forked from Ponysearch/Ponysearch
422 lines
No EOL
36 KiB
HTML
422 lines
No EOL
36 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.google_news — SearXNG Documentation (2024.4.28+fd93d0c60)</title>
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=4f649999" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/tabs.css?v=a5c4661c" />
|
|
<script src="../../../_static/documentation_options.js?v=88ac209d"></script>
|
|
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
|
|
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script src="../../../_static/tabs.js?v=3030b3cb"></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 navigation">
|
|
<h3>Navigation</h3>
|
|
<ul>
|
|
<li class="right" style="margin-right: 10px">
|
|
<a href="../../../genindex.html" title="General Index"
|
|
accesskey="I">index</a></li>
|
|
<li class="right" >
|
|
<a href="../../../py-modindex.html" title="Python Module Index"
|
|
>modules</a> |</li>
|
|
<li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2024.4.28+fd93d0c60)</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.google_news</a></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="document">
|
|
<div class="documentwrapper">
|
|
<div class="bodywrapper">
|
|
<div class="body" role="main">
|
|
|
|
<h1>Source code for searx.engines.google_news</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 Google News engine.</span>
|
|
|
|
<span class="sd">Google News has a different region handling compared to Google WEB.</span>
|
|
|
|
<span class="sd">- the ``ceid`` argument has to be set (:py:obj:`ceid_list`)</span>
|
|
<span class="sd">- the hl_ argument has to be set correctly (and different to Google WEB)</span>
|
|
<span class="sd">- the gl_ argument is mandatory</span>
|
|
|
|
<span class="sd">If one of this argument is not set correctly, the request is redirected to</span>
|
|
<span class="sd">CONSENT dialog::</span>
|
|
|
|
<span class="sd"> https://consent.google.com/m?continue=</span>
|
|
|
|
<span class="sd">The google news API ignores some parameters from the common :ref:`google API`:</span>
|
|
|
|
<span class="sd">- num_ : the number of search results is ignored / there is no paging all</span>
|
|
<span class="sd"> results for a query term are in the first response.</span>
|
|
<span class="sd">- save_ : is ignored / Google-News results are always *SafeSearch*</span>
|
|
|
|
<span class="sd">.. _hl: https://developers.google.com/custom-search/docs/xml_results#hlsp</span>
|
|
<span class="sd">.. _gl: https://developers.google.com/custom-search/docs/xml_results#glsp</span>
|
|
<span class="sd">.. _num: https://developers.google.com/custom-search/docs/xml_results#numsp</span>
|
|
<span class="sd">.. _save: https://developers.google.com/custom-search/docs/xml_results#safesp</span>
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">TYPE_CHECKING</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">urlencode</span>
|
|
<span class="kn">import</span> <span class="nn">base64</span>
|
|
<span class="kn">from</span> <span class="nn">lxml</span> <span class="kn">import</span> <span class="n">html</span>
|
|
<span class="kn">import</span> <span class="nn">babel</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">searx</span> <span class="kn">import</span> <span class="n">locales</span>
|
|
<span class="kn">from</span> <span class="nn">searx.utils</span> <span class="kn">import</span> <span class="p">(</span>
|
|
<span class="n">eval_xpath</span><span class="p">,</span>
|
|
<span class="n">eval_xpath_list</span><span class="p">,</span>
|
|
<span class="n">eval_xpath_getindex</span><span class="p">,</span>
|
|
<span class="n">extract_text</span><span class="p">,</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">searx.engines.google</span> <span class="kn">import</span> <span class="n">fetch_traits</span> <span class="k">as</span> <span class="n">_fetch_traits</span> <span class="c1"># pylint: disable=unused-import</span>
|
|
<span class="kn">from</span> <span class="nn">searx.engines.google</span> <span class="kn">import</span> <span class="p">(</span>
|
|
<span class="n">get_google_info</span><span class="p">,</span>
|
|
<span class="n">detect_google_sorry</span><span class="p">,</span>
|
|
<span class="p">)</span>
|
|
<span class="kn">from</span> <span class="nn">searx.enginelib.traits</span> <span class="kn">import</span> <span class="n">EngineTraits</span>
|
|
|
|
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
|
|
<span class="kn">import</span> <span class="nn">logging</span>
|
|
|
|
<span class="n">logger</span><span class="p">:</span> <span class="n">logging</span><span class="o">.</span><span class="n">Logger</span>
|
|
|
|
<span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
|
|
|
|
<span class="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="s1">'https://news.google.com'</span><span class="p">,</span>
|
|
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s1">'Q12020'</span><span class="p">,</span>
|
|
<span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="s1">'https://developers.google.com/custom-search'</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="s1">'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="s1">'news'</span><span class="p">]</span>
|
|
<span class="n">paging</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">False</span>
|
|
|
|
<span class="c1"># Google-News results are always *SafeSearch*. Option 'safesearch' is set to</span>
|
|
<span class="c1"># False here, otherwise checker will report safesearch-errors::</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># safesearch : results are identical for safesearch=0 and safesearch=2</span>
|
|
<span class="n">safesearch</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="c1"># send_accept_language_header = True</span>
|
|
|
|
|
|
<div class="viewcode-block" id="request">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/google.html#searx.engines.google_news.request">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""Google-News search request"""</span>
|
|
|
|
<span class="n">sxng_locale</span> <span class="o">=</span> <span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'searxng_locale'</span><span class="p">,</span> <span class="s1">'en-US'</span><span class="p">)</span>
|
|
<span class="n">ceid</span> <span class="o">=</span> <span class="n">locales</span><span class="o">.</span><span class="n">get_engine_locale</span><span class="p">(</span><span class="n">sxng_locale</span><span class="p">,</span> <span class="n">traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">'ceid'</span><span class="p">],</span> <span class="n">default</span><span class="o">=</span><span class="s1">'US:en'</span><span class="p">)</span>
|
|
<span class="n">google_info</span> <span class="o">=</span> <span class="n">get_google_info</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">traits</span><span class="p">)</span>
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'subdomain'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'news.google.com'</span> <span class="c1"># google news has only one domain</span>
|
|
|
|
<span class="n">ceid_region</span><span class="p">,</span> <span class="n">ceid_lang</span> <span class="o">=</span> <span class="n">ceid</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">':'</span><span class="p">)</span>
|
|
<span class="n">ceid_lang</span><span class="p">,</span> <span class="n">ceid_suffix</span> <span class="o">=</span> <span class="p">(</span>
|
|
<span class="n">ceid_lang</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'-'</span><span class="p">)</span>
|
|
<span class="o">+</span> <span class="p">[</span>
|
|
<span class="kc">None</span><span class="p">,</span>
|
|
<span class="p">]</span>
|
|
<span class="p">)[:</span><span class="mi">2</span><span class="p">]</span>
|
|
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'hl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">ceid_lang</span>
|
|
|
|
<span class="k">if</span> <span class="n">ceid_suffix</span> <span class="ow">and</span> <span class="n">ceid_suffix</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'Hans'</span><span class="p">,</span> <span class="s1">'Hant'</span><span class="p">]:</span>
|
|
|
|
<span class="k">if</span> <span class="n">ceid_region</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="n">ceid_lang</span><span class="p">:</span>
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'hl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">ceid_lang</span> <span class="o">+</span> <span class="s1">'-'</span> <span class="o">+</span> <span class="n">ceid_region</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'hl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">ceid_lang</span> <span class="o">+</span> <span class="s1">'-'</span> <span class="o">+</span> <span class="n">ceid_suffix</span>
|
|
|
|
<span class="k">elif</span> <span class="n">ceid_region</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">!=</span> <span class="n">ceid_lang</span><span class="p">:</span>
|
|
|
|
<span class="k">if</span> <span class="n">ceid_region</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'AT'</span><span class="p">,</span> <span class="s1">'BE'</span><span class="p">,</span> <span class="s1">'CH'</span><span class="p">,</span> <span class="s1">'IL'</span><span class="p">,</span> <span class="s1">'SA'</span><span class="p">,</span> <span class="s1">'IN'</span><span class="p">,</span> <span class="s1">'BD'</span><span class="p">,</span> <span class="s1">'PT'</span><span class="p">]:</span>
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'hl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">ceid_lang</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'hl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">ceid_lang</span> <span class="o">+</span> <span class="s1">'-'</span> <span class="o">+</span> <span class="n">ceid_region</span>
|
|
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'lang_'</span> <span class="o">+</span> <span class="n">ceid_lang</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'-'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'gl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">ceid_region</span>
|
|
|
|
<span class="n">query_url</span> <span class="o">=</span> <span class="p">(</span>
|
|
<span class="s1">'https://'</span>
|
|
<span class="o">+</span> <span class="n">google_info</span><span class="p">[</span><span class="s1">'subdomain'</span><span class="p">]</span>
|
|
<span class="o">+</span> <span class="s2">"/search?"</span>
|
|
<span class="o">+</span> <span class="n">urlencode</span><span class="p">(</span>
|
|
<span class="p">{</span>
|
|
<span class="s1">'q'</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
|
|
<span class="o">**</span><span class="n">google_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">],</span>
|
|
<span class="p">}</span>
|
|
<span class="p">)</span>
|
|
<span class="c1"># ceid includes a ':' character which must not be urlencoded</span>
|
|
<span class="o">+</span> <span class="p">(</span><span class="s1">'&ceid=</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">ceid</span><span class="p">)</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]</span> <span class="o">=</span> <span class="n">query_url</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">]</span> <span class="o">=</span> <span class="n">google_info</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">]</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">google_info</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">])</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/google.html#searx.engines.google_news.response">[docs]</a>
|
|
<span class="k">def</span> <span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""Get response from google's search request"""</span>
|
|
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">detect_google_sorry</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span>
|
|
|
|
<span class="c1"># convert the text to dom</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">result</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">'//div[@class="xrnccd"]'</span><span class="p">):</span>
|
|
|
|
<span class="c1"># The first <a> tag in the <article> contains the link to the article</span>
|
|
<span class="c1"># The href attribute of the <a> tag is a google internal link, we have</span>
|
|
<span class="c1"># to decode</span>
|
|
|
|
<span class="n">href</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">'./article/a/@href'</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
|
<span class="n">href</span> <span class="o">=</span> <span class="n">href</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'?'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="n">href</span> <span class="o">=</span> <span class="n">href</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</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">href</span> <span class="o">+</span> <span class="s1">'===='</span><span class="p">)</span>
|
|
<span class="n">href</span> <span class="o">=</span> <span class="n">href</span><span class="p">[</span><span class="n">href</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="sa">b</span><span class="s1">'http'</span><span class="p">)</span> <span class="p">:]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">b</span><span class="s1">'</span><span class="se">\xd2</span><span class="s1">'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
|
<span class="n">href</span> <span class="o">=</span> <span class="n">href</span><span class="o">.</span><span class="n">decode</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">eval_xpath</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">'./article/h3[1]'</span><span class="p">))</span>
|
|
|
|
<span class="c1"># The pub_date is mostly a string like 'yesterday', not a real</span>
|
|
<span class="c1"># timezone date or time. Therefore we can't use publishedDate.</span>
|
|
<span class="n">pub_date</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">'./article//time'</span><span class="p">))</span>
|
|
<span class="n">pub_origin</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">'./article//a[@data-n-tid]'</span><span class="p">))</span>
|
|
|
|
<span class="n">content</span> <span class="o">=</span> <span class="s1">' / '</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">x</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="p">[</span><span class="n">pub_origin</span><span class="p">,</span> <span class="n">pub_date</span><span class="p">]</span> <span class="k">if</span> <span class="n">x</span><span class="p">])</span>
|
|
|
|
<span class="c1"># The image URL is located in a preceding sibling <img> tag, e.g.:</span>
|
|
<span class="c1"># "https://lh3.googleusercontent.com/DjhQh7DMszk.....z=-p-h100-w100"</span>
|
|
<span class="c1"># These URL are long but not personalized (double checked via tor).</span>
|
|
|
|
<span class="n">img_src</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">result</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">'preceding-sibling::a/figure/img/@src'</span><span class="p">))</span>
|
|
|
|
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
|
|
<span class="p">{</span>
|
|
<span class="s1">'url'</span><span class="p">:</span> <span class="n">href</span><span class="p">,</span>
|
|
<span class="s1">'title'</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
|
|
<span class="s1">'content'</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span>
|
|
<span class="s1">'img_src'</span><span class="p">:</span> <span class="n">img_src</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="c1"># return results</span>
|
|
<span class="k">return</span> <span class="n">results</span></div>
|
|
|
|
|
|
|
|
<span class="n">ceid_list</span> <span class="o">=</span> <span class="p">[</span>
|
|
<span class="s1">'AE:ar'</span><span class="p">,</span>
|
|
<span class="s1">'AR:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'AT:de'</span><span class="p">,</span>
|
|
<span class="s1">'AU:en'</span><span class="p">,</span>
|
|
<span class="s1">'BD:bn'</span><span class="p">,</span>
|
|
<span class="s1">'BE:fr'</span><span class="p">,</span>
|
|
<span class="s1">'BE:nl'</span><span class="p">,</span>
|
|
<span class="s1">'BG:bg'</span><span class="p">,</span>
|
|
<span class="s1">'BR:pt-419'</span><span class="p">,</span>
|
|
<span class="s1">'BW:en'</span><span class="p">,</span>
|
|
<span class="s1">'CA:en'</span><span class="p">,</span>
|
|
<span class="s1">'CA:fr'</span><span class="p">,</span>
|
|
<span class="s1">'CH:de'</span><span class="p">,</span>
|
|
<span class="s1">'CH:fr'</span><span class="p">,</span>
|
|
<span class="s1">'CL:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'CN:zh-Hans'</span><span class="p">,</span>
|
|
<span class="s1">'CO:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'CU:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'CZ:cs'</span><span class="p">,</span>
|
|
<span class="s1">'DE:de'</span><span class="p">,</span>
|
|
<span class="s1">'EG:ar'</span><span class="p">,</span>
|
|
<span class="s1">'ES:es'</span><span class="p">,</span>
|
|
<span class="s1">'ET:en'</span><span class="p">,</span>
|
|
<span class="s1">'FR:fr'</span><span class="p">,</span>
|
|
<span class="s1">'GB:en'</span><span class="p">,</span>
|
|
<span class="s1">'GH:en'</span><span class="p">,</span>
|
|
<span class="s1">'GR:el'</span><span class="p">,</span>
|
|
<span class="s1">'HK:zh-Hant'</span><span class="p">,</span>
|
|
<span class="s1">'HU:hu'</span><span class="p">,</span>
|
|
<span class="s1">'ID:en'</span><span class="p">,</span>
|
|
<span class="s1">'ID:id'</span><span class="p">,</span>
|
|
<span class="s1">'IE:en'</span><span class="p">,</span>
|
|
<span class="s1">'IL:en'</span><span class="p">,</span>
|
|
<span class="s1">'IL:he'</span><span class="p">,</span>
|
|
<span class="s1">'IN:bn'</span><span class="p">,</span>
|
|
<span class="s1">'IN:en'</span><span class="p">,</span>
|
|
<span class="s1">'IN:hi'</span><span class="p">,</span>
|
|
<span class="s1">'IN:ml'</span><span class="p">,</span>
|
|
<span class="s1">'IN:mr'</span><span class="p">,</span>
|
|
<span class="s1">'IN:ta'</span><span class="p">,</span>
|
|
<span class="s1">'IN:te'</span><span class="p">,</span>
|
|
<span class="s1">'IT:it'</span><span class="p">,</span>
|
|
<span class="s1">'JP:ja'</span><span class="p">,</span>
|
|
<span class="s1">'KE:en'</span><span class="p">,</span>
|
|
<span class="s1">'KR:ko'</span><span class="p">,</span>
|
|
<span class="s1">'LB:ar'</span><span class="p">,</span>
|
|
<span class="s1">'LT:lt'</span><span class="p">,</span>
|
|
<span class="s1">'LV:en'</span><span class="p">,</span>
|
|
<span class="s1">'LV:lv'</span><span class="p">,</span>
|
|
<span class="s1">'MA:fr'</span><span class="p">,</span>
|
|
<span class="s1">'MX:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'MY:en'</span><span class="p">,</span>
|
|
<span class="s1">'NA:en'</span><span class="p">,</span>
|
|
<span class="s1">'NG:en'</span><span class="p">,</span>
|
|
<span class="s1">'NL:nl'</span><span class="p">,</span>
|
|
<span class="s1">'NO:no'</span><span class="p">,</span>
|
|
<span class="s1">'NZ:en'</span><span class="p">,</span>
|
|
<span class="s1">'PE:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'PH:en'</span><span class="p">,</span>
|
|
<span class="s1">'PK:en'</span><span class="p">,</span>
|
|
<span class="s1">'PL:pl'</span><span class="p">,</span>
|
|
<span class="s1">'PT:pt-150'</span><span class="p">,</span>
|
|
<span class="s1">'RO:ro'</span><span class="p">,</span>
|
|
<span class="s1">'RS:sr'</span><span class="p">,</span>
|
|
<span class="s1">'RU:ru'</span><span class="p">,</span>
|
|
<span class="s1">'SA:ar'</span><span class="p">,</span>
|
|
<span class="s1">'SE:sv'</span><span class="p">,</span>
|
|
<span class="s1">'SG:en'</span><span class="p">,</span>
|
|
<span class="s1">'SI:sl'</span><span class="p">,</span>
|
|
<span class="s1">'SK:sk'</span><span class="p">,</span>
|
|
<span class="s1">'SN:fr'</span><span class="p">,</span>
|
|
<span class="s1">'TH:th'</span><span class="p">,</span>
|
|
<span class="s1">'TR:tr'</span><span class="p">,</span>
|
|
<span class="s1">'TW:zh-Hant'</span><span class="p">,</span>
|
|
<span class="s1">'TZ:en'</span><span class="p">,</span>
|
|
<span class="s1">'UA:ru'</span><span class="p">,</span>
|
|
<span class="s1">'UA:uk'</span><span class="p">,</span>
|
|
<span class="s1">'UG:en'</span><span class="p">,</span>
|
|
<span class="s1">'US:en'</span><span class="p">,</span>
|
|
<span class="s1">'US:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'VE:es-419'</span><span class="p">,</span>
|
|
<span class="s1">'VN:vi'</span><span class="p">,</span>
|
|
<span class="s1">'ZA:en'</span><span class="p">,</span>
|
|
<span class="s1">'ZW:en'</span><span class="p">,</span>
|
|
<span class="p">]</span>
|
|
<span class="sd">"""List of region/language combinations supported by Google News. Values of the</span>
|
|
<span class="sd">``ceid`` argument of the Google News REST API."""</span>
|
|
|
|
|
|
<span class="n">_skip_values</span> <span class="o">=</span> <span class="p">[</span>
|
|
<span class="s1">'ET:en'</span><span class="p">,</span> <span class="c1"># english (ethiopia)</span>
|
|
<span class="s1">'ID:en'</span><span class="p">,</span> <span class="c1"># english (indonesia)</span>
|
|
<span class="s1">'LV:en'</span><span class="p">,</span> <span class="c1"># english (latvia)</span>
|
|
<span class="p">]</span>
|
|
|
|
<span class="n">_ceid_locale_map</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'NO:no'</span><span class="p">:</span> <span class="s1">'nb-NO'</span><span class="p">}</span>
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
|
|
<span class="n">_fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">,</span> <span class="n">add_domains</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
|
|
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">'ceid'</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
|
|
|
|
<span class="k">for</span> <span class="n">ceid</span> <span class="ow">in</span> <span class="n">ceid_list</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="n">ceid</span> <span class="ow">in</span> <span class="n">_skip_values</span><span class="p">:</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="n">region</span><span class="p">,</span> <span class="n">lang</span> <span class="o">=</span> <span class="n">ceid</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">':'</span><span class="p">)</span>
|
|
<span class="n">x</span> <span class="o">=</span> <span class="n">lang</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'-'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'Hant'</span><span class="p">,</span> <span class="s1">'Hans'</span><span class="p">]:</span>
|
|
<span class="n">lang</span> <span class="o">=</span> <span class="n">x</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
|
|
|
<span class="n">sxng_locale</span> <span class="o">=</span> <span class="n">_ceid_locale_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">ceid</span><span class="p">,</span> <span class="n">lang</span> <span class="o">+</span> <span class="s1">'-'</span> <span class="o">+</span> <span class="n">region</span><span class="p">)</span>
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="n">locale</span> <span class="o">=</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">sxng_locale</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s1">'-'</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="nb">print</span><span class="p">(</span><span class="s2">"ERROR: </span><span class="si">%s</span><span class="s2"> -> </span><span class="si">%s</span><span class="s2"> is unknown by babel"</span> <span class="o">%</span> <span class="p">(</span><span class="n">ceid</span><span class="p">,</span> <span class="n">sxng_locale</span><span class="p">))</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">'ceid'</span><span class="p">][</span><span class="n">locales</span><span class="o">.</span><span class="n">region_tag</span><span class="p">(</span><span class="n">locale</span><span class="p">)]</span> <span class="o">=</span> <span class="n">ceid</span>
|
|
</pre></div>
|
|
|
|
<div class="clearer"></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<span id="sidebar-top"></span>
|
|
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
|
<div class="sphinxsidebarwrapper">
|
|
|
|
|
|
<p class="logo"><a href="../../../index.html">
|
|
<img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo"/>
|
|
</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/Fauli1221/PonySearch/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>
|
|
<script src="../../../_static/version_warning_offset.js"></script>
|
|
|
|
</body>
|
|
</html> |