mirror of
https://github.com/searxng/searxng.git
synced 2026-05-11 05:25:46 +02:00
inetol
801 lines
74 KiB
HTML
801 lines
74 KiB
HTML
<!doctype html>
|
||
<html class="no-js" lang="en" data-content_root="../../../">
|
||
<head><meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width,initial-scale=1">
|
||
<meta name="color-scheme" content="light dark"><link rel="index" title="Index" href="../../../genindex.html"><link rel="search" title="Search" href="../../../search.html">
|
||
<link rel="prefetch" href="../../../_static/searxng-wordmark.svg" as="image">
|
||
|
||
<!-- Generated with Sphinx 9.1.0 and Furo 2025.12.19 -->
|
||
<title>searx.engines.wikipedia - SearXNG Documentation (2026.5.10+df1f24fb7)</title>
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=d111a655" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/styles/furo.css?v=7bdb33bb" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/styles/furo-extensions.css?v=8dab3a3b" />
|
||
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=4b1b1f10" />
|
||
|
||
|
||
|
||
|
||
<style>
|
||
body {
|
||
--color-code-background: #f2f2f2;
|
||
--color-code-foreground: #1e1e1e;
|
||
|
||
}
|
||
@media not print {
|
||
body[data-theme="dark"] {
|
||
--color-code-background: #202020;
|
||
--color-code-foreground: #d0d0d0;
|
||
|
||
}
|
||
@media (prefers-color-scheme: dark) {
|
||
body:not([data-theme="light"]) {
|
||
--color-code-background: #202020;
|
||
--color-code-foreground: #d0d0d0;
|
||
|
||
}
|
||
}
|
||
}
|
||
</style></head>
|
||
<body>
|
||
|
||
<script>
|
||
document.body.dataset.theme = localStorage.getItem("theme") || "auto";
|
||
</script>
|
||
|
||
|
||
<svg xmlns="http://www.w3.org/2000/svg" style="display: none;">
|
||
<symbol id="svg-toc" viewBox="0 0 24 24">
|
||
<title>Contents</title>
|
||
<svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 1024 1024">
|
||
<path d="M408 442h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8zm-8 204c0 4.4 3.6 8 8 8h480c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8H408c-4.4 0-8 3.6-8 8v56zm504-486H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zm0 632H120c-4.4 0-8 3.6-8 8v56c0 4.4 3.6 8 8 8h784c4.4 0 8-3.6 8-8v-56c0-4.4-3.6-8-8-8zM115.4 518.9L271.7 642c5.8 4.6 14.4.5 14.4-6.9V388.9c0-7.4-8.5-11.5-14.4-6.9L115.4 505.1a8.74 8.74 0 0 0 0 13.8z"/>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-menu" viewBox="0 0 24 24">
|
||
<title>Menu</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-menu">
|
||
<line x1="3" y1="12" x2="21" y2="12"></line>
|
||
<line x1="3" y1="6" x2="21" y2="6"></line>
|
||
<line x1="3" y1="18" x2="21" y2="18"></line>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-arrow-right" viewBox="0 0 24 24">
|
||
<title>Expand</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather-chevron-right">
|
||
<polyline points="9 18 15 12 9 6"></polyline>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-sun" viewBox="0 0 24 24">
|
||
<title>Light mode</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="feather-sun">
|
||
<circle cx="12" cy="12" r="5"></circle>
|
||
<line x1="12" y1="1" x2="12" y2="3"></line>
|
||
<line x1="12" y1="21" x2="12" y2="23"></line>
|
||
<line x1="4.22" y1="4.22" x2="5.64" y2="5.64"></line>
|
||
<line x1="18.36" y1="18.36" x2="19.78" y2="19.78"></line>
|
||
<line x1="1" y1="12" x2="3" y2="12"></line>
|
||
<line x1="21" y1="12" x2="23" y2="12"></line>
|
||
<line x1="4.22" y1="19.78" x2="5.64" y2="18.36"></line>
|
||
<line x1="18.36" y1="5.64" x2="19.78" y2="4.22"></line>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-moon" viewBox="0 0 24 24">
|
||
<title>Dark mode</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-moon">
|
||
<path stroke="none" d="M0 0h24v24H0z" fill="none" />
|
||
<path d="M12 3c.132 0 .263 0 .393 0a7.5 7.5 0 0 0 7.92 12.446a9 9 0 1 1 -8.313 -12.454z" />
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-sun-with-moon" viewBox="0 0 24 24">
|
||
<title>Auto light/dark, in light mode</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1" stroke-linecap="round" stroke-linejoin="round"
|
||
class="icon-custom-derived-from-feather-sun-and-tabler-moon">
|
||
<path style="opacity: 50%" d="M 5.411 14.504 C 5.471 14.504 5.532 14.504 5.591 14.504 C 3.639 16.319 4.383 19.569 6.931 20.352 C 7.693 20.586 8.512 20.551 9.25 20.252 C 8.023 23.207 4.056 23.725 2.11 21.184 C 0.166 18.642 1.702 14.949 4.874 14.536 C 5.051 14.512 5.231 14.5 5.411 14.5 L 5.411 14.504 Z"/>
|
||
<line x1="14.5" y1="3.25" x2="14.5" y2="1.25"/>
|
||
<line x1="14.5" y1="15.85" x2="14.5" y2="17.85"/>
|
||
<line x1="10.044" y1="5.094" x2="8.63" y2="3.68"/>
|
||
<line x1="19" y1="14.05" x2="20.414" y2="15.464"/>
|
||
<line x1="8.2" y1="9.55" x2="6.2" y2="9.55"/>
|
||
<line x1="20.8" y1="9.55" x2="22.8" y2="9.55"/>
|
||
<line x1="10.044" y1="14.006" x2="8.63" y2="15.42"/>
|
||
<line x1="19" y1="5.05" x2="20.414" y2="3.636"/>
|
||
<circle cx="14.5" cy="9.55" r="3.6"/>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-moon-with-sun" viewBox="0 0 24 24">
|
||
<title>Auto light/dark, in dark mode</title>
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1" stroke-linecap="round" stroke-linejoin="round"
|
||
class="icon-custom-derived-from-feather-sun-and-tabler-moon">
|
||
<path d="M 8.282 7.007 C 8.385 7.007 8.494 7.007 8.595 7.007 C 5.18 10.184 6.481 15.869 10.942 17.24 C 12.275 17.648 13.706 17.589 15 17.066 C 12.851 22.236 5.91 23.143 2.505 18.696 C -0.897 14.249 1.791 7.786 7.342 7.063 C 7.652 7.021 7.965 7 8.282 7 L 8.282 7.007 Z"/>
|
||
<line style="opacity: 50%" x1="18" y1="3.705" x2="18" y2="2.5"/>
|
||
<line style="opacity: 50%" x1="18" y1="11.295" x2="18" y2="12.5"/>
|
||
<line style="opacity: 50%" x1="15.316" y1="4.816" x2="14.464" y2="3.964"/>
|
||
<line style="opacity: 50%" x1="20.711" y1="10.212" x2="21.563" y2="11.063"/>
|
||
<line style="opacity: 50%" x1="14.205" y1="7.5" x2="13.001" y2="7.5"/>
|
||
<line style="opacity: 50%" x1="21.795" y1="7.5" x2="23" y2="7.5"/>
|
||
<line style="opacity: 50%" x1="15.316" y1="10.184" x2="14.464" y2="11.036"/>
|
||
<line style="opacity: 50%" x1="20.711" y1="4.789" x2="21.563" y2="3.937"/>
|
||
<circle style="opacity: 50%" cx="18" cy="7.5" r="2.169"/>
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-pencil" viewBox="0 0 24 24">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-pencil-code">
|
||
<path d="M4 20h4l10.5 -10.5a2.828 2.828 0 1 0 -4 -4l-10.5 10.5v4" />
|
||
<path d="M13.5 6.5l4 4" />
|
||
<path d="M20 21l2 -2l-2 -2" />
|
||
<path d="M17 17l-2 2l2 2" />
|
||
</svg>
|
||
</symbol>
|
||
<symbol id="svg-eye" viewBox="0 0 24 24">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="none" stroke="currentColor"
|
||
stroke-width="1" stroke-linecap="round" stroke-linejoin="round" class="icon-tabler-eye-code">
|
||
<path stroke="none" d="M0 0h24v24H0z" fill="none" />
|
||
<path d="M10 12a2 2 0 1 0 4 0a2 2 0 0 0 -4 0" />
|
||
<path
|
||
d="M11.11 17.958c-3.209 -.307 -5.91 -2.293 -8.11 -5.958c2.4 -4 5.4 -6 9 -6c3.6 0 6.6 2 9 6c-.21 .352 -.427 .688 -.647 1.008" />
|
||
<path d="M20 21l2 -2l-2 -2" />
|
||
<path d="M17 17l-2 2l2 2" />
|
||
</svg>
|
||
</symbol>
|
||
</svg>
|
||
|
||
<input type="checkbox" class="sidebar-toggle" name="__navigation" id="__navigation" aria-label="Toggle site navigation sidebar">
|
||
<input type="checkbox" class="sidebar-toggle" name="__toc" id="__toc" aria-label="Toggle table of contents sidebar">
|
||
<label class="overlay sidebar-overlay" for="__navigation"></label>
|
||
<label class="overlay toc-overlay" for="__toc"></label>
|
||
|
||
<a class="skip-to-content muted-link" href="#furo-main-content">Skip to content</a>
|
||
|
||
|
||
|
||
<div class="page">
|
||
<header class="mobile-header">
|
||
<div class="header-left">
|
||
<label class="nav-overlay-icon" for="__navigation">
|
||
<span class="icon"><svg><use href="#svg-menu"></use></svg></span>
|
||
</label>
|
||
</div>
|
||
<div class="header-center">
|
||
<a href="../../../index.html"><div class="brand">SearXNG Documentation (2026.5.10+df1f24fb7)</div></a>
|
||
</div>
|
||
<div class="header-right">
|
||
<div class="theme-toggle-container theme-toggle-header">
|
||
<button class="theme-toggle" aria-label="Toggle Light / Dark / Auto color theme">
|
||
<svg class="theme-icon-when-auto-light"><use href="#svg-sun-with-moon"></use></svg>
|
||
<svg class="theme-icon-when-auto-dark"><use href="#svg-moon-with-sun"></use></svg>
|
||
<svg class="theme-icon-when-dark"><use href="#svg-moon"></use></svg>
|
||
<svg class="theme-icon-when-light"><use href="#svg-sun"></use></svg>
|
||
</button>
|
||
</div>
|
||
<label class="toc-overlay-icon toc-header-icon no-toc" for="__toc">
|
||
<span class="icon"><svg><use href="#svg-toc"></use></svg></span>
|
||
</label>
|
||
</div>
|
||
</header>
|
||
<aside class="sidebar-drawer">
|
||
<div class="sidebar-container">
|
||
|
||
<div class="sidebar-sticky"><div class="sidebar-scroll"><a class="sidebar-brand" href="../../../index.html">
|
||
<div class="sidebar-logo-container">
|
||
<img class="sidebar-logo" src="../../../_static/searxng-wordmark.svg" alt="Logo"/>
|
||
</div>
|
||
|
||
<span class="sidebar-brand-text">SearXNG Documentation (2026.5.10+df1f24fb7)</span>
|
||
|
||
</a><form class="sidebar-search-container" method="get" action="../../../search.html" role="search">
|
||
<input class="sidebar-search" placeholder="Search" name="q" aria-label="Search">
|
||
<input type="hidden" name="check_keywords" value="yes">
|
||
<input type="hidden" name="area" value="default">
|
||
</form>
|
||
<div id="searchbox"></div><div class="sidebar-tree">
|
||
<ul>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../user/index.html">User information</a><input aria-label="Toggle navigation of User information" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" role="switch" type="checkbox"/><label for="toctree-checkbox-1"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../user/search-syntax.html">Search syntax</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../user/configured_engines.html">Configured Engines</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../user/about.html">About SearXNG</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a><input aria-label="Toggle navigation of Administrator documentation" class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" role="switch" type="checkbox"/><label for="toctree-checkbox-2"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l2 has-children"><a class="reference internal" href="../../../admin/settings/index.html">Settings</a><input aria-label="Toggle navigation of Settings" class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" role="switch" type="checkbox"/><label for="toctree-checkbox-3"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings.html"><code class="docutils literal notranslate"><span class="pre">settings.yml</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_engines.html"><code class="docutils literal notranslate"><span class="pre">engines:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_brand.html"><code class="docutils literal notranslate"><span class="pre">brand:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_general.html"><code class="docutils literal notranslate"><span class="pre">general:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_search.html"><code class="docutils literal notranslate"><span class="pre">search:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_server.html"><code class="docutils literal notranslate"><span class="pre">server:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_ui.html"><code class="docutils literal notranslate"><span class="pre">ui:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_redis.html"><code class="docutils literal notranslate"><span class="pre">redis:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_valkey.html"><code class="docutils literal notranslate"><span class="pre">valkey:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_outgoing.html"><code class="docutils literal notranslate"><span class="pre">outgoing:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_categories_as_tabs.html"><code class="docutils literal notranslate"><span class="pre">categories_as_tabs:</span></code></a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../admin/settings/settings_plugins.html"><code class="docutils literal notranslate"><span class="pre">plugins:</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation.html">Installation</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation-docker.html">Installation container</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation-scripts.html">Installation Script</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation-searxng.html">Step by step installation</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation-granian.html">Granian</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation-uwsgi.html">uWSGI</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation-nginx.html">NGINX</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/installation-apache.html">Apache</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/update-searxng.html">SearXNG maintenance</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/answer-captcha.html">Answer CAPTCHA from server’s IP</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/searx.favicons.html">Favicons</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/searx.limiter.html">Limiter</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/api.html">Administration API</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/architecture.html">Architecture</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/plugins.html">List of plugins</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../admin/buildhosts.html">Buildhosts</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a><input aria-label="Toggle navigation of Developer documentation" class="toctree-checkbox" id="toctree-checkbox-4" name="toctree-checkbox-4" role="switch" type="checkbox"/><label for="toctree-checkbox-4"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/quickstart.html">Development Quickstart</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/commits.html">Git Commits & Change Management</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/contribution_guide.html">How to contribute</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/extended_types.html">Extended Types</a></li>
|
||
<li class="toctree-l2 has-children"><a class="reference internal" href="../../../dev/engines/index.html">Engine Implementations</a><input aria-label="Toggle navigation of Engine Implementations" class="toctree-checkbox" id="toctree-checkbox-5" name="toctree-checkbox-5" role="switch" type="checkbox"/><label for="toctree-checkbox-5"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/enginelib.html">Engine Library</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/engines.html">SearXNG’s engines loader</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/engine_overview.html">Engine Overview</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/demo/demo_online.html">Demo Online Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/xpath.html">XPath Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/mediawiki.html">MediaWiki Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/json_engine.html">JSON Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/adobe_stock.html">Adobe Stock</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/alpinelinux.html">Alpine Linux Packages</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/annas_archive.html">Anna’s Archive</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/aol.html">AOL</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/archlinux.html">Arch Linux</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/arxiv.html">arXiv</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/astrophysics_data_system.html">Astrophysics Data System (ADS)</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/azure.html">Azure Resources</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/bing.html">Bing Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/bpb.html">Bpb</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/brave.html">Brave Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/bt4g.html">BT4G</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/chinaso.html">ChinaSo</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/core.html">CORE</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/crossref.html">Crossref</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/dailymotion.html">Dailymotion</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/discourse.html">Discourse Forums</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/duckduckgo.html">DuckDuckGo Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/geizhals.html">Geizhals</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/gitea.html">Gitea</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/github_code.html">Github Code</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/gitlab.html">GitLab</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/google.html">Google Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/huggingface.html">Hugging Face</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/karmasearch.html">Karmasearch</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/lemmy.html">Lemmy</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/loc.html">Library of Congress</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/marginalia.html">Marginalia Search</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/mastodon.html">Mastodon</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/moviepilot.html">Moviepilot</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/mrs.html">Matrix Rooms Search (MRS)</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/mwmbl.html">Mwmbl Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/odysee.html">Odysee</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/openalex.html">OpenAlex</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/openlibrary.html">Open Library</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/peertube.html">Peertube Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/piped.html">Piped</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/presearch.html">Presearch Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/pubmed.html">PubMed</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/qwant.html">Qwant</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/radio_browser.html">RadioBrowser</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/recoll.html">Recoll Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/repology.html">Repology</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/reuters.html">Reuters</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/semantic_scholar.html">Semantic Scholar</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/soundcloud.html">Soundcloud</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/sourcehut.html">Sourcehut</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/springer.html">Springer Nature</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/startpage.html">Startpage Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/tagesschau.html">Tagesschau API</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/torznab.html">Torznab WebAPI</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/tubearchivist.html">Tube Archivist</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/void.html">Void Linux binary packages</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/wallhaven.html">Wallhaven</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/wikipedia.html">Wikimedia</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/yacy.html">Yacy</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/yahoo.html">Yahoo Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online/zlibrary.html">Z-Library</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/offline_concept.html">Offline Concept</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/demo/demo_offline.html">Demo Offline Engine</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/offline/command-line-engines.html">Command Line Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/offline/nosql-engines.html">NoSQL databases</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/offline/search-indexer-engines.html">Local Search APIs</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/offline/sql-engines.html">SQL Engines</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/engines/online_url_search/tineye.html">Tineye</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2 has-children"><a class="reference internal" href="../../../dev/result_types/index.html">Result Types</a><input aria-label="Toggle navigation of Result Types" class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" role="switch" type="checkbox"/><label for="toctree-checkbox-6"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/result_types/base_result.html">Result</a></li>
|
||
<li class="toctree-l3 has-children"><a class="reference internal" href="../../../dev/result_types/main_result.html">Main Search Results</a><input aria-label="Toggle navigation of Main Search Results" class="toctree-checkbox" id="toctree-checkbox-7" name="toctree-checkbox-7" role="switch" type="checkbox"/><label for="toctree-checkbox-7"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/result_types/main/mainresult.html"><code class="docutils literal notranslate"><span class="pre">MainResult</span></code></a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/result_types/main/keyvalue.html">Key-Value Results</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/result_types/main/code.html">Code Results</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/result_types/main/paper.html">Paper Results</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/result_types/main/file.html">File Results</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/result_types/answer.html">Answer Results</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/result_types/correction.html">Correction Results</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/result_types/suggestion.html">Suggestion Results</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/result_types/infobox.html">Infobox Results</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/templates.html">Simple Theme Templates</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/search_api.html">Search API</a></li>
|
||
<li class="toctree-l2 has-children"><a class="reference internal" href="../../../dev/plugins/index.html">Plugins</a><input aria-label="Toggle navigation of Plugins" class="toctree-checkbox" id="toctree-checkbox-8" name="toctree-checkbox-8" role="switch" type="checkbox"/><label for="toctree-checkbox-8"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/plugins/development.html">Plugin Development</a></li>
|
||
<li class="toctree-l3 has-children"><a class="reference internal" href="../../../dev/plugins/builtins.html">Built-in Plugins</a><input aria-label="Toggle navigation of Built-in Plugins" class="toctree-checkbox" id="toctree-checkbox-9" name="toctree-checkbox-9" role="switch" type="checkbox"/><label for="toctree-checkbox-9"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/calculator.html">Calculator</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/hash_plugin.html">Hash Values</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/hostnames.html">Hostnames</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/infinite_scroll.html">Infinite scroll</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/self_info.html">Self-Info</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/tor_check.html">Tor check</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/unit_converter.html">Unit Converter</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/plugins/time_zone.html">Time Zone</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2 has-children"><a class="reference internal" href="../../../dev/answerers/index.html">Answerers</a><input aria-label="Toggle navigation of Answerers" class="toctree-checkbox" id="toctree-checkbox-10" name="toctree-checkbox-10" role="switch" type="checkbox"/><label for="toctree-checkbox-10"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/answerers/development.html">Answerer Development</a></li>
|
||
<li class="toctree-l3 has-children"><a class="reference internal" href="../../../dev/answerers/builtins.html">Built-in Answerers</a><input aria-label="Toggle navigation of Built-in Answerers" class="toctree-checkbox" id="toctree-checkbox-11" name="toctree-checkbox-11" role="switch" type="checkbox"/><label for="toctree-checkbox-11"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/answerers/random.html">Random</a></li>
|
||
<li class="toctree-l4"><a class="reference internal" href="../../../dev/answerers/statistics.html">Statistics</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/translation.html">Translation</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/makefile.html">Makefile & <code class="docutils literal notranslate"><span class="pre">./manage</span></code></a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../dev/reST.html">reST primer</a></li>
|
||
<li class="toctree-l2 has-children"><a class="reference internal" href="../../../dev/searxng_extra/index.html">Tooling box <code class="docutils literal notranslate"><span class="pre">searxng_extra</span></code></a><input aria-label="Toggle navigation of Tooling box searxng_extra" class="toctree-checkbox" id="toctree-checkbox-12" name="toctree-checkbox-12" role="switch" type="checkbox"/><label for="toctree-checkbox-12"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="../../../dev/searxng_extra/update.html"><code class="docutils literal notranslate"><span class="pre">searxng_extra/update/</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a><input aria-label="Toggle navigation of DevOps tooling box" class="toctree-checkbox" id="toctree-checkbox-13" name="toctree-checkbox-13" role="switch" type="checkbox"/><label for="toctree-checkbox-13"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../utils/searxng.sh.html"><code class="docutils literal notranslate"><span class="pre">utils/searxng.sh</span></code></a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../src/index.html">Source-Code</a><input aria-label="Toggle navigation of Source-Code" class="toctree-checkbox" id="toctree-checkbox-14" name="toctree-checkbox-14" role="switch" type="checkbox"/><label for="toctree-checkbox-14"><span class="icon"><svg><use href="#svg-arrow-right"></use></svg></span></label><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.babel_extract.html">Custom message extractor (i18n)</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.botdetection.html">Bot Detection</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.cache.html">Caches</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.exceptions.html">SearXNG Exceptions</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.favicons.html">Favicons (source)</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.infopage.html">Online <code class="docutils literal notranslate"><span class="pre">/info</span></code></a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.locales.html">Locales</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.search.html">Search</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.search.processors.html">Search processors</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.settings.html">Settings Loader</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.sqlitedb.html">SQLite DB</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.utils.html">Utility functions for the engines</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.valkeydb.html">Valkey DB</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.valkeylib.html">Valkey Library</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../../../src/searx.weather.html">Weather</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
</div>
|
||
</aside>
|
||
<div class="main">
|
||
<div class="content">
|
||
<div class="article-container">
|
||
<a href="#" class="back-to-top muted-link">
|
||
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
|
||
<path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8v12z"></path>
|
||
</svg>
|
||
<span>Back to top</span>
|
||
</a>
|
||
<div class="content-icon-container">
|
||
<div class="theme-toggle-container theme-toggle-content">
|
||
<button class="theme-toggle" aria-label="Toggle Light / Dark / Auto color theme">
|
||
<svg class="theme-icon-when-auto-light"><use href="#svg-sun-with-moon"></use></svg>
|
||
<svg class="theme-icon-when-auto-dark"><use href="#svg-moon-with-sun"></use></svg>
|
||
<svg class="theme-icon-when-dark"><use href="#svg-moon"></use></svg>
|
||
<svg class="theme-icon-when-light"><use href="#svg-sun"></use></svg>
|
||
</button>
|
||
</div>
|
||
<label class="toc-overlay-icon toc-content-icon no-toc" for="__toc">
|
||
<span class="icon"><svg><use href="#svg-toc"></use></svg></span>
|
||
</label>
|
||
</div>
|
||
<article role="main" id="furo-main-content">
|
||
<h1>Source code for searx.engines.wikipedia</h1><div class="highlight"><pre>
|
||
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
||
<span class="sd">"""This module implements the Wikipedia engine. Some of this implementations</span>
|
||
<span class="sd">are shared by other engines:</span>
|
||
|
||
<span class="sd">- :ref:`wikidata engine`</span>
|
||
|
||
<span class="sd">The list of supported languages is :py:obj:`fetched <fetch_wikimedia_traits>` from</span>
|
||
<span class="sd">the article linked by :py:obj:`list_of_wikipedias`.</span>
|
||
|
||
<span class="sd">Unlike traditional search engines, wikipedia does not support one Wikipedia for</span>
|
||
<span class="sd">all languages, but there is one Wikipedia for each supported language. Some of</span>
|
||
<span class="sd">these Wikipedias have a LanguageConverter_ enabled</span>
|
||
<span class="sd">(:py:obj:`rest_v1_summary_url`).</span>
|
||
|
||
<span class="sd">A LanguageConverter_ (LC) is a system based on language variants that</span>
|
||
<span class="sd">automatically converts the content of a page into a different variant. A variant</span>
|
||
<span class="sd">is mostly the same language in a different script.</span>
|
||
|
||
<span class="sd">- `Wikipedias in multiple writing systems`_</span>
|
||
<span class="sd">- `Automatic conversion between traditional and simplified Chinese characters`_</span>
|
||
|
||
<span class="sd">PR-2554_:</span>
|
||
<span class="sd"> The Wikipedia link returned by the API is still the same in all cases</span>
|
||
<span class="sd"> (`https://zh.wikipedia.org/wiki/出租車`_) but if your browser's</span>
|
||
<span class="sd"> ``Accept-Language`` is set to any of ``zh``, ``zh-CN``, ``zh-TW``, ``zh-HK``</span>
|
||
<span class="sd"> or .. Wikipedia's LC automatically returns the desired script in their</span>
|
||
<span class="sd"> web-page.</span>
|
||
|
||
<span class="sd"> - You can test the API here: https://reqbin.com/gesg2kvx</span>
|
||
|
||
<span class="sd">.. _https://zh.wikipedia.org/wiki/出租車:</span>
|
||
<span class="sd"> https://zh.wikipedia.org/wiki/%E5%87%BA%E7%A7%9F%E8%BB%8A</span>
|
||
|
||
<span class="sd">To support Wikipedia's LanguageConverter_, a SearXNG request to Wikipedia uses</span>
|
||
<span class="sd">:py:obj:`get_wiki_params` and :py:obj:`wiki_lc_locale_variants' in the</span>
|
||
<span class="sd">:py:obj:`fetch_wikimedia_traits` function.</span>
|
||
|
||
<span class="sd">To test in SearXNG, query for ``!wp 出租車`` with each of the available Chinese</span>
|
||
<span class="sd">options:</span>
|
||
|
||
<span class="sd">- ``!wp 出租車 :zh`` should show 出租車</span>
|
||
<span class="sd">- ``!wp 出租車 :zh-CN`` should show 出租车</span>
|
||
<span class="sd">- ``!wp 出租車 :zh-TW`` should show 計程車</span>
|
||
<span class="sd">- ``!wp 出租車 :zh-HK`` should show 的士</span>
|
||
<span class="sd">- ``!wp 出租車 :zh-SG`` should show 德士</span>
|
||
|
||
<span class="sd">.. _LanguageConverter:</span>
|
||
<span class="sd"> https://www.mediawiki.org/wiki/Writing_systems#LanguageConverter</span>
|
||
<span class="sd">.. _Wikipedias in multiple writing systems:</span>
|
||
<span class="sd"> https://meta.wikimedia.org/wiki/Wikipedias_in_multiple_writing_systems</span>
|
||
<span class="sd">.. _Automatic conversion between traditional and simplified Chinese characters:</span>
|
||
<span class="sd"> https://en.wikipedia.org/wiki/Chinese_Wikipedia#Automatic_conversion_between_traditional_and_simplified_Chinese_characters</span>
|
||
<span class="sd">.. _PR-2554: https://github.com/searx/searx/pull/2554</span>
|
||
|
||
<span class="sd">"""</span>
|
||
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">urllib.parse</span>
|
||
|
||
<span class="kn">import</span><span class="w"> </span><span class="nn">babel</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</span><span class="w"> </span><span class="kn">import</span> <span class="n">locales</span><span class="p">,</span> <span class="n">utils</span>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">searx</span><span class="w"> </span><span class="kn">import</span> <span class="n">network</span> <span class="k">as</span> <span class="n">_network</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="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="s2">"https://www.wikipedia.org/"</span><span class="p">,</span>
|
||
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s2">"Q52"</span><span class="p">,</span>
|
||
<span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="s2">"https://en.wikipedia.org/api/"</span><span class="p">,</span>
|
||
<span class="s2">"use_official_api"</span><span class="p">:</span> <span class="kc">True</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">display_type</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"infobox"</span><span class="p">]</span>
|
||
<span class="sd">"""A list of display types composed from ``infobox`` and ``list``. The latter</span>
|
||
<span class="sd">one will add a hit to the result list. The first one will show a hit in the</span>
|
||
<span class="sd">info box. Both values can be set, or one of the two can be set."""</span>
|
||
|
||
<span class="n">list_of_wikipedias</span> <span class="o">=</span> <span class="s2">"https://meta.wikimedia.org/wiki/List_of_Wikipedias"</span>
|
||
<span class="sd">"""`List of all wikipedias <https://meta.wikimedia.org/wiki/List_of_Wikipedias>`_</span>
|
||
<span class="sd">"""</span>
|
||
|
||
<span class="n">wikipedia_article_depth</span> <span class="o">=</span> <span class="s2">"https://meta.wikimedia.org/wiki/Wikipedia_article_depth"</span>
|
||
<span class="sd">"""The *editing depth* of Wikipedia is one of several possible rough indicators</span>
|
||
<span class="sd">of the encyclopedia's collaborative quality, showing how frequently its articles</span>
|
||
<span class="sd">are updated. The measurement of depth was introduced after some limitations of</span>
|
||
<span class="sd">the classic measurement of article count were realized.</span>
|
||
<span class="sd">"""</span>
|
||
|
||
<span class="n">rest_v1_summary_url</span> <span class="o">=</span> <span class="s2">"https://</span><span class="si">{wiki_netloc}</span><span class="s2">/api/rest_v1/page/summary/</span><span class="si">{title}</span><span class="s2">"</span>
|
||
<span class="sd">"""</span>
|
||
<span class="sd">`wikipedia rest_v1 summary API`_:</span>
|
||
<span class="sd"> The summary response includes an extract of the first paragraph of the page in</span>
|
||
<span class="sd"> plain text and HTML as well as the type of page. This is useful for page</span>
|
||
<span class="sd"> previews (fka. Hovercards, aka. Popups) on the web and link previews in the</span>
|
||
<span class="sd"> apps.</span>
|
||
|
||
<span class="sd">HTTP ``Accept-Language`` header (``send_accept_language_header``):</span>
|
||
<span class="sd"> The desired language variant code for wikis where LanguageConverter_ is</span>
|
||
<span class="sd"> enabled.</span>
|
||
|
||
<span class="sd">.. _wikipedia rest_v1 summary API:</span>
|
||
<span class="sd"> https://en.wikipedia.org/api/rest_v1/#/Page%20content/get_page_summary__title_</span>
|
||
|
||
<span class="sd">"""</span>
|
||
|
||
<span class="n">wiki_lc_locale_variants</span> <span class="o">=</span> <span class="p">{</span>
|
||
<span class="s2">"zh"</span><span class="p">:</span> <span class="p">(</span>
|
||
<span class="s2">"zh-CN"</span><span class="p">,</span>
|
||
<span class="s2">"zh-HK"</span><span class="p">,</span>
|
||
<span class="s2">"zh-MO"</span><span class="p">,</span>
|
||
<span class="s2">"zh-MY"</span><span class="p">,</span>
|
||
<span class="s2">"zh-SG"</span><span class="p">,</span>
|
||
<span class="s2">"zh-TW"</span><span class="p">,</span>
|
||
<span class="p">),</span>
|
||
<span class="s2">"zh-classical"</span><span class="p">:</span> <span class="p">(</span><span class="s2">"zh-classical"</span><span class="p">,),</span>
|
||
<span class="p">}</span>
|
||
<span class="sd">"""Mapping rule of the LanguageConverter_ to map a language and its variants to</span>
|
||
<span class="sd">a Locale (used in the HTTP ``Accept-Language`` header). For example see `LC</span>
|
||
<span class="sd">Chinese`_.</span>
|
||
|
||
<span class="sd">.. _LC Chinese:</span>
|
||
<span class="sd"> https://meta.wikimedia.org/wiki/Wikipedias_in_multiple_writing_systems#Chinese</span>
|
||
<span class="sd">"""</span>
|
||
|
||
<span class="n">wikipedia_script_variants</span> <span class="o">=</span> <span class="p">{</span>
|
||
<span class="s2">"zh"</span><span class="p">:</span> <span class="p">(</span>
|
||
<span class="s2">"zh_Hant"</span><span class="p">,</span>
|
||
<span class="s2">"zh_Hans"</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
<span class="p">}</span>
|
||
|
||
|
||
<div class="viewcode-block" id="get_wiki_params">
|
||
<a class="viewcode-back" href="../../../dev/engines/online/wikipedia.html#searx.engines.wikipedia.get_wiki_params">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">get_wiki_params</span><span class="p">(</span><span class="n">sxng_locale</span><span class="p">,</span> <span class="n">eng_traits</span><span class="p">):</span>
|
||
<span class="w"> </span><span class="sd">"""Returns the Wikipedia language tag and the netloc that fits to the</span>
|
||
<span class="sd"> ``sxng_locale``. To support LanguageConverter_ this function rates a locale</span>
|
||
<span class="sd"> (region) higher than a language (compare :py:obj:`wiki_lc_locale_variants`).</span>
|
||
|
||
<span class="sd"> """</span>
|
||
<span class="n">eng_tag</span> <span class="o">=</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">get_region</span><span class="p">(</span><span class="n">sxng_locale</span><span class="p">,</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">get_language</span><span class="p">(</span><span class="n">sxng_locale</span><span class="p">,</span> <span class="s2">"en"</span><span class="p">))</span>
|
||
<span class="n">wiki_netloc</span> <span class="o">=</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"wiki_netloc"</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">eng_tag</span><span class="p">,</span> <span class="s2">"en.wikipedia.org"</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="n">wiki_netloc</span></div>
|
||
|
||
|
||
|
||
<div class="viewcode-block" id="request">
|
||
<a class="viewcode-back" href="../../../dev/engines/online/wikipedia.html#searx.engines.wikipedia.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">"""Assemble a request (`wikipedia rest_v1 summary API`_)."""</span>
|
||
<span class="k">if</span> <span class="n">query</span><span class="o">.</span><span class="n">islower</span><span class="p">():</span>
|
||
<span class="n">query</span> <span class="o">=</span> <span class="n">query</span><span class="o">.</span><span class="n">title</span><span class="p">()</span>
|
||
|
||
<span class="n">_eng_tag</span><span class="p">,</span> <span class="n">wiki_netloc</span> <span class="o">=</span> <span class="n">get_wiki_params</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"searxng_locale"</span><span class="p">],</span> <span class="n">traits</span><span class="p">)</span>
|
||
<span class="n">title</span> <span class="o">=</span> <span class="n">urllib</span><span class="o">.</span><span class="n">parse</span><span class="o">.</span><span class="n">quote</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="s2">"url"</span><span class="p">]</span> <span class="o">=</span> <span class="n">rest_v1_summary_url</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">wiki_netloc</span><span class="o">=</span><span class="n">wiki_netloc</span><span class="p">,</span> <span class="n">title</span><span class="o">=</span><span class="n">title</span><span class="p">)</span>
|
||
|
||
<span class="n">params</span><span class="p">[</span><span class="s2">"raise_for_httperror"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">False</span>
|
||
<span class="n">params</span><span class="p">[</span><span class="s2">"soft_max_redirects"</span><span class="p">]</span> <span class="o">=</span> <span class="mi">2</span>
|
||
|
||
<span class="k">return</span> <span class="n">params</span></div>
|
||
|
||
|
||
|
||
<span class="c1"># get response from search-request</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="n">results</span> <span class="o">=</span> <span class="p">[]</span>
|
||
<span class="k">if</span> <span class="n">resp</span><span class="o">.</span><span class="n">status_code</span> <span class="o">==</span> <span class="mi">404</span><span class="p">:</span>
|
||
<span class="k">return</span> <span class="p">[]</span>
|
||
<span class="k">if</span> <span class="n">resp</span><span class="o">.</span><span class="n">status_code</span> <span class="o">==</span> <span class="mi">400</span><span class="p">:</span>
|
||
<span class="k">try</span><span class="p">:</span>
|
||
<span class="n">api_result</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">except</span> <span class="ne">Exception</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span>
|
||
<span class="k">pass</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="p">(</span>
|
||
<span class="n">api_result</span><span class="p">[</span><span class="s2">"type"</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"https://mediawiki.org/wiki/HyperSwitch/errors/bad_request"</span>
|
||
<span class="ow">and</span> <span class="n">api_result</span><span class="p">[</span><span class="s2">"detail"</span><span class="p">]</span> <span class="o">==</span> <span class="s2">"title-invalid-characters"</span>
|
||
<span class="p">):</span>
|
||
<span class="k">return</span> <span class="p">[]</span>
|
||
|
||
<span class="n">_network</span><span class="o">.</span><span class="n">raise_for_httperror</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span>
|
||
|
||
<span class="n">api_result</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="n">title</span> <span class="o">=</span> <span class="n">utils</span><span class="o">.</span><span class="n">html_to_text</span><span class="p">(</span><span class="n">api_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"titles"</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">"display"</span><span class="p">)</span> <span class="ow">or</span> <span class="n">api_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"title"</span><span class="p">))</span>
|
||
<span class="n">wikipedia_link</span> <span class="o">=</span> <span class="n">api_result</span><span class="p">[</span><span class="s2">"content_urls"</span><span class="p">][</span><span class="s2">"desktop"</span><span class="p">][</span><span class="s2">"page"</span><span class="p">]</span>
|
||
|
||
<span class="k">if</span> <span class="s2">"list"</span> <span class="ow">in</span> <span class="n">display_type</span> <span class="ow">or</span> <span class="n">api_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"type"</span><span class="p">)</span> <span class="o">!=</span> <span class="s2">"standard"</span><span class="p">:</span>
|
||
<span class="c1"># show item in the result list if 'list' is in the display options or it</span>
|
||
<span class="c1"># is a item that can't be displayed in a infobox.</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="s2">"url"</span><span class="p">:</span> <span class="n">wikipedia_link</span><span class="p">,</span>
|
||
<span class="s2">"title"</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
|
||
<span class="s2">"content"</span><span class="p">:</span> <span class="n">api_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"description"</span><span class="p">,</span> <span class="s2">""</span><span class="p">),</span>
|
||
<span class="p">}</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="s2">"infobox"</span> <span class="ow">in</span> <span class="n">display_type</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="n">api_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"type"</span><span class="p">)</span> <span class="o">==</span> <span class="s2">"standard"</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="s2">"infobox"</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
|
||
<span class="s2">"id"</span><span class="p">:</span> <span class="n">wikipedia_link</span><span class="p">,</span>
|
||
<span class="s2">"content"</span><span class="p">:</span> <span class="n">api_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"extract"</span><span class="p">,</span> <span class="s2">""</span><span class="p">),</span>
|
||
<span class="s2">"img_src"</span><span class="p">:</span> <span class="n">api_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="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"source"</span><span class="p">),</span>
|
||
<span class="s2">"urls"</span><span class="p">:</span> <span class="p">[{</span><span class="s2">"title"</span><span class="p">:</span> <span class="s2">"Wikipedia"</span><span class="p">,</span> <span class="s2">"url"</span><span class="p">:</span> <span class="n">wikipedia_link</span><span class="p">}],</span>
|
||
<span class="p">}</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="k">return</span> <span class="n">results</span>
|
||
|
||
|
||
<span class="c1"># Nonstandard language codes</span>
|
||
<span class="c1">#</span>
|
||
<span class="c1"># These Wikipedias use language codes that do not conform to the ISO 639</span>
|
||
<span class="c1"># standard (which is how wiki subdomains are chosen nowadays).</span>
|
||
|
||
<span class="n">lang_map</span> <span class="o">=</span> <span class="n">locales</span><span class="o">.</span><span class="n">LOCALE_BEST_MATCH</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span>
|
||
<span class="n">lang_map</span><span class="o">.</span><span class="n">update</span><span class="p">(</span>
|
||
<span class="p">{</span>
|
||
<span class="s2">"be-tarask"</span><span class="p">:</span> <span class="s2">"bel"</span><span class="p">,</span>
|
||
<span class="s2">"ak"</span><span class="p">:</span> <span class="s2">"aka"</span><span class="p">,</span>
|
||
<span class="s2">"als"</span><span class="p">:</span> <span class="s2">"gsw"</span><span class="p">,</span>
|
||
<span class="s2">"bat-smg"</span><span class="p">:</span> <span class="s2">"sgs"</span><span class="p">,</span>
|
||
<span class="s2">"cbk-zam"</span><span class="p">:</span> <span class="s2">"cbk"</span><span class="p">,</span>
|
||
<span class="s2">"fiu-vro"</span><span class="p">:</span> <span class="s2">"vro"</span><span class="p">,</span>
|
||
<span class="s2">"map-bms"</span><span class="p">:</span> <span class="s2">"map"</span><span class="p">,</span>
|
||
<span class="s2">"no"</span><span class="p">:</span> <span class="s2">"nb-NO"</span><span class="p">,</span>
|
||
<span class="s2">"nrm"</span><span class="p">:</span> <span class="s2">"nrf"</span><span class="p">,</span>
|
||
<span class="s2">"roa-rup"</span><span class="p">:</span> <span class="s2">"rup"</span><span class="p">,</span>
|
||
<span class="s2">"nds-nl"</span><span class="p">:</span> <span class="s2">"nds"</span><span class="p">,</span>
|
||
<span class="c1">#'simple: – invented code used for the Simple English Wikipedia (not the official IETF code en-simple)</span>
|
||
<span class="s2">"zh-min-nan"</span><span class="p">:</span> <span class="s2">"nan"</span><span class="p">,</span>
|
||
<span class="s2">"zh-yue"</span><span class="p">:</span> <span class="s2">"yue"</span><span class="p">,</span>
|
||
<span class="s2">"an"</span><span class="p">:</span> <span class="s2">"arg"</span><span class="p">,</span>
|
||
<span class="p">}</span>
|
||
<span class="p">)</span>
|
||
|
||
|
||
<span class="k">def</span><span class="w"> </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="n">fetch_wikimedia_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">)</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"WIKIPEDIA_LANGUAGES: </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="nb">len</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="s2">"WIKIPEDIA_LANGUAGES"</span><span class="p">]))</span>
|
||
|
||
|
||
<div class="viewcode-block" id="fetch_wikimedia_traits">
|
||
<a class="viewcode-back" href="../../../dev/engines/online/wikipedia.html#searx.engines.wikipedia.fetch_wikimedia_traits">[docs]</a>
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">fetch_wikimedia_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">"""Fetch languages from Wikipedia. Not all languages from the</span>
|
||
<span class="sd"> :py:obj:`list_of_wikipedias` are supported by SearXNG locales, only those</span>
|
||
<span class="sd"> known from :py:obj:`searx.locales.LOCALE_NAMES` or those with a minimal</span>
|
||
<span class="sd"> :py:obj:`editing depth <wikipedia_article_depth>`.</span>
|
||
|
||
<span class="sd"> The location of the Wikipedia address of a language is mapped in a</span>
|
||
<span class="sd"> :py:obj:`custom field <searx.enginelib.traits.EngineTraits.custom>`</span>
|
||
<span class="sd"> (``wiki_netloc``). Here is a reduced example:</span>
|
||
|
||
<span class="sd"> .. code:: python</span>
|
||
|
||
<span class="sd"> traits.custom['wiki_netloc'] = {</span>
|
||
<span class="sd"> "en": "en.wikipedia.org",</span>
|
||
<span class="sd"> ..</span>
|
||
<span class="sd"> "gsw": "als.wikipedia.org",</span>
|
||
<span class="sd"> ..</span>
|
||
<span class="sd"> "zh": "zh.wikipedia.org",</span>
|
||
<span class="sd"> "zh-classical": "zh-classical.wikipedia.org"</span>
|
||
<span class="sd"> }</span>
|
||
<span class="sd"> """</span>
|
||
<span class="c1"># pylint: disable=import-outside-toplevel, too-many-branches</span>
|
||
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.network</span><span class="w"> </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="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">searxng_useragent</span>
|
||
|
||
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"wiki_netloc"</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="s2">"WIKIPEDIA_LANGUAGES"</span><span class="p">]</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
||
<span class="c1"># insert alias to map from a script or region to a wikipedia variant</span>
|
||
|
||
<span class="k">for</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="n">sxng_tag_list</span> <span class="ow">in</span> <span class="n">wikipedia_script_variants</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||
<span class="k">for</span> <span class="n">sxng_tag</span> <span class="ow">in</span> <span class="n">sxng_tag_list</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="k">for</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="n">sxng_tag_list</span> <span class="ow">in</span> <span class="n">wiki_lc_locale_variants</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||
<span class="k">for</span> <span class="n">sxng_tag</span> <span class="ow">in</span> <span class="n">sxng_tag_list</span><span class="p">:</span>
|
||
<span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</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="n">headers</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"Accept"</span><span class="p">:</span> <span class="s2">"*/*"</span><span class="p">,</span> <span class="s2">"User-Agent"</span><span class="p">:</span> <span class="n">searxng_useragent</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="n">list_of_wikipedias</span><span class="p">,</span> <span class="n">timeout</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="n">headers</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="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="s2">"Response from Wikipedia is not OK."</span><span class="p">)</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="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">dom</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">'//table[contains(@class,"sortable")]//tbody/tr'</span><span class="p">):</span>
|
||
<span class="n">cols</span> <span class="o">=</span> <span class="n">row</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s2">"./td"</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="ow">not</span> <span class="n">cols</span><span class="p">:</span>
|
||
<span class="k">continue</span>
|
||
<span class="n">cols</span> <span class="o">=</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">text_content</span><span class="p">()</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">cols</span><span class="p">]</span>
|
||
|
||
<span class="n">depth</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">cols</span><span class="p">[</span><span class="mi">11</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">"-"</span><span class="p">,</span> <span class="s2">"0"</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">","</span><span class="p">,</span> <span class="s2">""</span><span class="p">))</span>
|
||
<span class="n">articles</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">cols</span><span class="p">[</span><span class="mi">4</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">","</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s2">","</span><span class="p">,</span> <span class="s2">""</span><span class="p">))</span>
|
||
|
||
<span class="n">eng_tag</span> <span class="o">=</span> <span class="n">cols</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span>
|
||
<span class="n">wiki_url</span> <span class="o">=</span> <span class="n">row</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s2">"./td[4]/a/@href"</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
||
<span class="n">wiki_url</span> <span class="o">=</span> <span class="n">urllib</span><span class="o">.</span><span class="n">parse</span><span class="o">.</span><span class="n">urlparse</span><span class="p">(</span><span class="n">wiki_url</span><span class="p">)</span>
|
||
|
||
<span class="k">try</span><span class="p">:</span>
|
||
<span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">locales</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">lang_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">eng_tag</span><span class="p">,</span> <span class="n">eng_tag</span><span class="p">),</span> <span class="n">sep</span><span class="o">=</span><span class="s2">"-"</span><span class="p">))</span>
|
||
<span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span>
|
||
<span class="c1"># print("ERROR: %s [%s] is unknown by babel" % (cols[0], eng_tag))</span>
|
||
<span class="k">continue</span>
|
||
<span class="k">finally</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="s2">"WIKIPEDIA_LANGUAGES"</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">eng_tag</span><span class="p">)</span>
|
||
|
||
<span class="k">if</span> <span class="n">sxng_tag</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">locales</span><span class="o">.</span><span class="n">LOCALE_NAMES</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="n">articles</span> <span class="o"><</span> <span class="mi">10000</span><span class="p">:</span>
|
||
<span class="c1"># exclude languages with too few articles</span>
|
||
<span class="k">continue</span>
|
||
|
||
<span class="k">if</span> <span class="nb">int</span><span class="p">(</span><span class="n">depth</span><span class="p">)</span> <span class="o"><</span> <span class="mi">20</span><span class="p">:</span>
|
||
<span class="c1"># Rough indicator of a Wikipedia’s quality, showing how</span>
|
||
<span class="c1"># frequently its articles are updated.</span>
|
||
<span class="k">continue</span>
|
||
|
||
<span class="n">conflict</span> <span class="o">=</span> <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</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="n">conflict</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="n">conflict</span> <span class="o">!=</span> <span class="n">eng_tag</span><span class="p">:</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"CONFLICT: babel </span><span class="si">%s</span><span class="s2"> --> </span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">sxng_tag</span><span class="p">,</span> <span class="n">conflict</span><span class="p">,</span> <span class="n">eng_tag</span><span class="p">))</span>
|
||
<span class="k">continue</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="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"wiki_netloc"</span><span class="p">][</span><span class="n">eng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">wiki_url</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="s2">"WIKIPEDIA_LANGUAGES"</span><span class="p">]</span><span class="o">.</span><span class="n">sort</span><span class="p">()</span></div>
|
||
|
||
</pre></div>
|
||
</article>
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="related-pages">
|
||
|
||
|
||
</div>
|
||
<div class="bottom-of-page">
|
||
<div class="left-details">
|
||
<div class="copyright">
|
||
Copyright © SearXNG team
|
||
</div>
|
||
Made with
|
||
<a href="https://github.com/pradyunsg/furo">Furo</a>
|
||
|
||
</div>
|
||
<div class="right-details">
|
||
<div class="icons">
|
||
<a class="muted-link " href="https://github.com/searxng/searxng/" aria-label="GitHub">💾</a>
|
||
<a class="muted-link " href="https://searx.space/" aria-label="searx.space">🌐</a>
|
||
|
||
</div>
|
||
</div>
|
||
</div>
|
||
|
||
</footer>
|
||
</div>
|
||
<aside class="toc-drawer no-toc">
|
||
|
||
|
||
|
||
</aside>
|
||
</div>
|
||
</div><script src="../../../_static/documentation_options.js?v=c15363ef"></script>
|
||
<script src="../../../_static/doctools.js?v=fd6eb6e6"></script>
|
||
<script src="../../../_static/sphinx_highlight.js?v=6ffebe34"></script>
|
||
<script src="../../../_static/scripts/furo.js?v=46bd48cc"></script>
|
||
</body>
|
||
</html> |