mirror of
https://github.com/searxng/searxng.git
synced 2025-11-09 00:04:00 -05:00
248 lines
19 KiB
HTML
248 lines
19 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.reuters — 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> »</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.reuters</a></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="document">
|
|
<div class="documentwrapper">
|
|
<div class="bodywrapper">
|
|
<div class="body" role="main">
|
|
|
|
<h1>Source code for searx.engines.reuters</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
|
<span class="sd">"""Reuters_ (news) is an international news agency.</span>
|
|
|
|
<span class="sd">.. _Reuters: https://www.reuters.com</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:`sort_order`</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> - name: reuters</span>
|
|
<span class="sd"> engine: reuters</span>
|
|
<span class="sd"> shortcut: reu</span>
|
|
<span class="sd"> sort_order: "relevance"</span>
|
|
|
|
<span class="sd">Implementations</span>
|
|
<span class="sd">===============</span>
|
|
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">json</span><span class="w"> </span><span class="kn">import</span> <span class="n">dumps</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">quote_plus</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="p">,</span> <span class="n">timedelta</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">dateutil</span><span class="w"> </span><span class="kn">import</span> <span class="n">parser</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="n">about</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"website"</span><span class="p">:</span> <span class="s2">"https://www.reuters.com"</span><span class="p">,</span>
|
|
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s2">"Q130879"</span><span class="p">,</span>
|
|
<span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="kc">None</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="s2">"JSON"</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">"news"</span><span class="p">]</span>
|
|
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</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">"https://www.reuters.com"</span>
|
|
|
|
<span class="n">results_per_page</span> <span class="o">=</span> <span class="mi">20</span>
|
|
<span class="n">sort_order</span> <span class="o">=</span> <span class="s2">"relevance"</span>
|
|
<span class="sd">"""Sort order, one of ``relevance``, ``display_date:desc`` or ``display_data:asc``."""</span>
|
|
|
|
<span class="n">time_range_duration_map</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"day"</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span>
|
|
<span class="s2">"week"</span><span class="p">:</span> <span class="mi">7</span><span class="p">,</span>
|
|
<span class="s2">"month"</span><span class="p">:</span> <span class="mi">30</span><span class="p">,</span>
|
|
<span class="s2">"year"</span><span class="p">:</span> <span class="mi">365</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
|
|
<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="n">args</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"keyword"</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
|
|
<span class="s2">"offset"</span><span class="p">:</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"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="n">results_per_page</span><span class="p">,</span>
|
|
<span class="s2">"orderby"</span><span class="p">:</span> <span class="n">sort_order</span><span class="p">,</span>
|
|
<span class="s2">"size"</span><span class="p">:</span> <span class="n">results_per_page</span><span class="p">,</span>
|
|
<span class="s2">"website"</span><span class="p">:</span> <span class="s2">"reuters"</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s2">"time_range"</span><span class="p">]:</span>
|
|
<span class="n">time_diff_days</span> <span class="o">=</span> <span class="n">time_range_duration_map</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s2">"time_range"</span><span class="p">]]</span>
|
|
<span class="n">start_date</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">timedelta</span><span class="p">(</span><span class="n">days</span><span class="o">=</span><span class="n">time_diff_days</span><span class="p">)</span>
|
|
<span class="n">args</span><span class="p">[</span><span class="s2">"start_date"</span><span class="p">]</span> <span class="o">=</span> <span class="n">start_date</span><span class="o">.</span><span class="n">isoformat</span><span class="p">()</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"url"</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">base_url</span><span class="si">}</span><span class="s2">/pf/api/v3/content/fetch/articles-by-search-v2?query=</span><span class="si">{</span><span class="n">quote_plus</span><span class="p">(</span><span class="n">dumps</span><span class="p">(</span><span class="n">args</span><span class="p">))</span><span class="si">}</span><span class="s2">"</span>
|
|
<span class="k">return</span> <span class="n">params</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="o">-></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">resp_json</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="ow">not</span> <span class="n">resp_json</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"result"</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="n">res</span>
|
|
|
|
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">resp_json</span><span class="p">[</span><span class="s2">"result"</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"articles"</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">res</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">MainResult</span><span class="p">(</span>
|
|
<span class="n">url</span><span class="o">=</span><span class="n">base_url</span> <span class="o">+</span> <span class="n">result</span><span class="p">[</span><span class="s2">"canonical_url"</span><span class="p">],</span>
|
|
<span class="n">title</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"web"</span><span class="p">],</span>
|
|
<span class="n">content</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"description"</span><span class="p">],</span>
|
|
<span class="n">thumbnail</span><span class="o">=</span><span class="n">resize_url</span><span class="p">(</span><span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"thumbnail"</span><span class="p">,</span> <span class="p">{}),</span> <span class="n">height</span><span class="o">=</span><span class="mi">80</span><span class="p">),</span>
|
|
<span class="n">metadata</span><span class="o">=</span><span class="n">result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"kicker"</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"name"</span><span class="p">),</span>
|
|
<span class="n">publishedDate</span><span class="o">=</span><span class="n">parser</span><span class="o">.</span><span class="n">isoparse</span><span class="p">(</span><span class="n">result</span><span class="p">[</span><span class="s2">"display_time"</span><span class="p">]),</span>
|
|
<span class="p">)</span>
|
|
<span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">res</span>
|
|
|
|
|
|
<div class="viewcode-block" id="resize_url">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/reuters.html#searx.engines.reuters.resize_url">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">resize_url</span><span class="p">(</span><span class="n">thumbnail</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="p">],</span> <span class="n">width</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">height</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">"""Generates a URL for Reuter's thumbnail with the dimensions *width* and</span>
|
|
<span class="sd"> *height*. If no URL can be generated from the *thumbnail data*, an empty</span>
|
|
<span class="sd"> string will be returned.</span>
|
|
|
|
<span class="sd"> width: default is *unset* (``0``)</span>
|
|
<span class="sd"> Image width in pixels (negative values are ignored). If only width is</span>
|
|
<span class="sd"> specified, the height matches the original aspect ratio.</span>
|
|
|
|
<span class="sd"> height: default is *unset* (``0``)</span>
|
|
<span class="sd"> Image height in pixels (negative values are ignored). If only height is</span>
|
|
<span class="sd"> specified, the width matches the original aspect ratio.</span>
|
|
|
|
<span class="sd"> The file size of a full-size image is usually several MB; when reduced to a</span>
|
|
<span class="sd"> height of, for example, 80 points, only a few KB remain!</span>
|
|
|
|
<span class="sd"> Fields of the *thumbnail data* (``result.articles.[<int>].thumbnail``):</span>
|
|
|
|
<span class="sd"> thumbnail.url:</span>
|
|
<span class="sd"> Is a full-size image (>MB).</span>
|
|
|
|
<span class="sd"> thumbnail.width & .height:</span>
|
|
<span class="sd"> Dimensions of the full-size image.</span>
|
|
|
|
<span class="sd"> thumbnail.resizer_url:</span>
|
|
<span class="sd"> Reuters has a *resizer* `REST-API for the images`_, this is the URL of the</span>
|
|
<span class="sd"> service. This URL includes the ``&auth`` argument, other arguments are</span>
|
|
<span class="sd"> ``&width=<int>`` and ``&height=<int>``.</span>
|
|
|
|
<span class="sd"> .. _REST-API for the images:</span>
|
|
<span class="sd"> https://dev.arcxp.com/photo-center/image-resizer/resizer-v2-how-to-transform-images/#query-parameters</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="n">url</span> <span class="o">=</span> <span class="n">thumbnail</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"resizer_url"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">url</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="s2">""</span>
|
|
<span class="k">if</span> <span class="nb">int</span><span class="p">(</span><span class="n">width</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="n">url</span> <span class="o">+=</span> <span class="sa">f</span><span class="s2">"&width=</span><span class="si">{</span><span class="nb">int</span><span class="p">(</span><span class="n">width</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span>
|
|
<span class="k">if</span> <span class="nb">int</span><span class="p">(</span><span class="n">height</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="n">url</span> <span class="o">+=</span> <span class="sa">f</span><span class="s2">"&height=</span><span class="si">{</span><span class="nb">int</span><span class="p">(</span><span class="n">height</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span>
|
|
<span class="k">return</span> <span class="n">url</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> |