forked from Ponysearch/Ponysearch
586 lines
61 KiB
HTML
586 lines
61 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.duckduckgo — 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.duckduckgo</a></li>
|
||
|
|
</ul>
|
||
|
|
</div>
|
||
|
|
|
||
|
|
<div class="document">
|
||
|
|
<div class="documentwrapper">
|
||
|
|
<div class="bodywrapper">
|
||
|
|
<div class="body" role="main">
|
||
|
|
|
||
|
|
<h1>Source code for searx.engines.duckduckgo</h1><div class="highlight"><pre>
|
||
|
|
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
||
|
|
<span class="sd">"""</span>
|
||
|
|
<span class="sd">DuckDuckGo Lite</span>
|
||
|
|
<span class="sd">~~~~~~~~~~~~~~~</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">import</span> <span class="nn">re</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">json</span>
|
||
|
|
<span class="kn">import</span> <span class="nn">babel</span>
|
||
|
|
<span class="kn">import</span> <span class="nn">lxml.html</span>
|
||
|
|
|
||
|
|
<span class="kn">from</span> <span class="nn">searx</span> <span class="kn">import</span> <span class="p">(</span>
|
||
|
|
<span class="n">locales</span><span class="p">,</span>
|
||
|
|
<span class="n">redislib</span><span class="p">,</span>
|
||
|
|
<span class="n">external_bang</span><span class="p">,</span>
|
||
|
|
<span class="p">)</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_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.network</span> <span class="kn">import</span> <span class="n">get</span> <span class="c1"># see https://github.com/searxng/searxng/issues/762</span>
|
||
|
|
<span class="kn">from</span> <span class="nn">searx</span> <span class="kn">import</span> <span class="n">redisdb</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="n">about</span> <span class="o">=</span> <span class="p">{</span>
|
||
|
|
<span class="s2">"website"</span><span class="p">:</span> <span class="s1">'https://lite.duckduckgo.com/lite/'</span><span class="p">,</span>
|
||
|
|
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s1">'Q12805'</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="n">send_accept_language_header</span> <span class="o">=</span> <span class="kc">True</span>
|
||
|
|
<span class="sd">"""DuckDuckGo-Lite tries to guess user's prefered language from the HTTP</span>
|
||
|
|
<span class="sd">``Accept-Language``. Optional the user can select a region filter (but not a</span>
|
||
|
|
<span class="sd">language).</span>
|
||
|
|
<span class="sd">"""</span>
|
||
|
|
|
||
|
|
<span class="c1"># engine dependent config</span>
|
||
|
|
<span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'general'</span><span class="p">,</span> <span class="s1">'web'</span><span class="p">]</span>
|
||
|
|
<span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
|
||
|
|
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
|
||
|
|
<span class="n">safesearch</span> <span class="o">=</span> <span class="kc">True</span> <span class="c1"># user can't select but the results are filtered</span>
|
||
|
|
|
||
|
|
<span class="n">url</span> <span class="o">=</span> <span class="s1">'https://lite.duckduckgo.com/lite/'</span>
|
||
|
|
<span class="c1"># url_ping = 'https://duckduckgo.com/t/sl_l'</span>
|
||
|
|
|
||
|
|
<span class="n">time_range_dict</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'day'</span><span class="p">:</span> <span class="s1">'d'</span><span class="p">,</span> <span class="s1">'week'</span><span class="p">:</span> <span class="s1">'w'</span><span class="p">,</span> <span class="s1">'month'</span><span class="p">:</span> <span class="s1">'m'</span><span class="p">,</span> <span class="s1">'year'</span><span class="p">:</span> <span class="s1">'y'</span><span class="p">}</span>
|
||
|
|
<span class="n">form_data</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'v'</span><span class="p">:</span> <span class="s1">'l'</span><span class="p">,</span> <span class="s1">'api'</span><span class="p">:</span> <span class="s1">'d.js'</span><span class="p">,</span> <span class="s1">'o'</span><span class="p">:</span> <span class="s1">'json'</span><span class="p">}</span>
|
||
|
|
|
||
|
|
|
||
|
|
<div class="viewcode-block" id="cache_vqd">
|
||
|
|
<a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.cache_vqd">[docs]</a>
|
||
|
|
<span class="k">def</span> <span class="nf">cache_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
|
||
|
|
<span class="w"> </span><span class="sd">"""Caches a ``vqd`` value from a query."""</span>
|
||
|
|
<span class="n">c</span> <span class="o">=</span> <span class="n">redisdb</span><span class="o">.</span><span class="n">client</span><span class="p">()</span>
|
||
|
|
<span class="k">if</span> <span class="n">c</span><span class="p">:</span>
|
||
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"cache vqd value: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
||
|
|
<span class="n">key</span> <span class="o">=</span> <span class="s1">'SearXNG_ddg_web_vqd'</span> <span class="o">+</span> <span class="n">redislib</span><span class="o">.</span><span class="n">secret_hash</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
|
||
|
|
<span class="n">c</span><span class="o">.</span><span class="n">set</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">ex</span><span class="o">=</span><span class="mi">600</span><span class="p">)</span></div>
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
<div class="viewcode-block" id="get_vqd">
|
||
|
|
<a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.get_vqd">[docs]</a>
|
||
|
|
<span class="k">def</span> <span class="nf">get_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">):</span>
|
||
|
|
<span class="w"> </span><span class="sd">"""Returns the ``vqd`` that fits to the *query*. If there is no ``vqd`` cached</span>
|
||
|
|
<span class="sd"> (:py:obj:`cache_vqd`) the query is sent to DDG to get a vqd value from the</span>
|
||
|
|
<span class="sd"> response.</span>
|
||
|
|
|
||
|
|
<span class="sd"> .. hint::</span>
|
||
|
|
|
||
|
|
<span class="sd"> If an empty string is returned there are no results for the ``query`` and</span>
|
||
|
|
<span class="sd"> therefore no ``vqd`` value.</span>
|
||
|
|
|
||
|
|
<span class="sd"> DDG's bot detection is sensitive to the ``vqd`` value. For some search terms</span>
|
||
|
|
<span class="sd"> (such as extremely long search terms that are often sent by bots), no ``vqd``</span>
|
||
|
|
<span class="sd"> value can be determined.</span>
|
||
|
|
|
||
|
|
<span class="sd"> If SearXNG cannot determine a ``vqd`` value, then no request should go out</span>
|
||
|
|
<span class="sd"> to DDG:</span>
|
||
|
|
|
||
|
|
<span class="sd"> A request with a wrong ``vqd`` value leads to DDG temporarily putting</span>
|
||
|
|
<span class="sd"> SearXNG's IP on a block list.</span>
|
||
|
|
|
||
|
|
<span class="sd"> Requests from IPs in this block list run into timeouts.</span>
|
||
|
|
|
||
|
|
<span class="sd"> Not sure, but it seems the block list is a sliding window: to get my IP rid</span>
|
||
|
|
<span class="sd"> from the bot list I had to cool down my IP for 1h (send no requests from</span>
|
||
|
|
<span class="sd"> that IP to DDG).</span>
|
||
|
|
|
||
|
|
<span class="sd"> TL;DR; the ``vqd`` value is needed to pass DDG's bot protection and is used</span>
|
||
|
|
<span class="sd"> by all request to DDG:</span>
|
||
|
|
|
||
|
|
<span class="sd"> - DuckDuckGo Lite: ``https://lite.duckduckgo.com/lite`` (POST form data)</span>
|
||
|
|
<span class="sd"> - DuckDuckGo Web: ``https://links.duckduckgo.com/d.js?q=...&vqd=...``</span>
|
||
|
|
<span class="sd"> - DuckDuckGo Images: ``https://duckduckgo.com/i.js??q=...&vqd=...``</span>
|
||
|
|
<span class="sd"> - DuckDuckGo Videos: ``https://duckduckgo.com/v.js??q=...&vqd=...``</span>
|
||
|
|
<span class="sd"> - DuckDuckGo News: ``https://duckduckgo.com/news.js??q=...&vqd=...``</span>
|
||
|
|
|
||
|
|
<span class="sd"> """</span>
|
||
|
|
<span class="n">value</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
|
<span class="n">c</span> <span class="o">=</span> <span class="n">redisdb</span><span class="o">.</span><span class="n">client</span><span class="p">()</span>
|
||
|
|
<span class="k">if</span> <span class="n">c</span><span class="p">:</span>
|
||
|
|
<span class="n">key</span> <span class="o">=</span> <span class="s1">'SearXNG_ddg_web_vqd'</span> <span class="o">+</span> <span class="n">redislib</span><span class="o">.</span><span class="n">secret_hash</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
|
||
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">c</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">key</span><span class="p">)</span>
|
||
|
|
<span class="k">if</span> <span class="n">value</span> <span class="ow">or</span> <span class="n">value</span> <span class="o">==</span> <span class="sa">b</span><span class="s1">''</span><span class="p">:</span>
|
||
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">value</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span>
|
||
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"re-use cached vqd value: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
||
|
|
<span class="k">return</span> <span class="n">value</span>
|
||
|
|
|
||
|
|
<span class="n">query_url</span> <span class="o">=</span> <span class="s1">'https://duckduckgo.com/?'</span> <span class="o">+</span> <span class="n">urlencode</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="n">res</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="n">query_url</span><span class="p">)</span>
|
||
|
|
<span class="n">doc</span> <span class="o">=</span> <span class="n">lxml</span><span class="o">.</span><span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">res</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
|
||
|
|
<span class="k">for</span> <span class="n">script</span> <span class="ow">in</span> <span class="n">doc</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s2">"//script[@type='text/javascript']"</span><span class="p">):</span>
|
||
|
|
<span class="n">script</span> <span class="o">=</span> <span class="n">script</span><span class="o">.</span><span class="n">text</span>
|
||
|
|
<span class="k">if</span> <span class="s1">'vqd="'</span> <span class="ow">in</span> <span class="n">script</span><span class="p">:</span>
|
||
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">script</span><span class="p">[</span><span class="n">script</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s1">'vqd="'</span><span class="p">)</span> <span class="o">+</span> <span class="mi">5</span> <span class="p">:]</span>
|
||
|
|
<span class="n">value</span> <span class="o">=</span> <span class="n">value</span><span class="p">[:</span> <span class="n">value</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s1">'"'</span><span class="p">)]</span>
|
||
|
|
<span class="k">break</span>
|
||
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"new vqd value: '</span><span class="si">%s</span><span class="s2">'"</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
||
|
|
<span class="k">if</span> <span class="n">value</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
|
<span class="n">cache_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span>
|
||
|
|
<span class="k">return</span> <span class="n">value</span></div>
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
<div class="viewcode-block" id="get_ddg_lang">
|
||
|
|
<a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.get_ddg_lang">[docs]</a>
|
||
|
|
<span class="k">def</span> <span class="nf">get_ddg_lang</span><span class="p">(</span><span class="n">eng_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">,</span> <span class="n">sxng_locale</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s1">'en_US'</span><span class="p">):</span>
|
||
|
|
<span class="w"> </span><span class="sd">"""Get DuckDuckGo's language identifier from SearXNG's locale.</span>
|
||
|
|
|
||
|
|
<span class="sd"> DuckDuckGo defines its languages by region codes (see</span>
|
||
|
|
<span class="sd"> :py:obj:`fetch_traits`).</span>
|
||
|
|
|
||
|
|
<span class="sd"> To get region and language of a DDG service use:</span>
|
||
|
|
|
||
|
|
<span class="sd"> .. code: python</span>
|
||
|
|
|
||
|
|
<span class="sd"> eng_region = traits.get_region(params['searxng_locale'], traits.all_locale)</span>
|
||
|
|
<span class="sd"> eng_lang = get_ddg_lang(traits, params['searxng_locale'])</span>
|
||
|
|
|
||
|
|
<span class="sd"> It might confuse, but the ``l`` value of the cookie is what SearXNG calls</span>
|
||
|
|
<span class="sd"> the *region*:</span>
|
||
|
|
|
||
|
|
<span class="sd"> .. code:: python</span>
|
||
|
|
|
||
|
|
<span class="sd"> # !ddi paris :es-AR --> {'ad': 'es_AR', 'ah': 'ar-es', 'l': 'ar-es'}</span>
|
||
|
|
<span class="sd"> params['cookies']['ad'] = eng_lang</span>
|
||
|
|
<span class="sd"> params['cookies']['ah'] = eng_region</span>
|
||
|
|
<span class="sd"> params['cookies']['l'] = eng_region</span>
|
||
|
|
|
||
|
|
<span class="sd"> .. hint::</span>
|
||
|
|
|
||
|
|
<span class="sd"> `DDG-lite <https://lite.duckduckgo.com/lite>`__ does not offer a language</span>
|
||
|
|
<span class="sd"> selection to the user, only a region can be selected by the user</span>
|
||
|
|
<span class="sd"> (``eng_region`` from the example above). DDG-lite stores the selected</span>
|
||
|
|
<span class="sd"> region in a cookie::</span>
|
||
|
|
|
||
|
|
<span class="sd"> params['cookies']['kl'] = eng_region # 'ar-es'</span>
|
||
|
|
|
||
|
|
<span class="sd"> """</span>
|
||
|
|
<span class="k">return</span> <span class="n">eng_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">'lang_region'</span><span class="p">]</span><span class="o">.</span><span class="n">get</span><span class="p">(</span> <span class="c1"># type: ignore</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="n">default</span><span class="p">)</span>
|
||
|
|
<span class="p">)</span></div>
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
<span class="n">ddg_reg_map</span> <span class="o">=</span> <span class="p">{</span>
|
||
|
|
<span class="s1">'tw-tzh'</span><span class="p">:</span> <span class="s1">'zh_TW'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'hk-tzh'</span><span class="p">:</span> <span class="s1">'zh_HK'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'ct-ca'</span><span class="p">:</span> <span class="s1">'skip'</span><span class="p">,</span> <span class="c1"># ct-ca and es-ca both map to ca_ES</span>
|
||
|
|
<span class="s1">'es-ca'</span><span class="p">:</span> <span class="s1">'ca_ES'</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">'no-no'</span><span class="p">:</span> <span class="s1">'nb_NO'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'jp-jp'</span><span class="p">:</span> <span class="s1">'ja_JP'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'kr-kr'</span><span class="p">:</span> <span class="s1">'ko_KR'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'xa-ar'</span><span class="p">:</span> <span class="s1">'ar_SA'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'sl-sl'</span><span class="p">:</span> <span class="s1">'sl_SI'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'th-en'</span><span class="p">:</span> <span class="s1">'th_TH'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'vn-en'</span><span class="p">:</span> <span class="s1">'vi_VN'</span><span class="p">,</span>
|
||
|
|
<span class="p">}</span>
|
||
|
|
|
||
|
|
<span class="n">ddg_lang_map</span> <span class="o">=</span> <span class="p">{</span>
|
||
|
|
<span class="c1"># use ar --> ar_EG (Egypt's arabic)</span>
|
||
|
|
<span class="s2">"ar_DZ"</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s2">"ar_JO"</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s2">"ar_SA"</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># use bn --> bn_BD</span>
|
||
|
|
<span class="s1">'bn_IN'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># use de --> de_DE</span>
|
||
|
|
<span class="s1">'de_CH'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># use en --> en_US,</span>
|
||
|
|
<span class="s1">'en_AU'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'en_CA'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'en_GB'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># Esperanto</span>
|
||
|
|
<span class="s1">'eo_XX'</span><span class="p">:</span> <span class="s1">'eo'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># use es --> es_ES,</span>
|
||
|
|
<span class="s1">'es_AR'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_CL'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_CO'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_CR'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_EC'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_MX'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_PE'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_UY'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'es_VE'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># use fr --> rf_FR</span>
|
||
|
|
<span class="s1">'fr_CA'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'fr_CH'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'fr_BE'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># use nl --> nl_NL</span>
|
||
|
|
<span class="s1">'nl_BE'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># use pt --> pt_PT</span>
|
||
|
|
<span class="s1">'pt_BR'</span><span class="p">:</span> <span class="s1">'lang_region'</span><span class="p">,</span>
|
||
|
|
<span class="c1"># skip these languages</span>
|
||
|
|
<span class="s1">'od_IN'</span><span class="p">:</span> <span class="s1">'skip'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'io_XX'</span><span class="p">:</span> <span class="s1">'skip'</span><span class="p">,</span>
|
||
|
|
<span class="s1">'tokipona_XX'</span><span class="p">:</span> <span class="s1">'skip'</span><span class="p">,</span>
|
||
|
|
<span class="p">}</span>
|
||
|
|
|
||
|
|
|
||
|
|
<span class="k">def</span> <span class="nf">quote_ddg_bangs</span><span class="p">(</span><span class="n">query</span><span class="p">):</span>
|
||
|
|
<span class="c1"># quote ddg bangs</span>
|
||
|
|
<span class="n">query_parts</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
|
|
||
|
|
<span class="c1"># for val in re.split(r'(\s+)', query):</span>
|
||
|
|
<span class="k">for</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">r</span><span class="s1">'(\s+)'</span><span class="p">,</span> <span class="n">query</span><span class="p">):</span>
|
||
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">val</span><span class="o">.</span><span class="n">strip</span><span class="p">():</span>
|
||
|
|
<span class="k">continue</span>
|
||
|
|
<span class="k">if</span> <span class="n">val</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'!'</span><span class="p">)</span> <span class="ow">and</span> <span class="n">external_bang</span><span class="o">.</span><span class="n">get_node</span><span class="p">(</span><span class="n">external_bang</span><span class="o">.</span><span class="n">EXTERNAL_BANGS</span><span class="p">,</span> <span class="n">val</span><span class="p">[</span><span class="mi">1</span><span class="p">:]):</span>
|
||
|
|
<span class="n">val</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"'</span><span class="si">{</span><span class="n">val</span><span class="si">}</span><span class="s2">'"</span>
|
||
|
|
<span class="n">query_parts</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">val</span><span class="p">)</span>
|
||
|
|
<span class="k">return</span> <span class="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">query_parts</span><span class="p">)</span>
|
||
|
|
|
||
|
|
|
||
|
|
<span class="k">def</span> <span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
|
||
|
|
|
||
|
|
<span class="n">query</span> <span class="o">=</span> <span class="n">quote_ddg_bangs</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="c1"># request needs a vqd argument</span>
|
||
|
|
<span class="n">vqd</span> <span class="o">=</span> <span class="n">get_vqd</span><span class="p">(</span><span class="n">query</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="n">eng_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="s1">'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="c1"># eng_lang = get_ddg_lang(traits, params['searxng_locale'])</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">url</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'method'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'POST'</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'q'</span><span class="p">]</span> <span class="o">=</span> <span class="n">query</span>
|
||
|
|
|
||
|
|
<span class="c1"># The API is not documented, so we do some reverse engineering and emulate</span>
|
||
|
|
<span class="c1"># what https://lite.duckduckgo.com/lite/ does when you press "next Page"</span>
|
||
|
|
<span class="c1"># link again and again ..</span>
|
||
|
|
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">][</span><span class="s1">'Content-Type'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'application/x-www-form-urlencoded'</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'vqd'</span><span class="p">]</span> <span class="o">=</span> <span class="n">vqd</span>
|
||
|
|
|
||
|
|
<span class="c1"># initial page does not have an offset</span>
|
||
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'pageno'</span><span class="p">]</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
|
||
|
|
<span class="c1"># second page does have an offset of 20</span>
|
||
|
|
<span class="n">offset</span> <span class="o">=</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">'pageno'</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="mi">20</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'s'</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'dc'</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span> <span class="o">+</span> <span class="mi">1</span>
|
||
|
|
|
||
|
|
<span class="k">elif</span> <span class="n">params</span><span class="p">[</span><span class="s1">'pageno'</span><span class="p">]</span> <span class="o">></span> <span class="mi">2</span><span class="p">:</span>
|
||
|
|
<span class="c1"># third and following pages do have an offset of 20 + n*50</span>
|
||
|
|
<span class="n">offset</span> <span class="o">=</span> <span class="mi">20</span> <span class="o">+</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">'pageno'</span><span class="p">]</span> <span class="o">-</span> <span class="mi">2</span><span class="p">)</span> <span class="o">*</span> <span class="mi">50</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'s'</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'dc'</span><span class="p">]</span> <span class="o">=</span> <span class="n">offset</span> <span class="o">+</span> <span class="mi">1</span>
|
||
|
|
|
||
|
|
<span class="c1"># initial page does not have additional data in the input form</span>
|
||
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'pageno'</span><span class="p">]</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span>
|
||
|
|
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'o'</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'o'</span><span class="p">,</span> <span class="s1">'json'</span><span class="p">)</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'api'</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'api'</span><span class="p">,</span> <span class="s1">'d.js'</span><span class="p">)</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'nextParams'</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'nextParams'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'v'</span><span class="p">]</span> <span class="o">=</span> <span class="n">form_data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'v'</span><span class="p">,</span> <span class="s1">'l'</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="s1">'Referer'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'https://lite.duckduckgo.com/'</span>
|
||
|
|
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'kl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_region</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">][</span><span class="s1">'kl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_region</span>
|
||
|
|
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'df'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">''</span>
|
||
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'time_range'</span><span class="p">]</span> <span class="ow">in</span> <span class="n">time_range_dict</span><span class="p">:</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="s1">'df'</span><span class="p">]</span> <span class="o">=</span> <span class="n">time_range_dict</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s1">'time_range'</span><span class="p">]]</span>
|
||
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">][</span><span class="s1">'df'</span><span class="p">]</span> <span class="o">=</span> <span class="n">time_range_dict</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s1">'time_range'</span><span class="p">]]</span>
|
||
|
|
|
||
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"param data: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">params</span><span class="p">[</span><span class="s1">'data'</span><span class="p">])</span>
|
||
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"param cookies: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">])</span>
|
||
|
|
<span class="k">return</span> <span class="n">params</span>
|
||
|
|
|
||
|
|
|
||
|
|
<span class="k">def</span> <span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
|
||
|
|
|
||
|
|
<span class="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">303</span><span class="p">:</span>
|
||
|
|
<span class="k">return</span> <span class="p">[]</span>
|
||
|
|
|
||
|
|
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
|
<span class="n">doc</span> <span class="o">=</span> <span class="n">lxml</span><span class="o">.</span><span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="n">result_table</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="s1">'//html/body/form/div[@class="filters"]/table'</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">result_table</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
|
||
|
|
<span class="c1"># some locales (at least China) does not have a "next page" button and</span>
|
||
|
|
<span class="c1"># the layout of the HTML tables is different.</span>
|
||
|
|
<span class="n">result_table</span> <span class="o">=</span> <span class="n">result_table</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
||
|
|
<span class="k">elif</span> <span class="ow">not</span> <span class="nb">len</span><span class="p">(</span><span class="n">result_table</span><span class="p">)</span> <span class="o">>=</span> <span class="mi">3</span><span class="p">:</span>
|
||
|
|
<span class="c1"># no more results</span>
|
||
|
|
<span class="k">return</span> <span class="p">[]</span>
|
||
|
|
<span class="k">else</span><span class="p">:</span>
|
||
|
|
<span class="n">result_table</span> <span class="o">=</span> <span class="n">result_table</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
|
||
|
|
<span class="c1"># update form data from response</span>
|
||
|
|
<span class="n">form</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">doc</span><span class="p">,</span> <span class="s1">'//html/body/form/div[@class="filters"]/table//input/..'</span><span class="p">)</span>
|
||
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">form</span><span class="p">):</span>
|
||
|
|
|
||
|
|
<span class="n">form</span> <span class="o">=</span> <span class="n">form</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
|
||
|
|
<span class="n">form_data</span><span class="p">[</span><span class="s1">'v'</span><span class="p">]</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">form</span><span class="p">,</span> <span class="s1">'//input[@name="v"]/@value'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
||
|
|
<span class="n">form_data</span><span class="p">[</span><span class="s1">'api'</span><span class="p">]</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">form</span><span class="p">,</span> <span class="s1">'//input[@name="api"]/@value'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
||
|
|
<span class="n">form_data</span><span class="p">[</span><span class="s1">'o'</span><span class="p">]</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">form</span><span class="p">,</span> <span class="s1">'//input[@name="o"]/@value'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
||
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">'form_data: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">form_data</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="n">tr_rows</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">result_table</span><span class="p">,</span> <span class="s1">'.//tr'</span><span class="p">)</span>
|
||
|
|
<span class="c1"># In the last <tr> is the form of the 'previous/next page' links</span>
|
||
|
|
<span class="n">tr_rows</span> <span class="o">=</span> <span class="n">tr_rows</span><span class="p">[:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
||
|
|
|
||
|
|
<span class="n">len_tr_rows</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">tr_rows</span><span class="p">)</span>
|
||
|
|
<span class="n">offset</span> <span class="o">=</span> <span class="mi">0</span>
|
||
|
|
|
||
|
|
<span class="k">while</span> <span class="n">len_tr_rows</span> <span class="o">>=</span> <span class="n">offset</span> <span class="o">+</span> <span class="mi">4</span><span class="p">:</span>
|
||
|
|
|
||
|
|
<span class="c1"># assemble table rows we need to scrap</span>
|
||
|
|
<span class="n">tr_title</span> <span class="o">=</span> <span class="n">tr_rows</span><span class="p">[</span><span class="n">offset</span><span class="p">]</span>
|
||
|
|
<span class="n">tr_content</span> <span class="o">=</span> <span class="n">tr_rows</span><span class="p">[</span><span class="n">offset</span> <span class="o">+</span> <span class="mi">1</span><span class="p">]</span>
|
||
|
|
<span class="n">offset</span> <span class="o">+=</span> <span class="mi">4</span>
|
||
|
|
|
||
|
|
<span class="c1"># ignore sponsored Adds <tr class="result-sponsored"></span>
|
||
|
|
<span class="k">if</span> <span class="n">tr_content</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'class'</span><span class="p">)</span> <span class="o">==</span> <span class="s1">'result-sponsored'</span><span class="p">:</span>
|
||
|
|
<span class="k">continue</span>
|
||
|
|
|
||
|
|
<span class="n">a_tag</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">tr_title</span><span class="p">,</span> <span class="s1">'.//td//a[@class="result-link"]'</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">a_tag</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
|
<span class="k">continue</span>
|
||
|
|
|
||
|
|
<span class="n">td_content</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">tr_content</span><span class="p">,</span> <span class="s1">'.//td[@class="result-snippet"]'</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">td_content</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
|
<span class="k">continue</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">'title'</span><span class="p">:</span> <span class="n">a_tag</span><span class="o">.</span><span class="n">text_content</span><span class="p">(),</span>
|
||
|
|
<span class="s1">'content'</span><span class="p">:</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">td_content</span><span class="p">),</span>
|
||
|
|
<span class="s1">'url'</span><span class="p">:</span> <span class="n">a_tag</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'href'</span><span class="p">),</span>
|
||
|
|
<span class="p">}</span>
|
||
|
|
<span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="k">return</span> <span class="n">results</span>
|
||
|
|
|
||
|
|
|
||
|
|
<div class="viewcode-block" id="fetch_traits">
|
||
|
|
<a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo.fetch_traits">[docs]</a>
|
||
|
|
<span class="k">def</span> <span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
|
||
|
|
<span class="w"> </span><span class="sd">"""Fetch languages & regions from DuckDuckGo.</span>
|
||
|
|
|
||
|
|
<span class="sd"> SearXNG's ``all`` locale maps DuckDuckGo's "Alle regions" (``wt-wt``).</span>
|
||
|
|
<span class="sd"> DuckDuckGo's language "Browsers prefered language" (``wt_WT``) makes no</span>
|
||
|
|
<span class="sd"> sense in a SearXNG request since SearXNG's ``all`` will not add a</span>
|
||
|
|
<span class="sd"> ``Accept-Language`` HTTP header. The value in ``engine_traits.all_locale``</span>
|
||
|
|
<span class="sd"> is ``wt-wt`` (the region).</span>
|
||
|
|
|
||
|
|
<span class="sd"> Beside regions DuckDuckGo also defines its languages by region codes. By</span>
|
||
|
|
<span class="sd"> example these are the english languages in DuckDuckGo:</span>
|
||
|
|
|
||
|
|
<span class="sd"> - en_US</span>
|
||
|
|
<span class="sd"> - en_AU</span>
|
||
|
|
<span class="sd"> - en_CA</span>
|
||
|
|
<span class="sd"> - en_GB</span>
|
||
|
|
|
||
|
|
<span class="sd"> The function :py:obj:`get_ddg_lang` evaluates DuckDuckGo's language from</span>
|
||
|
|
<span class="sd"> SearXNG's locale.</span>
|
||
|
|
|
||
|
|
<span class="sd"> """</span>
|
||
|
|
<span class="c1"># pylint: disable=too-many-branches, too-many-statements</span>
|
||
|
|
<span class="c1"># fetch regions</span>
|
||
|
|
|
||
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">all_locale</span> <span class="o">=</span> <span class="s1">'wt-wt'</span>
|
||
|
|
|
||
|
|
<span class="c1"># updated from u661.js to u.7669f071a13a7daa57cb / should be updated automatically?</span>
|
||
|
|
<span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s1">'https://duckduckgo.com/dist/util/u.7669f071a13a7daa57cb.js'</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">ok</span><span class="p">:</span> <span class="c1"># type: ignore</span>
|
||
|
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"ERROR: response from DuckDuckGo is not OK."</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="n">pos</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'regions:{'</span><span class="p">)</span> <span class="o">+</span> <span class="mi">8</span> <span class="c1"># type: ignore</span>
|
||
|
|
<span class="n">js_code</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">[</span><span class="n">pos</span><span class="p">:]</span> <span class="c1"># type: ignore</span>
|
||
|
|
<span class="n">pos</span> <span class="o">=</span> <span class="n">js_code</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'}'</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span>
|
||
|
|
<span class="n">regions</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">js_code</span><span class="p">[:</span><span class="n">pos</span><span class="p">])</span>
|
||
|
|
|
||
|
|
<span class="k">for</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">regions</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||
|
|
|
||
|
|
<span class="k">if</span> <span class="n">eng_tag</span> <span class="o">==</span> <span class="s1">'wt-wt'</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="s1">'wt-wt'</span>
|
||
|
|
<span class="k">continue</span>
|
||
|
|
|
||
|
|
<span class="n">region</span> <span class="o">=</span> <span class="n">ddg_reg_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="k">if</span> <span class="n">region</span> <span class="o">==</span> <span class="s1">'skip'</span><span class="p">:</span>
|
||
|
|
<span class="k">continue</span>
|
||
|
|
|
||
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">region</span><span class="p">:</span>
|
||
|
|
<span class="n">eng_territory</span><span class="p">,</span> <span class="n">eng_lang</span> <span class="o">=</span> <span class="n">eng_tag</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">region</span> <span class="o">=</span> <span class="n">eng_lang</span> <span class="o">+</span> <span class="s1">'_'</span> <span class="o">+</span> <span class="n">eng_territory</span><span class="o">.</span><span class="n">upper</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">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="n">region</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">) -> </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">name</span><span class="p">,</span> <span class="n">eng_tag</span><span class="p">,</span> <span class="n">region</span><span class="p">))</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">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">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="c1"># fetch languages</span>
|
||
|
|
|
||
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">'lang_region'</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
|
||
|
|
|
||
|
|
<span class="n">pos</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'languages:{'</span><span class="p">)</span> <span class="o">+</span> <span class="mi">10</span> <span class="c1"># type: ignore</span>
|
||
|
|
<span class="n">js_code</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">[</span><span class="n">pos</span><span class="p">:]</span> <span class="c1"># type: ignore</span>
|
||
|
|
<span class="n">pos</span> <span class="o">=</span> <span class="n">js_code</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s1">'}'</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span>
|
||
|
|
<span class="n">js_code</span> <span class="o">=</span> <span class="s1">'{"'</span> <span class="o">+</span> <span class="n">js_code</span><span class="p">[</span><span class="mi">1</span><span class="p">:</span><span class="n">pos</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">':'</span><span class="p">,</span> <span class="s1">'":'</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">','</span><span class="p">,</span> <span class="s1">',"'</span><span class="p">)</span>
|
||
|
|
<span class="n">languages</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">js_code</span><span class="p">)</span>
|
||
|
|
|
||
|
|
<span class="k">for</span> <span class="n">eng_lang</span><span class="p">,</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">languages</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
||
|
|
|
||
|
|
<span class="k">if</span> <span class="n">eng_lang</span> <span class="o">==</span> <span class="s1">'wt_WT'</span><span class="p">:</span>
|
||
|
|
<span class="k">continue</span>
|
||
|
|
|
||
|
|
<span class="n">babel_tag</span> <span class="o">=</span> <span class="n">ddg_lang_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">eng_lang</span><span class="p">,</span> <span class="n">eng_lang</span><span class="p">)</span>
|
||
|
|
<span class="k">if</span> <span class="n">babel_tag</span> <span class="o">==</span> <span class="s1">'skip'</span><span class="p">:</span>
|
||
|
|
<span class="k">continue</span>
|
||
|
|
|
||
|
|
<span class="k">try</span><span class="p">:</span>
|
||
|
|
|
||
|
|
<span class="k">if</span> <span class="n">babel_tag</span> <span class="o">==</span> <span class="s1">'lang_region'</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">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="n">eng_lang</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">'lang_region'</span><span class="p">][</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">eng_lang</span>
|
||
|
|
<span class="k">continue</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">babel_tag</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: language </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">name</span><span class="p">,</span> <span class="n">eng_lang</span><span class="p">))</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_lang</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_lang</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_lang</span></div>
|
||
|
|
|
||
|
|
</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>
|