</a>
  489. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  490. </ul><h3>Navigation</h3>
  491. <ul>
  492. <li><a href="../../../index.html">Overview</a>
  493. <ul>
  494. <li><a href="../../index.html">Module code</a>
  495. <ul>
  496. <li><a href="../engines.html">searx.engines</a>
  497. </ul>
  498. </li></ul>
  499. </li>
  500. </ul>
  501. </li>
  502. </ul>
  503. <search id="searchbox" style="display: none" role="search">
  504. <h3 id="searchlabel">Quick search</h3>
  505. <div class="searchformwrapper">
  506. <form class="search" action="../../../search.html" method="get">
  507. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  508. <input type="submit" value="Go" />
  509. </form>
  510. </div>
  511. </search>
  512. <script>document.getElementById('searchbox').style.display = "block"</script>
  513. </div>
  514. </div>
  515. <div class="clearer"></div>
  516. </div>
  517. <div class="footer" role="contentinfo">
  518. &#169; Copyright SearXNG team.
  519. </div>
  520. </body>
  521. </html>