123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344 |
- <!DOCTYPE html>
- <html lang="en" data-content_root="../../../">
- <head>
- <meta charset="utf-8" />
- <meta name="viewport" content="width=device-width, initial-scale=1.0" />
- <meta name="viewport" content="width=device-width, initial-scale=1">
- <title>searx.engines.google_scholar — SearXNG Documentation (2025.5.1+1a1628149)</title>
- <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
- <link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
- <script src="../../../_static/documentation_options.js?v=cc9fc81d"></script>
- <script src="../../../_static/doctools.js?v=9a2dae69"></script>
- <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
- <script data-project="searxng" data-version="2025.5.1+1a1628149" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
- <link rel="index" title="Index" href="../../../genindex.html" />
- <link rel="search" title="Search" href="../../../search.html" />
- </head><body>
- <div class="related" role="navigation" aria-label="Related">
- <h3>Navigation</h3>
- <ul>
- <li class="right" style="margin-right: 10px">
- <a href="../../../genindex.html" title="General Index"
- accesskey="I">index</a></li>
- <li class="right" >
- <a href="../../../py-modindex.html" title="Python Module Index"
- >modules</a> |</li>
- <li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2025.5.1+1a1628149)</a> »</li>
- <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
- <li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> »</li>
- <li class="nav-item nav-item-this"><a href="">searx.engines.google_scholar</a></li>
- </ul>
- </div>
- <div class="document">
- <div class="documentwrapper">
- <div class="bodywrapper">
- <div class="body" role="main">
-
- <h1>Source code for searx.engines.google_scholar</h1><div class="highlight"><pre>
- <span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
- <span class="sd">"""This is the implementation of the Google Scholar engine.</span>
- <span class="sd">Compared to other Google services the Scholar engine has a simple GET REST-API</span>
- <span class="sd">and there does not exists `async` API. Even though the API slightly vintage we</span>
- <span class="sd">can make use of the :ref:`google API` to assemble the arguments of the GET</span>
- <span class="sd">request.</span>
- <span class="sd">"""</span>
- <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>
- <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>
- <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>
- <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>
- <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>
- <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>
- <span class="n">eval_xpath</span><span class="p">,</span>
- <span class="n">eval_xpath_getindex</span><span class="p">,</span>
- <span class="n">eval_xpath_list</span><span class="p">,</span>
- <span class="n">extract_text</span><span class="p">,</span>
- <span class="p">)</span>
- <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>
- <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>
- <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>
- <span class="n">get_google_info</span><span class="p">,</span>
- <span class="n">time_range_dict</span><span class="p">,</span>
- <span class="p">)</span>
- <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>
- <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
- <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
- <span class="n">logger</span><span class="p">:</span> <span class="n">logging</span><span class="o">.</span><span class="n">Logger</span>
- <span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
- <span class="c1"># about</span>
- <span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
- <span class="s2">"website"</span><span class="p">:</span> <span class="s1">'https://scholar.google.com'</span><span class="p">,</span>
- <span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s1">'Q494817'</span><span class="p">,</span>
- <span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="s1">'https://developers.google.com/custom-search'</span><span class="p">,</span>
- <span class="s2">"use_official_api"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
- <span class="s2">"require_api_key"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
- <span class="s2">"results"</span><span class="p">:</span> <span class="s1">'HTML'</span><span class="p">,</span>
- <span class="p">}</span>
- <span class="c1"># engine dependent config</span>
- <span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'science'</span><span class="p">,</span> <span class="s1">'scientific publications'</span><span class="p">]</span>
- <span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
- <span class="n">max_page</span> <span class="o">=</span> <span class="mi">50</span>
- <span class="sd">"""`Google max 50 pages`_</span>
- <span class="sd">.. _Google max 50 pages: https://github.com/searxng/searxng/issues/2982</span>
- <span class="sd">"""</span>
- <span class="n">language_support</span> <span class="o">=</span> <span class="kc">True</span>
- <span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
- <span class="n">safesearch</span> <span class="o">=</span> <span class="kc">False</span>
- <span class="n">send_accept_language_header</span> <span class="o">=</span> <span class="kc">True</span>
- <div class="viewcode-block" id="time_range_args">
- <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.time_range_args">[docs]</a>
- <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>
- <span class="w"> </span><span class="sd">"""Returns a dictionary with a time range arguments based on</span>
- <span class="sd"> ``params['time_range']``.</span>
- <span class="sd"> Google Scholar supports a detailed search by year. Searching by *last</span>
- <span class="sd"> month* or *last week* (as offered by SearXNG) is uncommon for scientific</span>
- <span class="sd"> publications and is not supported by Google Scholar.</span>
- <span class="sd"> To limit the result list when the users selects a range, all the SearXNG</span>
- <span class="sd"> ranges (*day*, *week*, *month*, *year*) are mapped to *year*. If no range</span>
- <span class="sd"> is set an empty dictionary of arguments is returned. Example; when</span>
- <span class="sd"> user selects a time range (current year minus one in 2022):</span>
- <span class="sd"> .. code:: python</span>
- <span class="sd"> { 'as_ylo' : 2021 }</span>
- <span class="sd"> """</span>
- <span class="n">ret_val</span> <span class="o">=</span> <span class="p">{}</span>
- <span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'time_range'</span><span class="p">]</span> <span class="ow">in</span> <span class="n">time_range_dict</span><span class="p">:</span>
- <span class="n">ret_val</span><span class="p">[</span><span class="s1">'as_ylo'</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>
- <span class="k">return</span> <span class="n">ret_val</span></div>
- <div class="viewcode-block" id="detect_google_captcha">
- <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.detect_google_captcha">[docs]</a>
- <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>
- <span class="w"> </span><span class="sd">"""In case of CAPTCHA Google Scholar open its own *not a Robot* dialog and is</span>
- <span class="sd"> not redirected to ``sorry.google.com``.</span>
- <span class="sd"> """</span>
- <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">"//form[@id='gs_captcha_f']"</span><span class="p">):</span>
- <span class="k">raise</span> <span class="n">SearxEngineCaptchaException</span><span class="p">()</span></div>
- <div class="viewcode-block" id="request">
- <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.request">[docs]</a>
- <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>
- <span class="w"> </span><span class="sd">"""Google-Scholar search request"""</span>
- <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>
- <span class="c1"># subdomain is: scholar.google.xy</span>
- <span class="n">google_info</span><span class="p">[</span><span class="s1">'subdomain'</span><span class="p">]</span> <span class="o">=</span> <span class="n">google_info</span><span class="p">[</span><span class="s1">'subdomain'</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"www."</span><span class="p">,</span> <span class="s2">"scholar."</span><span class="p">)</span>
- <span class="n">args</span> <span class="o">=</span> <span class="p">{</span>
- <span class="s1">'q'</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
- <span class="o">**</span><span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">],</span>
- <span class="s1">'start'</span><span class="p">:</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">'pageno'</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>
- <span class="s1">'as_sdt'</span><span class="p">:</span> <span class="s1">'2007'</span><span class="p">,</span> <span class="c1"># include patents / to disable set '0,5'</span>
- <span class="s1">'as_vis'</span><span class="p">:</span> <span class="s1">'0'</span><span class="p">,</span> <span class="c1"># include citations / to disable set '1'</span>
- <span class="p">}</span>
- <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>
- <span class="n">params</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'https://'</span> <span class="o">+</span> <span class="n">google_info</span><span class="p">[</span><span class="s1">'subdomain'</span><span class="p">]</span> <span class="o">+</span> <span class="s1">'/scholar?'</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">(</span><span class="n">args</span><span class="p">)</span>
- <span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">]</span> <span class="o">=</span> <span class="n">google_info</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">]</span>
- <span class="n">params</span><span class="p">[</span><span class="s1">'headers'</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">'headers'</span><span class="p">])</span>
- <span class="k">return</span> <span class="n">params</span></div>
- <div class="viewcode-block" id="parse_gs_a">
- <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.parse_gs_a">[docs]</a>
- <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>
- <span class="w"> </span><span class="sd">"""Parse the text written in green.</span>
- <span class="sd"> Possible formats:</span>
- <span class="sd"> * "{authors} - {journal}, {year} - {publisher}"</span>
- <span class="sd"> * "{authors} - {year} - {publisher}"</span>
- <span class="sd"> * "{authors} - {publisher}"</span>
- <span class="sd"> """</span>
- <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">""</span><span class="p">:</span>
- <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>
- <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">' - '</span><span class="p">)</span>
- <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">', '</span><span class="p">)</span>
- <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>
- <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>
- <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>
- <span class="c1"># the format is "{authors} - {journal}, {year} - {publisher}" or "{authors} - {year} - {publisher}"</span>
- <span class="c1"># get journal and year</span>
- <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">', '</span><span class="p">)</span>
- <span class="c1"># journal is optional and may contains some coma</span>
- <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">></span> <span class="mi">1</span><span class="p">:</span>
- <span class="n">journal</span> <span class="o">=</span> <span class="s1">', '</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>
- <span class="k">if</span> <span class="n">journal</span> <span class="o">==</span> <span class="s1">'…'</span><span class="p">:</span>
- <span class="n">journal</span> <span class="o">=</span> <span class="kc">None</span>
- <span class="k">else</span><span class="p">:</span>
- <span class="n">journal</span> <span class="o">=</span> <span class="kc">None</span>
- <span class="c1"># year</span>
- <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>
- <span class="k">try</span><span class="p">:</span>
- <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">'%Y'</span><span class="p">)</span>
- <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
- <span class="n">publishedDate</span> <span class="o">=</span> <span class="kc">None</span>
- <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>
- <div class="viewcode-block" id="response">
- <a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_scholar.response">[docs]</a>
- <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>
- <span class="w"> </span><span class="sd">"""Parse response from Google Scholar"""</span>
- <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
- <span class="c1"># convert the text to dom</span>
- <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>
- <span class="n">detect_google_captcha</span><span class="p">(</span><span class="n">dom</span><span class="p">)</span>
- <span class="c1"># parse results</span>
- <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">'//div[@data-rp]'</span><span class="p">):</span>
- <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">'.//h3[1]//a'</span><span class="p">))</span>
- <span class="k">if</span> <span class="ow">not</span> <span class="n">title</span><span class="p">:</span>
- <span class="c1"># this is a [ZITATION] block</span>
- <span class="k">continue</span>
- <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">'.//span[@class="gs_ctg2"]'</span><span class="p">))</span>
- <span class="k">if</span> <span class="n">pub_type</span><span class="p">:</span>
- <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>
- <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">'.//h3[1]//a/@href'</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
- <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">'.//div[@class="gs_rs"]'</span><span class="p">))</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> <span class="o">=</span> <span class="n">parse_gs_a</span><span class="p">(</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">'.//div[@class="gs_a"]'</span><span class="p">))</span>
- <span class="p">)</span>
- <span class="k">if</span> <span class="n">publisher</span> <span class="ow">in</span> <span class="n">url</span><span class="p">:</span>
- <span class="n">publisher</span> <span class="o">=</span> <span class="kc">None</span>
- <span class="c1"># cited by</span>
- <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">'.//div[@class="gs_fl"]/a[starts-with(@href,"/scholar?cites=")]'</span><span class="p">))</span>
- <span class="c1"># link to the html or pdf document</span>
- <span class="n">html_url</span> <span class="o">=</span> <span class="kc">None</span>
- <span class="n">pdf_url</span> <span class="o">=</span> <span class="kc">None</span>
- <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">'.//div[@class="gs_or_ggsm"]/a/@href'</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>
- <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">'.//span[@class="gs_ctg2"]'</span><span class="p">))</span>
- <span class="k">if</span> <span class="n">doc_type</span> <span class="o">==</span> <span class="s2">"[PDF]"</span><span class="p">:</span>
- <span class="n">pdf_url</span> <span class="o">=</span> <span class="n">doc_url</span>
- <span class="k">else</span><span class="p">:</span>
- <span class="n">html_url</span> <span class="o">=</span> <span class="n">doc_url</span>
- <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
- <span class="p">{</span>
- <span class="s1">'template'</span><span class="p">:</span> <span class="s1">'paper.html'</span><span class="p">,</span>
- <span class="s1">'type'</span><span class="p">:</span> <span class="n">pub_type</span><span class="p">,</span>
- <span class="s1">'url'</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span>
- <span class="s1">'title'</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
- <span class="s1">'authors'</span><span class="p">:</span> <span class="n">authors</span><span class="p">,</span>
- <span class="s1">'publisher'</span><span class="p">:</span> <span class="n">publisher</span><span class="p">,</span>
- <span class="s1">'journal'</span><span class="p">:</span> <span class="n">journal</span><span class="p">,</span>
- <span class="s1">'publishedDate'</span><span class="p">:</span> <span class="n">publishedDate</span><span class="p">,</span>
- <span class="s1">'content'</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span>
- <span class="s1">'comments'</span><span class="p">:</span> <span class="n">comments</span><span class="p">,</span>
- <span class="s1">'html_url'</span><span class="p">:</span> <span class="n">html_url</span><span class="p">,</span>
- <span class="s1">'pdf_url'</span><span class="p">:</span> <span class="n">pdf_url</span><span class="p">,</span>
- <span class="p">}</span>
- <span class="p">)</span>
- <span class="c1"># parse suggestion</span>
- <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">'//div[contains(@class, "gs_qsuggest_wrap")]//li//a'</span><span class="p">):</span>
- <span class="c1"># append suggestion</span>
- <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'suggestion'</span><span class="p">:</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">suggestion</span><span class="p">)})</span>
- <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">'//div[@class="gs_r gs_pda"]/a'</span><span class="p">):</span>
- <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'correction'</span><span class="p">:</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">correction</span><span class="p">)})</span>
- <span class="k">return</span> <span class="n">results</span></div>
- </pre></div>
- <div class="clearer"></div>
- </div>
- </div>
- </div>
- <span id="sidebar-top"></span>
- <div class="sphinxsidebar" role="navigation" aria-label="Main">
- <div class="sphinxsidebarwrapper">
-
-
- <p class="logo"><a href="../../../index.html">
- <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
- </a></p>
-
- <h3><a href="../../../index.html">Table of Contents</a></h3>
- <ul>
- <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
- <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
- <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
- <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
- <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
- <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
- </ul>
- <h3>Project Links</h3>
- <ul>
- <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
-
- <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
-
- <li><a href="https://searx.space">Public instances</a>
-
- <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
- </ul><h3>Navigation</h3>
- <ul>
- <li><a href="../../../index.html">Overview</a>
- <ul>
- <li><a href="../../index.html">Module code</a>
- <ul>
- <li><a href="../engines.html">searx.engines</a>
-
-
- </ul>
- </li></ul>
- </li>
- </ul>
- </li>
- </ul>
- <search id="searchbox" style="display: none" role="search">
- <h3 id="searchlabel">Quick search</h3>
- <div class="searchformwrapper">
- <form class="search" action="../../../search.html" method="get">
- <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
- <input type="submit" value="Go" />
- </form>
- </div>
- </search>
- <script>document.getElementById('searchbox').style.display = "block"</script>
- </div>
- </div>
- <div class="clearer"></div>
- </div>
- <div class="footer" role="contentinfo">
- © Copyright SearXNG team.
- </div>
- </body>
- </html>
|