mirror of
https://github.com/searxng/searxng.git
synced 2026-05-07 18:03:51 +02:00
346 lines
35 KiB
HTML
346 lines
35 KiB
HTML
<!DOCTYPE html>
|
|
|
|
<html lang="en" data-content_root="../../../">
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<title>searx.engines.bing — SearXNG Documentation (2026.4.28+ed5955a5c)</title>
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
|
|
<script src="../../../_static/documentation_options.js?v=0cda547d"></script>
|
|
<script src="../../../_static/doctools.js?v=9bcbadda"></script>
|
|
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script data-project="searxng" data-version="2026.4.28+ed5955a5c" 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 (2026.4.28+ed5955a5c)</a> »</li>
|
|
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
|
|
<li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> »</li>
|
|
<li class="nav-item nav-item-this"><a href="">searx.engines.bing</a></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="document">
|
|
<div class="documentwrapper">
|
|
<div class="bodywrapper">
|
|
<div class="body" role="main">
|
|
|
|
<h1>Source code for searx.engines.bing</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
|
<span class="sd">"""This is the implementation of the Bing-Web engine. Some of this</span>
|
|
<span class="sd">implementations are shared by other engines:</span>
|
|
|
|
<span class="sd">- :ref:`bing images engine`</span>
|
|
<span class="sd">- :ref:`bing news engine`</span>
|
|
<span class="sd">- :ref:`bing videos engine`</span>
|
|
|
|
<span class="sd">.. note::</span>
|
|
|
|
<span class="sd"> Some functionality (paging and time-range results) are not supported</span>
|
|
<span class="sd"> since they depend on JavaScript.</span>
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">base64</span>
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">re</span>
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">t</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">urllib.parse</span><span class="w"> </span><span class="kn">import</span> <span class="n">parse_qs</span><span class="p">,</span> <span class="n">urlencode</span><span class="p">,</span> <span class="n">urlparse</span>
|
|
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">babel</span>
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">babel.languages</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.enginelib.traits</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineTraits</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.locales</span><span class="w"> </span><span class="kn">import</span> <span class="n">region_tag</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">eval_xpath</span><span class="p">,</span> <span class="n">eval_xpath_getindex</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">,</span> <span class="n">extract_text</span>
|
|
|
|
<span class="k">if</span> <span class="n">t</span><span class="o">.</span><span class="n">TYPE_CHECKING</span><span class="p">:</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.extended_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">SXNG_Response</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.search.processors</span><span class="w"> </span><span class="kn">import</span> <span class="n">OnlineParams</span>
|
|
|
|
<span class="n">about</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"website"</span><span class="p">:</span> <span class="s2">"https://www.bing.com"</span><span class="p">,</span>
|
|
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s2">"Q182496"</span><span class="p">,</span>
|
|
<span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="s2">"https://github.com/MicrosoftDocs/bing-docs"</span><span class="p">,</span>
|
|
<span class="s2">"use_official_api"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="s2">"require_api_key"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="s2">"results"</span><span class="p">:</span> <span class="s2">"HTML"</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="c1"># engine dependent config</span>
|
|
<span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"general"</span><span class="p">,</span> <span class="s2">"web"</span><span class="p">]</span>
|
|
<span class="n">safesearch</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">_safesearch_map</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">int</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="mi">0</span><span class="p">:</span> <span class="s2">"off"</span><span class="p">,</span>
|
|
<span class="mi">1</span><span class="p">:</span> <span class="s2">"moderate"</span><span class="p">,</span>
|
|
<span class="mi">2</span><span class="p">:</span> <span class="s2">"strict"</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="sd">"""Filter results. 0: None, 1: Moderate, 2: Strict"""</span>
|
|
|
|
<span class="n">base_url</span> <span class="o">=</span> <span class="s2">"https://www.bing.com/search"</span>
|
|
<span class="sd">"""Bing-Web search URL"""</span>
|
|
|
|
|
|
<div class="viewcode-block" id="get_locale_params">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.get_locale_params">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">get_locale_params</span><span class="p">(</span><span class="n">engine_region</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">"""API documentation states the ``mkt`` parameter is *the</span>
|
|
<span class="sd"> recommended primary signal* for locale:</span>
|
|
|
|
<span class="sd"> If known, you are encouraged to always specify the market.</span>
|
|
<span class="sd"> Specifying the market helps Bing route the request and return an</span>
|
|
<span class="sd"> appropriate and optimal response.</span>
|
|
|
|
<span class="sd"> The ``mkt`` parameter takes a full ``<language>-<country>`` code.</span>
|
|
|
|
<span class="sd"> This function is shared with :py:mod:`searx.engines.bing_images`,</span>
|
|
<span class="sd"> :py:mod:`searx.engines.bing_news`, and :py:mod:`searx.engines.bing_videos`.</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">engine_region</span> <span class="ow">or</span> <span class="n">engine_region</span> <span class="o">==</span> <span class="s2">"clear"</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="kc">None</span>
|
|
|
|
<span class="k">return</span> <span class="p">{</span><span class="s2">"mkt"</span><span class="p">:</span> <span class="n">engine_region</span><span class="p">}</span></div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="override_accept_language">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.override_accept_language">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">override_accept_language</span><span class="p">(</span><span class="n">params</span><span class="p">:</span> <span class="s2">"OnlineParams"</span><span class="p">,</span> <span class="n">engine_region</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">"""Override the ``Accept-Language`` header.</span>
|
|
|
|
<span class="sd"> The default header built by :py:class:`~searx.search.processors.online.OnlineProcessor`</span>
|
|
<span class="sd"> appends ``en;q=0.3`` as a fallback language::</span>
|
|
|
|
<span class="sd"> Accept-Language: de,de-DE;q=0.7,en;q=0.3</span>
|
|
|
|
<span class="sd"> Bing seems to better select the results locale based on the</span>
|
|
<span class="sd"> ``Accept-Language`` value header.</span>
|
|
|
|
<span class="sd"> This function is shared with :py:mod:`searx.engines.bing_images`,</span>
|
|
<span class="sd"> :py:mod:`searx.engines.bing_news`, and :py:mod:`searx.engines.bing_videos`.</span>
|
|
<span class="sd"> """</span>
|
|
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">engine_region</span> <span class="ow">or</span> <span class="n">engine_region</span> <span class="o">==</span> <span class="s2">"clear"</span><span class="p">:</span>
|
|
<span class="k">return</span>
|
|
|
|
<span class="n">lang</span> <span class="o">=</span> <span class="n">engine_region</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"-"</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"headers"</span><span class="p">][</span><span class="s2">"Accept-Language"</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">engine_region</span><span class="si">}</span><span class="s2">,</span><span class="si">{</span><span class="n">lang</span><span class="si">}</span><span class="s2">;q=0.9"</span></div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="request">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.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="nb">str</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="s2">"OnlineParams"</span><span class="p">)</span> <span class="o">-></span> <span class="s2">"OnlineParams"</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">"""Assemble a Bing-Web request."""</span>
|
|
|
|
<span class="n">engine_region</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">get_region</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="o">.</span><span class="n">all_locale</span><span class="p">)</span>
|
|
|
|
<span class="n">override_accept_language</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">engine_region</span><span class="p">)</span>
|
|
|
|
<span class="n">query_params</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span> <span class="o">|</span> <span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"q"</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
|
|
<span class="s2">"adlt"</span><span class="p">:</span> <span class="n">_safesearch_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"safesearch"</span><span class="p">,</span> <span class="mi">0</span><span class="p">),</span> <span class="s2">"off"</span><span class="p">),</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="n">locale_params</span> <span class="o">=</span> <span class="n">get_locale_params</span><span class="p">(</span><span class="n">engine_region</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">locale_params</span><span class="p">:</span>
|
|
<span class="n">query_params</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">locale_params</span><span class="p">)</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"url"</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">base_url</span><span class="si">}</span><span class="s2">?</span><span class="si">{</span><span class="n">urlencode</span><span class="p">(</span><span class="n">query_params</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span>
|
|
|
|
<span class="c1"># in some regions where geoblocking is employed (e.g. China),</span>
|
|
<span class="c1"># www.bing.com redirects to the regional version of Bing</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"allow_redirects"</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span>
|
|
|
|
<span class="k">return</span> <span class="n">params</span></div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="response">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.response">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">:</span> <span class="s2">"SXNG_Response"</span><span class="p">)</span> <span class="o">-></span> <span class="nb">list</span><span class="p">[</span><span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]]:</span>
|
|
<span class="w"> </span><span class="sd">"""Get response from Bing-Web"""</span>
|
|
|
|
<span class="n">results</span><span class="p">:</span> <span class="nb">list</span><span class="p">[</span><span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="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">item</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">'//ol[@id="b_results"]/li[contains(@class, "b_algo")]'</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">item</span><span class="p">,</span> <span class="s2">".//h2/a"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">link</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="n">href</span> <span class="o">=</span> <span class="n">link</span><span class="o">.</span><span class="n">attrib</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"href"</span><span class="p">,</span> <span class="s2">""</span><span class="p">)</span>
|
|
<span class="n">title</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">link</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">href</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">title</span><span class="p">:</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="c1"># what about cn.bing.com, ..?</span>
|
|
<span class="k">if</span> <span class="n">href</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"https://www.bing.com/ck/a?"</span><span class="p">):</span>
|
|
<span class="n">qs</span> <span class="o">=</span> <span class="n">parse_qs</span><span class="p">(</span><span class="n">urlparse</span><span class="p">(</span><span class="n">href</span><span class="p">)</span><span class="o">.</span><span class="n">query</span><span class="p">)</span>
|
|
<span class="n">u_values</span> <span class="o">=</span> <span class="n">qs</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"u"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">u_values</span><span class="p">:</span>
|
|
<span class="n">u_val</span> <span class="o">=</span> <span class="n">u_values</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">if</span> <span class="n">u_val</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s2">"a1"</span><span class="p">):</span>
|
|
<span class="n">encoded</span> <span class="o">=</span> <span class="n">u_val</span><span class="p">[</span><span class="mi">2</span><span class="p">:]</span>
|
|
<span class="c1"># base64url without padding</span>
|
|
<span class="n">encoded</span> <span class="o">+=</span> <span class="s2">"="</span> <span class="o">*</span> <span class="p">(</span><span class="o">-</span><span class="nb">len</span><span class="p">(</span><span class="n">encoded</span><span class="p">)</span> <span class="o">%</span> <span class="mi">4</span><span class="p">)</span>
|
|
<span class="n">href</span> <span class="o">=</span> <span class="n">base64</span><span class="o">.</span><span class="n">urlsafe_b64decode</span><span class="p">(</span><span class="n">encoded</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s2">"utf-8"</span><span class="p">,</span> <span class="n">errors</span><span class="o">=</span><span class="s2">"replace"</span><span class="p">)</span>
|
|
|
|
<span class="c1"># remove decorative icons that Bing injects into <p> elements</span>
|
|
<span class="c1"># (`<span class="algoSlug_icon">`)</span>
|
|
<span class="n">content_els</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">item</span><span class="p">,</span> <span class="s2">".//p"</span><span class="p">)</span>
|
|
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">content_els</span><span class="p">:</span>
|
|
<span class="k">for</span> <span class="n">icon</span> <span class="ow">in</span> <span class="n">p</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">'.//span[@class="algoSlug_icon"]'</span><span class="p">):</span>
|
|
<span class="n">icon</span><span class="o">.</span><span class="n">getparent</span><span class="p">()</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">icon</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">content_els</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="s2">"url"</span><span class="p">:</span> <span class="n">href</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">content</span><span class="p">})</span>
|
|
|
|
<span class="k">if</span> <span class="n">results</span><span class="p">:</span>
|
|
<span class="n">result_len_container</span> <span class="o">=</span> <span class="s2">""</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">'//span[@class="sb_count"]//text()'</span><span class="p">))</span>
|
|
<span class="n">result_len_container</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s2">"[^0-9]"</span><span class="p">,</span> <span class="s2">""</span><span class="p">,</span> <span class="n">result_len_container</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">result_len_container</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="s2">"number_of_results"</span><span class="p">:</span> <span class="nb">int</span><span class="p">(</span><span class="n">result_len_container</span><span class="p">)})</span>
|
|
|
|
<span class="k">return</span> <span class="n">results</span></div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="fetch_traits">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.fetch_traits">[docs]</a>
|
|
<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="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="w"> </span><span class="sd">"""Fetch regions from Bing-Web."""</span>
|
|
<span class="c1"># pylint: disable=import-outside-toplevel</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">gen_useragent</span>
|
|
|
|
<span class="n">headers</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"User-Agent"</span><span class="p">:</span> <span class="n">gen_useragent</span><span class="p">(),</span>
|
|
<span class="s2">"Accept"</span><span class="p">:</span> <span class="s2">"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"</span><span class="p">,</span>
|
|
<span class="s2">"Accept-Language"</span><span class="p">:</span> <span class="s2">"en-US;q=0.5,en;q=0.3"</span><span class="p">,</span>
|
|
<span class="s2">"DNT"</span><span class="p">:</span> <span class="s2">"1"</span><span class="p">,</span>
|
|
<span class="s2">"Connection"</span><span class="p">:</span> <span class="s2">"keep-alive"</span><span class="p">,</span>
|
|
<span class="s2">"Upgrade-Insecure-Requests"</span><span class="p">:</span> <span class="s2">"1"</span><span class="p">,</span>
|
|
<span class="s2">"Sec-GPC"</span><span class="p">:</span> <span class="s2">"1"</span><span class="p">,</span>
|
|
<span class="s2">"Cache-Control"</span><span class="p">:</span> <span class="s2">"max-age=0"</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="s2">"https://www.bing.com/account/general"</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="n">timeout</span><span class="o">=</span><span class="mi">5</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 Bing 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="n">map_market_codes</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"zh-hk"</span><span class="p">:</span> <span class="s2">"en-hk"</span><span class="p">,</span> <span class="c1"># not sure why, but at Microslop this is the market code for Hongkong</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="k">for</span> <span class="n">href</span> <span class="ow">in</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">'//div[@id="region-section-content"]//div[@class="regionItem"]/a/@href'</span><span class="p">):</span>
|
|
<span class="n">cc_tag</span> <span class="o">=</span> <span class="n">parse_qs</span><span class="p">(</span><span class="n">urlparse</span><span class="p">(</span><span class="n">href</span><span class="p">)</span><span class="o">.</span><span class="n">query</span><span class="p">)[</span><span class="s2">"cc"</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="k">if</span> <span class="n">cc_tag</span> <span class="o">==</span> <span class="s2">"clear"</span><span class="p">:</span>
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">all_locale</span> <span class="o">=</span> <span class="n">cc_tag</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="c1"># add market codes from official languages of the country ..</span>
|
|
<span class="k">for</span> <span class="n">lang_tag</span> <span class="ow">in</span> <span class="n">babel</span><span class="o">.</span><span class="n">languages</span><span class="o">.</span><span class="n">get_official_languages</span><span class="p">(</span><span class="n">cc_tag</span><span class="p">,</span> <span class="n">de_facto</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
|
|
<span class="n">lang_tag</span> <span class="o">=</span> <span class="n">lang_tag</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"_"</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="c1"># zh_Hant --> zh</span>
|
|
<span class="n">market_code</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">lang_tag</span><span class="si">}</span><span class="s2">-</span><span class="si">{</span><span class="n">cc_tag</span><span class="si">}</span><span class="s2">"</span> <span class="c1"># zh-tw</span>
|
|
<span class="n">market_code</span> <span class="o">=</span> <span class="n">map_market_codes</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">market_code</span><span class="p">,</span> <span class="n">market_code</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">region_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="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">lang_tag</span><span class="p">,</span> <span class="n">cc_tag</span><span class="o">.</span><span class="n">upper</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"># silently ignore unknown languages</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">regions</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">market_code</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">market_code</span><span class="p">))</span>
|
|
<span class="k">continue</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">market_code</span></div>
|
|
|
|
</pre></div>
|
|
|
|
<div class="clearer"></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<span id="sidebar-top"></span>
|
|
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
|
<div class="sphinxsidebarwrapper">
|
|
|
|
|
|
<p class="logo"><a href="../../../index.html">
|
|
<img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
|
|
</a></p>
|
|
|
|
|
|
<h3><a href="../../../index.html">Table of Contents</a></h3>
|
|
<ul>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
|
|
</ul>
|
|
|
|
<h3>Project Links</h3>
|
|
<ul>
|
|
<li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
|
|
|
|
<li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
|
|
|
|
<li><a href="https://searx.space">Public instances</a>
|
|
|
|
<li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
|
|
</ul><h3>Navigation</h3>
|
|
<ul>
|
|
<li><a href="../../../index.html">Overview</a>
|
|
<ul>
|
|
<li><a href="../../index.html">Module code</a>
|
|
<ul>
|
|
<li><a href="../engines.html">searx.engines</a>
|
|
|
|
|
|
</ul>
|
|
</li></ul>
|
|
</li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
<search id="searchbox" style="display: none" role="search">
|
|
<h3 id="searchlabel">Quick search</h3>
|
|
<div class="searchformwrapper">
|
|
<form class="search" action="../../../search.html" method="get">
|
|
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
|
<input type="submit" value="Go" />
|
|
</form>
|
|
</div>
|
|
</search>
|
|
<script>document.getElementById('searchbox').style.display = "block"</script>
|
|
</div>
|
|
</div>
|
|
<div class="clearer"></div>
|
|
</div>
|
|
<div class="footer" role="contentinfo">
|
|
© Copyright SearXNG team.
|
|
</div>
|
|
</body>
|
|
</html> |