google_scholar.html 31 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344
  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_scholar &#8212; SearXNG Documentation (2025.5.1+1a1628149)</title>
  8. <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
  9. <link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
  10. <script src="../../../_static/documentation_options.js?v=cc9fc81d"></script>
  11. <script src="../../../_static/doctools.js?v=9a2dae69"></script>
  12. <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
  13. <script data-project="searxng" data-version="2025.5.1+1a1628149" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
  14. <link rel="index" title="Index" href="../../../genindex.html" />
  15. <link rel="search" title="Search" href="../../../search.html" />
  16. </head><body>
  17. <div class="related" role="navigation" aria-label="Related">
  18. <h3>Navigation</h3>
  19. <ul>
  20. <li class="right" style="margin-right: 10px">
  21. <a href="../../../genindex.html" title="General Index"
  22. accesskey="I">index</a></li>
  23. <li class="right" >
  24. <a href="../../../py-modindex.html" title="Python Module Index"
  25. >modules</a> |</li>
  26. <li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2025.5.1+1a1628149)</a> &#187;</li>
  27. <li class="nav-item nav-item-1"><a href="../../index.html" >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_scholar</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_scholar</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 Scholar engine.</span>
  39. <span class="sd">Compared to other Google services the Scholar engine has a simple GET REST-API</span>
  40. <span class="sd">and there does not exists `async` API. Even though the API slightly vintage we</span>
  41. <span class="sd">can make use of the :ref:`google API` to assemble the arguments of the GET</span>
  42. <span class="sd">request.</span>
  43. <span class="sd">&quot;&quot;&quot;</span>
  44. <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>
  45. <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">Optional</span>
  46. <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>
  47. <span class="kn">from</span><span class="w"> </span><span class="nn">datetime</span><span class="w"> </span><span class="kn">import</span> <span class="n">datetime</span>
  48. <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>
  49. <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>
  50. <span class="n">eval_xpath</span><span class="p">,</span>
  51. <span class="n">eval_xpath_getindex</span><span class="p">,</span>
  52. <span class="n">eval_xpath_list</span><span class="p">,</span>
  53. <span class="n">extract_text</span><span class="p">,</span>
  54. <span class="p">)</span>
  55. <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>
  56. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.engines.google</span><span class="w"> </span><span class="kn">import</span> <span class="n">fetch_traits</span> <span class="c1"># pylint: disable=unused-import</span>
  57. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.engines.google</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
  58. <span class="n">get_google_info</span><span class="p">,</span>
  59. <span class="n">time_range_dict</span><span class="p">,</span>
  60. <span class="p">)</span>
  61. <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>
  62. <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
  63. <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
  64. <span class="n">logger</span><span class="p">:</span> <span class="n">logging</span><span class="o">.</span><span class="n">Logger</span>
  65. <span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
  66. <span class="c1"># about</span>
  67. <span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
  68. <span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="s1">&#39;https://scholar.google.com&#39;</span><span class="p">,</span>
  69. <span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s1">&#39;Q494817&#39;</span><span class="p">,</span>
  70. <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>
  71. <span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  72. <span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  73. <span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s1">&#39;HTML&#39;</span><span class="p">,</span>
  74. <span class="p">}</span>
  75. <span class="c1"># engine dependent config</span>
  76. <span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;science&#39;</span><span class="p">,</span> <span class="s1">&#39;scientific publications&#39;</span><span class="p">]</span>
  77. <span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
  78. <span class="n">max_page</span> <span class="o">=</span> <span class="mi">50</span>
  79. <span class="sd">&quot;&quot;&quot;`Google max 50 pages`_</span>
  80. <span class="sd">.. _Google max 50 pages: https://github.com/searxng/searxng/issues/2982</span>
  81. <span class="sd">&quot;&quot;&quot;</span>
  82. <span class="n">language_support</span> <span class="o">=</span> <span class="kc">True</span>
  83. <span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
  84. <span class="n">safesearch</span> <span class="o">=</span> <span class="kc">False</span>
  85. <span class="n">send_accept_language_header</span> <span class="o">=</span> <span class="kc">True</span>
  86. <div class="viewcode-block" id="time_range_args">
  87. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.time_range_args">[docs]</a>
  88. <span class="k">def</span><span class="w"> </span><span class="nf">time_range_args</span><span class="p">(</span><span class="n">params</span><span class="p">):</span>
  89. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns a dictionary with a time range arguments based on</span>
  90. <span class="sd"> ``params[&#39;time_range&#39;]``.</span>
  91. <span class="sd"> Google Scholar supports a detailed search by year. Searching by *last</span>
  92. <span class="sd"> month* or *last week* (as offered by SearXNG) is uncommon for scientific</span>
  93. <span class="sd"> publications and is not supported by Google Scholar.</span>
  94. <span class="sd"> To limit the result list when the users selects a range, all the SearXNG</span>
  95. <span class="sd"> ranges (*day*, *week*, *month*, *year*) are mapped to *year*. If no range</span>
  96. <span class="sd"> is set an empty dictionary of arguments is returned. Example; when</span>
  97. <span class="sd"> user selects a time range (current year minus one in 2022):</span>
  98. <span class="sd"> .. code:: python</span>
  99. <span class="sd"> { &#39;as_ylo&#39; : 2021 }</span>
  100. <span class="sd"> &quot;&quot;&quot;</span>
  101. <span class="n">ret_val</span> <span class="o">=</span> <span class="p">{}</span>
  102. <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>
  103. <span class="n">ret_val</span><span class="p">[</span><span class="s1">&#39;as_ylo&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">now</span><span class="p">()</span><span class="o">.</span><span class="n">year</span> <span class="o">-</span> <span class="mi">1</span>
  104. <span class="k">return</span> <span class="n">ret_val</span></div>
  105. <div class="viewcode-block" id="detect_google_captcha">
  106. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.detect_google_captcha">[docs]</a>
  107. <span class="k">def</span><span class="w"> </span><span class="nf">detect_google_captcha</span><span class="p">(</span><span class="n">dom</span><span class="p">):</span>
  108. <span class="w"> </span><span class="sd">&quot;&quot;&quot;In case of CAPTCHA Google Scholar open its own *not a Robot* dialog and is</span>
  109. <span class="sd"> not redirected to ``sorry.google.com``.</span>
  110. <span class="sd"> &quot;&quot;&quot;</span>
  111. <span class="k">if</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;gs_captcha_f&#39;]&quot;</span><span class="p">):</span>
  112. <span class="k">raise</span> <span class="n">SearxEngineCaptchaException</span><span class="p">()</span></div>
  113. <div class="viewcode-block" id="request">
  114. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.request">[docs]</a>
  115. <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>
  116. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Google-Scholar search request&quot;&quot;&quot;</span>
  117. <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>
  118. <span class="c1"># subdomain is: scholar.google.xy</span>
  119. <span class="n">google_info</span><span class="p">[</span><span class="s1">&#39;subdomain&#39;</span><span class="p">]</span> <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><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">&quot;www.&quot;</span><span class="p">,</span> <span class="s2">&quot;scholar.&quot;</span><span class="p">)</span>
  120. <span class="n">args</span> <span class="o">=</span> <span class="p">{</span>
  121. <span class="s1">&#39;q&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
  122. <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>
  123. <span class="s1">&#39;start&#39;</span><span class="p">:</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><span class="p">,</span>
  124. <span class="s1">&#39;as_sdt&#39;</span><span class="p">:</span> <span class="s1">&#39;2007&#39;</span><span class="p">,</span> <span class="c1"># include patents / to disable set &#39;0,5&#39;</span>
  125. <span class="s1">&#39;as_vis&#39;</span><span class="p">:</span> <span class="s1">&#39;0&#39;</span><span class="p">,</span> <span class="c1"># include citations / to disable set &#39;1&#39;</span>
  126. <span class="p">}</span>
  127. <span class="n">args</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">time_range_args</span><span class="p">(</span><span class="n">params</span><span class="p">))</span>
  128. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;url&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;https://&#39;</span> <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> <span class="o">+</span> <span class="s1">&#39;/scholar?&#39;</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">(</span><span class="n">args</span><span class="p">)</span>
  129. <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>
  130. <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>
  131. <span class="k">return</span> <span class="n">params</span></div>
  132. <div class="viewcode-block" id="parse_gs_a">
  133. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.parse_gs_a">[docs]</a>
  134. <span class="k">def</span><span class="w"> </span><span class="nf">parse_gs_a</span><span class="p">(</span><span class="n">text</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
  135. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Parse the text written in green.</span>
  136. <span class="sd"> Possible formats:</span>
  137. <span class="sd"> * &quot;{authors} - {journal}, {year} - {publisher}&quot;</span>
  138. <span class="sd"> * &quot;{authors} - {year} - {publisher}&quot;</span>
  139. <span class="sd"> * &quot;{authors} - {publisher}&quot;</span>
  140. <span class="sd"> &quot;&quot;&quot;</span>
  141. <span class="k">if</span> <span class="n">text</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">text</span> <span class="o">==</span> <span class="s2">&quot;&quot;</span><span class="p">:</span>
  142. <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span>
  143. <span class="n">s_text</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="s1">&#39; - &#39;</span><span class="p">)</span>
  144. <span class="n">authors</span> <span class="o">=</span> <span class="n">s_text</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;, &#39;</span><span class="p">)</span>
  145. <span class="n">publisher</span> <span class="o">=</span> <span class="n">s_text</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
  146. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">s_text</span><span class="p">)</span> <span class="o">!=</span> <span class="mi">3</span><span class="p">:</span>
  147. <span class="k">return</span> <span class="n">authors</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="n">publisher</span><span class="p">,</span> <span class="kc">None</span>
  148. <span class="c1"># the format is &quot;{authors} - {journal}, {year} - {publisher}&quot; or &quot;{authors} - {year} - {publisher}&quot;</span>
  149. <span class="c1"># get journal and year</span>
  150. <span class="n">journal_year</span> <span class="o">=</span> <span class="n">s_text</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;, &#39;</span><span class="p">)</span>
  151. <span class="c1"># journal is optional and may contains some coma</span>
  152. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">journal_year</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
  153. <span class="n">journal</span> <span class="o">=</span> <span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">journal_year</span><span class="p">[</span><span class="mi">0</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span>
  154. <span class="k">if</span> <span class="n">journal</span> <span class="o">==</span> <span class="s1">&#39;…&#39;</span><span class="p">:</span>
  155. <span class="n">journal</span> <span class="o">=</span> <span class="kc">None</span>
  156. <span class="k">else</span><span class="p">:</span>
  157. <span class="n">journal</span> <span class="o">=</span> <span class="kc">None</span>
  158. <span class="c1"># year</span>
  159. <span class="n">year</span> <span class="o">=</span> <span class="n">journal_year</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
  160. <span class="k">try</span><span class="p">:</span>
  161. <span class="n">publishedDate</span> <span class="o">=</span> <span class="n">datetime</span><span class="o">.</span><span class="n">strptime</span><span class="p">(</span><span class="n">year</span><span class="o">.</span><span class="n">strip</span><span class="p">(),</span> <span class="s1">&#39;%Y&#39;</span><span class="p">)</span>
  162. <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
  163. <span class="n">publishedDate</span> <span class="o">=</span> <span class="kc">None</span>
  164. <span class="k">return</span> <span class="n">authors</span><span class="p">,</span> <span class="n">journal</span><span class="p">,</span> <span class="n">publisher</span><span class="p">,</span> <span class="n">publishedDate</span></div>
  165. <div class="viewcode-block" id="response">
  166. <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.response">[docs]</a>
  167. <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="c1"># pylint: disable=too-many-locals</span>
  168. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Parse response from Google Scholar&quot;&quot;&quot;</span>
  169. <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
  170. <span class="c1"># convert the text to dom</span>
  171. <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>
  172. <span class="n">detect_google_captcha</span><span class="p">(</span><span class="n">dom</span><span class="p">)</span>
  173. <span class="c1"># parse results</span>
  174. <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[@data-rp]&#39;</span><span class="p">):</span>
  175. <span class="n">title</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">result</span><span class="p">,</span> <span class="s1">&#39;.//h3[1]//a&#39;</span><span class="p">))</span>
  176. <span class="k">if</span> <span class="ow">not</span> <span class="n">title</span><span class="p">:</span>
  177. <span class="c1"># this is a [ZITATION] block</span>
  178. <span class="k">continue</span>
  179. <span class="n">pub_type</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">result</span><span class="p">,</span> <span class="s1">&#39;.//span[@class=&quot;gs_ctg2&quot;]&#39;</span><span class="p">))</span>
  180. <span class="k">if</span> <span class="n">pub_type</span><span class="p">:</span>
  181. <span class="n">pub_type</span> <span class="o">=</span> <span class="n">pub_type</span><span class="p">[</span><span class="mi">1</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">lower</span><span class="p">()</span>
  182. <span class="n">url</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">&#39;.//h3[1]//a/@href&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
  183. <span class="n">content</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">result</span><span class="p">,</span> <span class="s1">&#39;.//div[@class=&quot;gs_rs&quot;]&#39;</span><span class="p">))</span>
  184. <span class="n">authors</span><span class="p">,</span> <span class="n">journal</span><span class="p">,</span> <span class="n">publisher</span><span class="p">,</span> <span class="n">publishedDate</span> <span class="o">=</span> <span class="n">parse_gs_a</span><span class="p">(</span>
  185. <span class="n">extract_text</span><span class="p">(</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[@class=&quot;gs_a&quot;]&#39;</span><span class="p">))</span>
  186. <span class="p">)</span>
  187. <span class="k">if</span> <span class="n">publisher</span> <span class="ow">in</span> <span class="n">url</span><span class="p">:</span>
  188. <span class="n">publisher</span> <span class="o">=</span> <span class="kc">None</span>
  189. <span class="c1"># cited by</span>
  190. <span class="n">comments</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">result</span><span class="p">,</span> <span class="s1">&#39;.//div[@class=&quot;gs_fl&quot;]/a[starts-with(@href,&quot;/scholar?cites=&quot;)]&#39;</span><span class="p">))</span>
  191. <span class="c1"># link to the html or pdf document</span>
  192. <span class="n">html_url</span> <span class="o">=</span> <span class="kc">None</span>
  193. <span class="n">pdf_url</span> <span class="o">=</span> <span class="kc">None</span>
  194. <span class="n">doc_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;.//div[@class=&quot;gs_or_ggsm&quot;]/a/@href&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
  195. <span class="n">doc_type</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">result</span><span class="p">,</span> <span class="s1">&#39;.//span[@class=&quot;gs_ctg2&quot;]&#39;</span><span class="p">))</span>
  196. <span class="k">if</span> <span class="n">doc_type</span> <span class="o">==</span> <span class="s2">&quot;[PDF]&quot;</span><span class="p">:</span>
  197. <span class="n">pdf_url</span> <span class="o">=</span> <span class="n">doc_url</span>
  198. <span class="k">else</span><span class="p">:</span>
  199. <span class="n">html_url</span> <span class="o">=</span> <span class="n">doc_url</span>
  200. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
  201. <span class="p">{</span>
  202. <span class="s1">&#39;template&#39;</span><span class="p">:</span> <span class="s1">&#39;paper.html&#39;</span><span class="p">,</span>
  203. <span class="s1">&#39;type&#39;</span><span class="p">:</span> <span class="n">pub_type</span><span class="p">,</span>
  204. <span class="s1">&#39;url&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span>
  205. <span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
  206. <span class="s1">&#39;authors&#39;</span><span class="p">:</span> <span class="n">authors</span><span class="p">,</span>
  207. <span class="s1">&#39;publisher&#39;</span><span class="p">:</span> <span class="n">publisher</span><span class="p">,</span>
  208. <span class="s1">&#39;journal&#39;</span><span class="p">:</span> <span class="n">journal</span><span class="p">,</span>
  209. <span class="s1">&#39;publishedDate&#39;</span><span class="p">:</span> <span class="n">publishedDate</span><span class="p">,</span>
  210. <span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span>
  211. <span class="s1">&#39;comments&#39;</span><span class="p">:</span> <span class="n">comments</span><span class="p">,</span>
  212. <span class="s1">&#39;html_url&#39;</span><span class="p">:</span> <span class="n">html_url</span><span class="p">,</span>
  213. <span class="s1">&#39;pdf_url&#39;</span><span class="p">:</span> <span class="n">pdf_url</span><span class="p">,</span>
  214. <span class="p">}</span>
  215. <span class="p">)</span>
  216. <span class="c1"># parse suggestion</span>
  217. <span class="k">for</span> <span class="n">suggestion</span> <span class="ow">in</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;gs_qsuggest_wrap&quot;)]//li//a&#39;</span><span class="p">):</span>
  218. <span class="c1"># append suggestion</span>
  219. <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>
  220. <span class="k">for</span> <span class="n">correction</span> <span class="ow">in</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[@class=&quot;gs_r gs_pda&quot;]/a&#39;</span><span class="p">):</span>
  221. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">&#39;correction&#39;</span><span class="p">:</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">correction</span><span class="p">)})</span>
  222. <span class="k">return</span> <span class="n">results</span></div>
  223. </pre></div>
  224. <div class="clearer"></div>
  225. </div>
  226. </div>
  227. </div>
  228. <span id="sidebar-top"></span>
  229. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  230. <div class="sphinxsidebarwrapper">
  231. <p class="logo"><a href="../../../index.html">
  232. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  233. </a></p>
  234. <h3><a href="../../../index.html">Table of Contents</a></h3>
  235. <ul>
  236. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  237. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  238. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  239. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  240. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  241. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  242. </ul>
  243. <h3>Project Links</h3>
  244. <ul>
  245. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  246. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  247. <li><a href="https://searx.space">Public instances</a>
  248. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  249. </ul><h3>Navigation</h3>
  250. <ul>
  251. <li><a href="../../../index.html">Overview</a>
  252. <ul>
  253. <li><a href="../../index.html">Module code</a>
  254. <ul>
  255. <li><a href="../engines.html">searx.engines</a>
  256. </ul>
  257. </li></ul>
  258. </li>
  259. </ul>
  260. </li>
  261. </ul>
  262. <search id="searchbox" style="display: none" role="search">
  263. <h3 id="searchlabel">Quick search</h3>
  264. <div class="searchformwrapper">
  265. <form class="search" action="../../../search.html" method="get">
  266. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  267. <input type="submit" value="Go" />
  268. </form>
  269. </div>
  270. </search>
  271. <script>document.getElementById('searchbox').style.display = "block"</script>
  272. </div>
  273. </div>
  274. <div class="clearer"></div>
  275. </div>
  276. <div class="footer" role="contentinfo">
  277. &#169; Copyright SearXNG team.
  278. </div>
  279. </body>
  280. </html>