searxng/_modules/searx/engines/astrophysics_data_system.html

274 lines
24 KiB
HTML

<!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.astrophysics_data_system &#8212; SearXNG Documentation (2025.10.27+ea4a55fa5)</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=d52f7eb8"></script>
<script src="../../../_static/doctools.js?v=9bcbadda"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script data-project="searxng" data-version="2025.10.27+ea4a55fa5" 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 (2025.10.27+ea4a55fa5)</a> &#187;</li>
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li>
<li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">searx.engines.astrophysics_data_system</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for searx.engines.astrophysics_data_system</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
<span class="sd">&quot;&quot;&quot;The Astrophysics Data System (ADS_) is a digital library portal for</span>
<span class="sd">researchers in astronomy and physics, operated by the Smithsonian Astrophysical</span>
<span class="sd">Observatory (SAO) under a NASA grant. The ADS_ is a solr instance, but not with</span>
<span class="sd">the standard API paths.</span>
<span class="sd">.. note::</span>
<span class="sd"> The ADS_ engine requires an :py:obj:`API key &lt;api_key&gt;`.</span>
<span class="sd">This engine uses the `search/query`_ API endpoint. Since the user&#39;s search term</span>
<span class="sd">is passed through, the `search syntax`_ of ADS can be used (at least to some</span>
<span class="sd">extent).</span>
<span class="sd">.. _ADS: https://ui.adsabs.harvard.edu</span>
<span class="sd">.. _search/query: https://ui.adsabs.harvard.edu/help/api/api-docs.html#get-/search/query</span>
<span class="sd">.. _search syntax: https://ui.adsabs.harvard.edu/help/search/search-syntax</span>
<span class="sd">Configuration</span>
<span class="sd">=============</span>
<span class="sd">The engine has the following additional settings:</span>
<span class="sd">- :py:obj:`api_key`</span>
<span class="sd">- :py:obj:`ads_sort`</span>
<span class="sd">.. code:: yaml</span>
<span class="sd"> - name: astrophysics data system</span>
<span class="sd"> api_key: &quot;...&quot;</span>
<span class="sd"> inactive: false</span>
<span class="sd">Implementations</span>
<span class="sd">===============</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">import</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">t</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">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">searx.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">html_to_text</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">SearxEngineAPIException</span>
<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>
<span class="k">if</span> <span class="n">t</span><span class="o">.</span><span class="n">TYPE_CHECKING</span><span class="p">:</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.extended_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">SXNG_Response</span>
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.search.processors</span><span class="w"> </span><span class="kn">import</span> <span class="n">OnlineParams</span>
<span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="s2">&quot;https://ui.adsabs.harvard.edu/&quot;</span><span class="p">,</span>
<span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s2">&quot;Q752099&quot;</span><span class="p">,</span>
<span class="s2">&quot;official_api_documentation&quot;</span><span class="p">:</span> <span class="s2">&quot;https://ui.adsabs.harvard.edu/help/api/api-docs.html&quot;</span><span class="p">,</span>
<span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span>
<span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span>
<span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s2">&quot;JSON&quot;</span><span class="p">,</span>
<span class="p">}</span>
<span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;science&quot;</span><span class="p">,</span> <span class="s2">&quot;scientific publications&quot;</span><span class="p">]</span>
<span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">base_url</span> <span class="o">=</span> <span class="s2">&quot;https://api.adsabs.harvard.edu/v1/search/query&quot;</span>
<span class="n">api_key</span> <span class="o">=</span> <span class="s2">&quot;unset&quot;</span>
<span class="sd">&quot;&quot;&quot;Get an API token as described in https://ui.adsabs.harvard.edu/help/api&quot;&quot;&quot;</span>
<span class="n">ads_field_list</span> <span class="o">=</span> <span class="p">[</span>
<span class="s2">&quot;abstract&quot;</span><span class="p">,</span>
<span class="s2">&quot;author&quot;</span><span class="p">,</span>
<span class="s2">&quot;bibcode&quot;</span><span class="p">,</span>
<span class="s2">&quot;comment&quot;</span><span class="p">,</span>
<span class="s2">&quot;date&quot;</span><span class="p">,</span>
<span class="s2">&quot;doi&quot;</span><span class="p">,</span>
<span class="s2">&quot;isbn&quot;</span><span class="p">,</span>
<span class="s2">&quot;issn&quot;</span><span class="p">,</span>
<span class="s2">&quot;keyword&quot;</span><span class="p">,</span>
<span class="s2">&quot;page&quot;</span><span class="p">,</span>
<span class="s2">&quot;page_count&quot;</span><span class="p">,</span>
<span class="s2">&quot;page_range&quot;</span><span class="p">,</span>
<span class="s2">&quot;pub&quot;</span><span class="p">,</span>
<span class="s2">&quot;pubdate&quot;</span><span class="p">,</span>
<span class="s2">&quot;pubnote&quot;</span><span class="p">,</span>
<span class="s2">&quot;read_count&quot;</span><span class="p">,</span>
<span class="s2">&quot;title&quot;</span><span class="p">,</span>
<span class="s2">&quot;volume&quot;</span><span class="p">,</span>
<span class="s2">&quot;year&quot;</span><span class="p">,</span>
<span class="p">]</span>
<span class="sd">&quot;&quot;&quot;Set of fields to return in the response from ADS.&quot;&quot;&quot;</span>
<span class="n">ads_rows</span> <span class="o">=</span> <span class="mi">10</span>
<span class="sd">&quot;&quot;&quot;How many records to return for the ADS request.&quot;&quot;&quot;</span>
<span class="n">ads_sort</span> <span class="o">=</span> <span class="s2">&quot;read_count desc&quot;</span>
<span class="sd">&quot;&quot;&quot;The format is &#39;field&#39; + &#39;direction&#39; where direction is one of &#39;asc&#39; or &#39;desc&#39;</span>
<span class="sd">and field is any of the valid indexes.&quot;&quot;&quot;</span>
<div class="viewcode-block" id="setup">
<a class="viewcode-back" href="../../../dev/engines/online/astrophysics_data_system.html#searx.engines.astrophysics_data_system.setup">[docs]</a>
<span class="k">def</span><span class="w"> </span><span class="nf">setup</span><span class="p">(</span><span class="n">engine_settings</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="nb">bool</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initialization of the ADS_ engine, checks whether the :py:obj:`api_key`</span>
<span class="sd"> is set, otherwise the engine is inactive.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">key</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">engine_settings</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;api_key&quot;</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">key</span> <span class="ow">and</span> <span class="n">key</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">(</span><span class="s2">&quot;unset&quot;</span><span class="p">,</span> <span class="s2">&quot;unknown&quot;</span><span class="p">,</span> <span class="s2">&quot;...&quot;</span><span class="p">):</span>
<span class="k">return</span> <span class="kc">True</span>
<span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">&quot;Astrophysics Data System (ADS) API key is not set or invalid.&quot;</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">False</span></div>
<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="nb">str</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="s2">&quot;OnlineParams&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">args</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span> <span class="o">|</span> <span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;q&quot;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
<span class="s2">&quot;fl&quot;</span><span class="p">:</span> <span class="s2">&quot;,&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">ads_field_list</span><span class="p">),</span>
<span class="s2">&quot;rows&quot;</span><span class="p">:</span> <span class="n">ads_rows</span><span class="p">,</span>
<span class="s2">&quot;start&quot;</span><span class="p">:</span> <span class="n">ads_rows</span> <span class="o">*</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">&quot;pageno&quot;</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">),</span>
<span class="p">}</span>
<span class="k">if</span> <span class="n">ads_sort</span><span class="p">:</span>
<span class="n">args</span><span class="p">[</span><span class="s2">&quot;sort&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="n">ads_sort</span>
<span class="n">params</span><span class="p">[</span><span class="s2">&quot;headers&quot;</span><span class="p">][</span><span class="s2">&quot;Authorization&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;Bearer </span><span class="si">{</span><span class="n">api_key</span><span class="si">}</span><span class="s2">&quot;</span>
<span class="n">params</span><span class="p">[</span><span class="s2">&quot;url&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">base_url</span><span class="si">}</span><span class="s2">?</span><span class="si">{</span><span class="n">urlencode</span><span class="p">(</span><span class="n">args</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span>
<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="s2">&quot;SXNG_Response&quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">EngineResults</span><span class="p">:</span>
<span class="n">res</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
<span class="n">json_data</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">json</span><span class="p">()</span>
<span class="k">if</span> <span class="s2">&quot;error&quot;</span> <span class="ow">in</span> <span class="n">json_data</span><span class="p">:</span>
<span class="k">raise</span> <span class="n">SearxEngineAPIException</span><span class="p">(</span><span class="n">json_data</span><span class="p">[</span><span class="s2">&quot;error&quot;</span><span class="p">][</span><span class="s2">&quot;msg&quot;</span><span class="p">])</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_str</span><span class="p">(</span><span class="n">k</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">doc</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="s2">&quot;&quot;</span><span class="p">))</span>
<span class="k">def</span><span class="w"> </span><span class="nf">_list</span><span class="p">(</span><span class="n">k</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span>
<span class="k">return</span> <span class="n">doc</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="p">[])</span>
<span class="k">for</span> <span class="n">doc</span> <span class="ow">in</span> <span class="n">json_data</span><span class="p">[</span><span class="s2">&quot;response&quot;</span><span class="p">][</span><span class="s2">&quot;docs&quot;</span><span class="p">]:</span>
<span class="n">authors</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="n">doc</span><span class="p">[</span><span class="s2">&quot;author&quot;</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">authors</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">15</span><span class="p">:</span>
<span class="c1"># There are articles with hundreds of authors</span>
<span class="n">authors</span> <span class="o">=</span> <span class="n">authors</span><span class="p">[:</span><span class="mi">15</span><span class="p">]</span> <span class="o">+</span> <span class="p">[</span><span class="s2">&quot;et al.&quot;</span><span class="p">]</span>
<span class="n">paper</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">Paper</span><span class="p">(</span>
<span class="n">url</span><span class="o">=</span><span class="sa">f</span><span class="s2">&quot;https://ui.adsabs.harvard.edu/abs/</span><span class="si">{</span><span class="n">doc</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;bibcode&#39;</span><span class="p">)</span><span class="si">}</span><span class="s2">/&quot;</span><span class="p">,</span>
<span class="n">title</span><span class="o">=</span><span class="n">html_to_text</span><span class="p">(</span><span class="n">_list</span><span class="p">(</span><span class="s2">&quot;title&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]),</span>
<span class="n">authors</span><span class="o">=</span><span class="n">authors</span><span class="p">,</span>
<span class="n">content</span><span class="o">=</span><span class="n">html_to_text</span><span class="p">(</span><span class="n">_str</span><span class="p">(</span><span class="s2">&quot;abstract&quot;</span><span class="p">)),</span>
<span class="n">doi</span><span class="o">=</span><span class="n">_list</span><span class="p">(</span><span class="s2">&quot;doi&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">],</span>
<span class="n">issn</span><span class="o">=</span><span class="n">_list</span><span class="p">(</span><span class="s2">&quot;issn&quot;</span><span class="p">),</span>
<span class="n">isbn</span><span class="o">=</span><span class="n">_list</span><span class="p">(</span><span class="s2">&quot;isbn&quot;</span><span class="p">),</span>
<span class="n">tags</span><span class="o">=</span><span class="n">_list</span><span class="p">(</span><span class="s2">&quot;keyword&quot;</span><span class="p">),</span>
<span class="n">pages</span><span class="o">=</span><span class="s2">&quot;,&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">_list</span><span class="p">(</span><span class="s2">&quot;page&quot;</span><span class="p">)),</span>
<span class="n">publisher</span><span class="o">=</span><span class="n">_str</span><span class="p">(</span><span class="s2">&quot;pub&quot;</span><span class="p">)</span> <span class="o">+</span> <span class="s2">&quot; &quot;</span> <span class="o">+</span> <span class="n">_str</span><span class="p">(</span><span class="s2">&quot;year&quot;</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">fromisoformat</span><span class="p">(</span><span class="n">_str</span><span class="p">(</span><span class="s2">&quot;date&quot;</span><span class="p">)),</span>
<span class="n">volume</span><span class="o">=</span><span class="n">_str</span><span class="p">(</span><span class="s2">&quot;volume&quot;</span><span class="p">),</span>
<span class="n">views</span><span class="o">=</span><span class="n">_str</span><span class="p">(</span><span class="s2">&quot;read_count&quot;</span><span class="p">),</span>
<span class="n">comments</span><span class="o">=</span><span class="s2">&quot; / &quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">_list</span><span class="p">(</span><span class="s2">&quot;pubnote&quot;</span><span class="p">)),</span>
<span class="p">)</span>
<span class="n">res</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">paper</span><span class="p">)</span>
<span class="k">return</span> <span class="n">res</span>
</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">
&#169; Copyright SearXNG team.
</div>
</body>
</html>