jandieman
/
searxng
mirror of https://github.com/searxng/searxng.git
2
0
Fork 0
Code Issues Projects Releases Wiki Activity
searxng/_modules/searx/engines/archlinux.html

263 lines
24 KiB
HTML
Raw Blame History

<!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.archlinux &#8212; SearXNG Documentation (2024.10.29+fa4dfd4ef)</title>
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=4f649999" />
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
<link rel="stylesheet" type="text/css" href="../../../_static/autodoc_pydantic.css" />
<script src="../../../_static/documentation_options.js?v=605fe176"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script data-project="searxng" data-version="2024.10.29+fa4dfd4ef" 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 (2024.10.29+fa4dfd4ef)</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.archlinux</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for searx.engines.archlinux</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;</span>
<span class="sd">Arch Linux Wiki</span>
<span class="sd">~~~~~~~~~~~~~~~</span>
<span class="sd">This implementation does not use a official API: Mediawiki provides API, but</span>
<span class="sd">Arch Wiki blocks access to it.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">TYPE_CHECKING</span>
<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">urlencode</span><span class="p">,</span> <span class="n">urljoin</span><span class="p">,</span> <span class="n">urlparse</span>
<span class="kn">import</span> <span class="nn">lxml</span>
<span class="kn">import</span> <span class="nn">babel</span>
<span class="kn">from</span> <span class="nn">searx.utils</span> <span class="kn">import</span> <span class="n">extract_text</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">,</span> <span class="n">eval_xpath_getindex</span>
<span class="kn">from</span> <span class="nn">searx.enginelib.traits</span> <span class="kn">import</span> <span class="n">EngineTraits</span>
<span class="kn">from</span> <span class="nn">searx.locales</span> <span class="kn">import</span> <span class="n">language_tag</span>
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
<span class="kn">import</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="n">about</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="s1">&#39;https://wiki.archlinux.org/&#39;</span><span class="p">,</span>
<span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s1">&#39;Q101445877&#39;</span><span class="p">,</span>
<span class="s2">&quot;official_api_documentation&quot;</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
<span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
<span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
<span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s1">&#39;HTML&#39;</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">&#39;it&#39;</span><span class="p">,</span> <span class="s1">&#39;software wikis&#39;</span><span class="p">]</span>
<span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">main_wiki</span> <span class="o">=</span> <span class="s1">&#39;wiki.archlinux.org&#39;</span>
<span class="k">def</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">sxng_lang</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;searxng_locale&#39;</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><span class="mi">0</span><span class="p">]</span>
<span class="n">netloc</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;wiki_netloc&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_lang</span><span class="p">,</span> <span class="n">main_wiki</span><span class="p">)</span> <span class="c1"># type: ignore</span>
<span class="n">title</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;title&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_lang</span><span class="p">,</span> <span class="s1">&#39;Special:Search&#39;</span><span class="p">)</span> <span class="c1"># type: ignore</span>
<span class="n">base_url</span> <span class="o">=</span> <span class="s1">&#39;https://&#39;</span> <span class="o">+</span> <span class="n">netloc</span> <span class="o">+</span> <span class="s1">&#39;/index.php?&#39;</span>
<span class="n">offset</span> <span class="o">=</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;pageno&#39;</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="mi">20</span>
<span class="k">if</span> <span class="n">netloc</span> <span class="o">==</span> <span class="n">main_wiki</span><span class="p">:</span>
<span class="n">eng_lang</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">get_language</span><span class="p">(</span><span class="n">sxng_lang</span><span class="p">,</span> <span class="s1">&#39;English&#39;</span><span class="p">)</span> <span class="c1"># type: ignore</span>
<span class="n">query</span> <span class="o">+=</span> <span class="s1">&#39; (&#39;</span> <span class="o">+</span> <span class="n">eng_lang</span> <span class="o">+</span> <span class="s1">&#39;)&#39;</span>
<span class="k">elif</span> <span class="n">netloc</span> <span class="o">==</span> <span class="s1">&#39;wiki.archlinuxcn.org&#39;</span><span class="p">:</span>
<span class="n">base_url</span> <span class="o">=</span> <span class="s1">&#39;https://&#39;</span> <span class="o">+</span> <span class="n">netloc</span> <span class="o">+</span> <span class="s1">&#39;/wzh/index.php?&#39;</span>
<span class="n">args</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;search&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
<span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
<span class="s1">&#39;limit&#39;</span><span class="p">:</span> <span class="mi">20</span><span class="p">,</span>
<span class="s1">&#39;offset&#39;</span><span class="p">:</span> <span class="n">offset</span><span class="p">,</span>
<span class="s1">&#39;profile&#39;</span><span class="p">:</span> <span class="s1">&#39;default&#39;</span><span class="p">,</span>
<span class="p">}</span>
<span class="n">params</span><span class="p">[</span><span class="s1">&#39;url&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">base_url</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="k">return</span> <span class="n">params</span>
<span class="k">def</span> <span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">dom</span> <span class="o">=</span> <span class="n">lxml</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="c1"># type: ignore</span>
<span class="c1"># get the base URL for the language in which request was made</span>
<span class="n">sxng_lang</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">search_params</span><span class="p">[</span><span class="s1">&#39;searxng_locale&#39;</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><span class="mi">0</span><span class="p">]</span>
<span class="n">netloc</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;wiki_netloc&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_lang</span><span class="p">,</span> <span class="n">main_wiki</span><span class="p">)</span> <span class="c1"># type: ignore</span>
<span class="n">base_url</span> <span class="o">=</span> <span class="s1">&#39;https://&#39;</span> <span class="o">+</span> <span class="n">netloc</span> <span class="o">+</span> <span class="s1">&#39;/index.php?&#39;</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">&#39;//ul[@class=&quot;mw-search-results&quot;]/li&#39;</span><span class="p">):</span>
<span class="n">link</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;mw-search-result-heading&quot;]/a&#39;</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">result</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">&#39;.//div[@class=&quot;searchresult&quot;]&#39;</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="p">{</span>
<span class="s1">&#39;url&#39;</span><span class="p">:</span> <span class="n">urljoin</span><span class="p">(</span><span class="n">base_url</span><span class="p">,</span> <span class="n">link</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;href&#39;</span><span class="p">)),</span> <span class="c1"># type: ignore</span>
<span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">link</span><span class="p">),</span>
<span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span>
<span class="p">}</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">results</span>
<div class="viewcode-block" id="fetch_traits">
<a class="viewcode-back" href="../../../dev/engines/online/archlinux.html#searx.engines.archlinux.fetch_traits">[docs]</a>
<span class="k">def</span> <span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Fetch languages from Archlinux-Wiki. The location of the Wiki address of a</span>
<span class="sd"> language is mapped in a :py:obj:`custom field</span>
<span class="sd"> &lt;searx.enginelib.traits.EngineTraits.custom&gt;` (``wiki_netloc``). Depending</span>
<span class="sd"> on the location, the ``title`` argument in the request is translated.</span>
<span class="sd"> .. code:: python</span>
<span class="sd"> &quot;custom&quot;: {</span>
<span class="sd"> &quot;wiki_netloc&quot;: {</span>
<span class="sd"> &quot;de&quot;: &quot;wiki.archlinux.de&quot;,</span>
<span class="sd"> # ...</span>
<span class="sd"> &quot;zh&quot;: &quot;wiki.archlinuxcn.org&quot;</span>
<span class="sd"> }</span>
<span class="sd"> &quot;title&quot;: {</span>
<span class="sd"> &quot;de&quot;: &quot;Spezial:Suche&quot;,</span>
<span class="sd"> # ...</span>
<span class="sd"> &quot;zh&quot;: &quot;Special:\u641c\u7d22&quot;</span>
<span class="sd"> },</span>
<span class="sd"> },</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="c1"># pylint: disable=import-outside-toplevel</span>
<span class="kn">from</span> <span class="nn">searx.network</span> <span class="kn">import</span> <span class="n">get</span> <span class="c1"># see https://github.com/searxng/searxng/issues/762</span>
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;wiki_netloc&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;title&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
<span class="n">title_map</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;de&#39;</span><span class="p">:</span> <span class="s1">&#39;Spezial:Suche&#39;</span><span class="p">,</span>
<span class="s1">&#39;fa&#39;</span><span class="p">:</span> <span class="s1">&#39;ویژه:جستجو&#39;</span><span class="p">,</span>
<span class="s1">&#39;ja&#39;</span><span class="p">:</span> <span class="s1">&#39;特別:検索&#39;</span><span class="p">,</span>
<span class="s1">&#39;zh&#39;</span><span class="p">:</span> <span class="s1">&#39;Special:搜索&#39;</span><span class="p">,</span>
<span class="p">}</span>
<span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s1">&#39;https://wiki.archlinux.org/&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">ok</span><span class="p">:</span> <span class="c1"># type: ignore</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: response from wiki.archlinux.org is not OK.&quot;</span><span class="p">)</span>
<span class="n">dom</span> <span class="o">=</span> <span class="n">lxml</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="c1"># type: ignore</span>
<span class="k">for</span> <span class="n">a</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s2">&quot;//a[@class=&#39;interlanguage-link-target&#39;]&quot;</span><span class="p">):</span>
<span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">language_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;lang&#39;</span><span class="p">),</span> <span class="n">sep</span><span class="o">=</span><span class="s1">&#39;-&#39;</span><span class="p">))</span>
<span class="c1"># zh_Hans --&gt; zh</span>
<span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">sxng_tag</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;_&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">netloc</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">a</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;href&#39;</span><span class="p">))</span><span class="o">.</span><span class="n">netloc</span>
<span class="k">if</span> <span class="n">netloc</span> <span class="o">!=</span> <span class="s1">&#39;wiki.archlinux.org&#39;</span><span class="p">:</span>
<span class="n">title</span> <span class="o">=</span> <span class="n">title_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_tag</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="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: title tag from </span><span class="si">%s</span><span class="s2"> (</span><span class="si">%s</span><span class="s2">) is unknown&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">netloc</span><span class="p">,</span> <span class="n">sxng_tag</span><span class="p">))</span>
<span class="k">continue</span>
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;wiki_netloc&#39;</span><span class="p">][</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">netloc</span>
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;title&#39;</span><span class="p">][</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">title</span> <span class="c1"># type: ignore</span>
<span class="n">eng_tag</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="s2">&quot;.//span&quot;</span><span class="p">))</span>
<span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_tag</span> <span class="c1"># type: ignore</span>
<span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="s1">&#39;en&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;English&#39;</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">
&#169; Copyright SearXNG team.
</div>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink