mirror of https://github.com/searxng/searxng.git
372 lines
43 KiB
HTML
372 lines
43 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_definitions — SearXNG Documentation (2024.10.31+fa108c140)</title>
|
||
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=4f649999" />
|
||
|
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
|
||
|
<link rel="stylesheet" type="text/css" href="../../../_static/autodoc_pydantic.css" />
|
||
|
<script src="../../../_static/documentation_options.js?v=b20e5003"></script>
|
||
|
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
|
||
|
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
|
<script data-project="searxng" data-version="2024.10.31+fa108c140" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
|
||
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
||
|
<link rel="search" title="Search" href="../../../search.html" />
|
||
|
</head><body>
|
||
|
<div class="related" role="navigation" aria-label="Related">
|
||
|
<h3>Navigation</h3>
|
||
|
<ul>
|
||
|
<li class="right" style="margin-right: 10px">
|
||
|
<a href="../../../genindex.html" title="General Index"
|
||
|
accesskey="I">index</a></li>
|
||
|
<li class="right" >
|
||
|
<a href="../../../py-modindex.html" title="Python Module Index"
|
||
|
>modules</a> |</li>
|
||
|
<li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2024.10.31+fa108c140)</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_definitions</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_definitions</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 Instant Answer API</span>
|
||
|
<span class="sd">~~~~~~~~~~~~~~~~~~~~~~~~~~~~~</span>
|
||
|
|
||
|
<span class="sd">The `DDG-API <https://duckduckgo.com/api>`__ is no longer documented but from</span>
|
||
|
<span class="sd">reverse engineering we can see that some services (e.g. instant answers) still</span>
|
||
|
<span class="sd">in use from the DDG search engine.</span>
|
||
|
|
||
|
<span class="sd">As far we can say the *instant answers* API does not support languages, or at</span>
|
||
|
<span class="sd">least we could not find out how language support should work. It seems that</span>
|
||
|
<span class="sd">most of the features are based on English terms.</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="p">,</span> <span class="n">urlparse</span><span class="p">,</span> <span class="n">urljoin</span>
|
||
|
<span class="kn">from</span> <span class="nn">lxml</span> <span class="kn">import</span> <span class="n">html</span>
|
||
|
|
||
|
<span class="kn">from</span> <span class="nn">searx.data</span> <span class="kn">import</span> <span class="n">WIKIDATA_UNITS</span>
|
||
|
<span class="kn">from</span> <span class="nn">searx.utils</span> <span class="kn">import</span> <span class="n">extract_text</span><span class="p">,</span> <span class="n">html_to_text</span><span class="p">,</span> <span class="n">get_string_replaces_function</span>
|
||
|
<span class="kn">from</span> <span class="nn">searx.external_urls</span> <span class="kn">import</span> <span class="n">get_external_url</span><span class="p">,</span> <span class="n">get_earth_coordinates_url</span><span class="p">,</span> <span class="n">area_to_osm_zoom</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="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://duckduckgo.com/'</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">"official_api_documentation"</span><span class="p">:</span> <span class="s1">'https://duckduckgo.com/api'</span><span class="p">,</span>
|
||
|
<span class="s2">"use_official_api"</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span>
|
||
|
<span class="s2">"require_api_key"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
||
|
<span class="s2">"results"</span><span class="p">:</span> <span class="s1">'JSON'</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="n">URL</span> <span class="o">=</span> <span class="s1">'https://api.duckduckgo.com/'</span> <span class="o">+</span> <span class="s1">'?</span><span class="si">{query}</span><span class="s1">&format=json&pretty=0&no_redirect=1&d=1'</span>
|
||
|
|
||
|
<span class="n">WIKIDATA_PREFIX</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'http://www.wikidata.org/entity/'</span><span class="p">,</span> <span class="s1">'https://www.wikidata.org/entity/'</span><span class="p">]</span>
|
||
|
|
||
|
<span class="n">replace_http_by_https</span> <span class="o">=</span> <span class="n">get_string_replaces_function</span><span class="p">({</span><span class="s1">'http:'</span><span class="p">:</span> <span class="s1">'https:'</span><span class="p">})</span>
|
||
|
|
||
|
|
||
|
<div class="viewcode-block" id="is_broken_text">
|
||
|
<a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo_definitions.is_broken_text">[docs]</a>
|
||
|
<span class="k">def</span> <span class="nf">is_broken_text</span><span class="p">(</span><span class="n">text</span><span class="p">):</span>
|
||
|
<span class="w"> </span><span class="sd">"""duckduckgo may return something like ``<a href="xxxx">http://somewhere Related website<a/>``</span>
|
||
|
|
||
|
<span class="sd"> The href URL is broken, the "Related website" may contains some HTML.</span>
|
||
|
|
||
|
<span class="sd"> The best solution seems to ignore these results.</span>
|
||
|
<span class="sd"> """</span>
|
||
|
<span class="k">return</span> <span class="n">text</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'http'</span><span class="p">)</span> <span class="ow">and</span> <span class="s1">' '</span> <span class="ow">in</span> <span class="n">text</span></div>
|
||
|
|
||
|
|
||
|
|
||
|
<span class="k">def</span> <span class="nf">result_to_text</span><span class="p">(</span><span class="n">text</span><span class="p">,</span> <span class="n">htmlResult</span><span class="p">):</span>
|
||
|
<span class="c1"># TODO : remove result ending with "Meaning" or "Category" # pylint: disable=fixme</span>
|
||
|
<span class="n">result</span> <span class="o">=</span> <span class="kc">None</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">htmlResult</span><span class="p">)</span>
|
||
|
<span class="n">a</span> <span class="o">=</span> <span class="n">dom</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">'//a'</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">a</span><span class="p">)</span> <span class="o">>=</span> <span class="mi">1</span><span class="p">:</span>
|
||
|
<span class="n">result</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">a</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
|
||
|
<span class="k">else</span><span class="p">:</span>
|
||
|
<span class="n">result</span> <span class="o">=</span> <span class="n">text</span>
|
||
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">is_broken_text</span><span class="p">(</span><span class="n">result</span><span class="p">):</span>
|
||
|
<span class="k">return</span> <span class="n">result</span>
|
||
|
<span class="k">return</span> <span class="kc">None</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">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="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">query</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="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="c1"># pylint: disable=too-many-locals, too-many-branches, too-many-statements</span>
|
||
|
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
|
||
|
<span class="n">search_res</span> <span class="o">=</span> <span class="n">resp</span><span class="o">.</span><span class="n">json</span><span class="p">()</span>
|
||
|
|
||
|
<span class="c1"># search_res.get('Entity') possible values (not exhaustive) :</span>
|
||
|
<span class="c1"># * continent / country / department / location / waterfall</span>
|
||
|
<span class="c1"># * actor / musician / artist</span>
|
||
|
<span class="c1"># * book / performing art / film / television / media franchise / concert tour / playwright</span>
|
||
|
<span class="c1"># * prepared food</span>
|
||
|
<span class="c1"># * website / software / os / programming language / file format / software engineer</span>
|
||
|
<span class="c1"># * company</span>
|
||
|
|
||
|
<span class="n">content</span> <span class="o">=</span> <span class="s1">''</span>
|
||
|
<span class="n">heading</span> <span class="o">=</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Heading'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
|
||
|
<span class="n">attributes</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
<span class="n">urls</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
<span class="n">infobox_id</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
<span class="n">relatedTopics</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
|
||
|
<span class="c1"># add answer if there is one</span>
|
||
|
<span class="n">answer</span> <span class="o">=</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Answer'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="n">answer</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">'AnswerType="</span><span class="si">%s</span><span class="s1">" Answer="</span><span class="si">%s</span><span class="s1">"'</span><span class="p">,</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'AnswerType'</span><span class="p">),</span> <span class="n">answer</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'AnswerType'</span><span class="p">)</span> <span class="ow">not</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'calc'</span><span class="p">,</span> <span class="s1">'ip'</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="s1">'answer'</span><span class="p">:</span> <span class="n">html_to_text</span><span class="p">(</span><span class="n">answer</span><span class="p">),</span> <span class="s1">'url'</span><span class="p">:</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'AbstractURL'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)})</span>
|
||
|
|
||
|
<span class="c1"># add infobox</span>
|
||
|
<span class="k">if</span> <span class="s1">'Definition'</span> <span class="ow">in</span> <span class="n">search_res</span><span class="p">:</span>
|
||
|
<span class="n">content</span> <span class="o">=</span> <span class="n">content</span> <span class="o">+</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Definition'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
|
||
|
|
||
|
<span class="k">if</span> <span class="s1">'Abstract'</span> <span class="ow">in</span> <span class="n">search_res</span><span class="p">:</span>
|
||
|
<span class="n">content</span> <span class="o">=</span> <span class="n">content</span> <span class="o">+</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Abstract'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
|
||
|
|
||
|
<span class="c1"># image</span>
|
||
|
<span class="n">image</span> <span class="o">=</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Image'</span><span class="p">)</span>
|
||
|
<span class="n">image</span> <span class="o">=</span> <span class="kc">None</span> <span class="k">if</span> <span class="n">image</span> <span class="o">==</span> <span class="s1">''</span> <span class="k">else</span> <span class="n">image</span>
|
||
|
<span class="k">if</span> <span class="n">image</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">image</span><span class="p">)</span><span class="o">.</span><span class="n">netloc</span> <span class="o">==</span> <span class="s1">''</span><span class="p">:</span>
|
||
|
<span class="n">image</span> <span class="o">=</span> <span class="n">urljoin</span><span class="p">(</span><span class="s1">'https://duckduckgo.com'</span><span class="p">,</span> <span class="n">image</span><span class="p">)</span>
|
||
|
|
||
|
<span class="c1"># urls</span>
|
||
|
<span class="c1"># Official website, Wikipedia page</span>
|
||
|
<span class="k">for</span> <span class="n">ddg_result</span> <span class="ow">in</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Results'</span><span class="p">,</span> <span class="p">[]):</span>
|
||
|
<span class="n">firstURL</span> <span class="o">=</span> <span class="n">ddg_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'FirstURL'</span><span class="p">)</span>
|
||
|
<span class="n">text</span> <span class="o">=</span> <span class="n">ddg_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Text'</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="n">firstURL</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">text</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
<span class="n">urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'title'</span><span class="p">:</span> <span class="n">text</span><span class="p">,</span> <span class="s1">'url'</span><span class="p">:</span> <span class="n">firstURL</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="s1">'title'</span><span class="p">:</span> <span class="n">heading</span><span class="p">,</span> <span class="s1">'url'</span><span class="p">:</span> <span class="n">firstURL</span><span class="p">})</span>
|
||
|
|
||
|
<span class="c1"># related topics</span>
|
||
|
<span class="k">for</span> <span class="n">ddg_result</span> <span class="ow">in</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'RelatedTopics'</span><span class="p">,</span> <span class="p">[]):</span>
|
||
|
<span class="k">if</span> <span class="s1">'FirstURL'</span> <span class="ow">in</span> <span class="n">ddg_result</span><span class="p">:</span>
|
||
|
<span class="n">firstURL</span> <span class="o">=</span> <span class="n">ddg_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'FirstURL'</span><span class="p">)</span>
|
||
|
<span class="n">text</span> <span class="o">=</span> <span class="n">ddg_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Text'</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">is_broken_text</span><span class="p">(</span><span class="n">text</span><span class="p">):</span>
|
||
|
<span class="n">suggestion</span> <span class="o">=</span> <span class="n">result_to_text</span><span class="p">(</span><span class="n">text</span><span class="p">,</span> <span class="n">ddg_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Result'</span><span class="p">))</span>
|
||
|
<span class="k">if</span> <span class="n">suggestion</span> <span class="o">!=</span> <span class="n">heading</span> <span class="ow">and</span> <span class="n">suggestion</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</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="s1">'suggestion'</span><span class="p">:</span> <span class="n">suggestion</span><span class="p">})</span>
|
||
|
<span class="k">elif</span> <span class="s1">'Topics'</span> <span class="ow">in</span> <span class="n">ddg_result</span><span class="p">:</span>
|
||
|
<span class="n">suggestions</span> <span class="o">=</span> <span class="p">[]</span>
|
||
|
<span class="n">relatedTopics</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'name'</span><span class="p">:</span> <span class="n">ddg_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Name'</span><span class="p">,</span> <span class="s1">''</span><span class="p">),</span> <span class="s1">'suggestions'</span><span class="p">:</span> <span class="n">suggestions</span><span class="p">})</span>
|
||
|
<span class="k">for</span> <span class="n">topic_result</span> <span class="ow">in</span> <span class="n">ddg_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Topics'</span><span class="p">,</span> <span class="p">[]):</span>
|
||
|
<span class="n">suggestion</span> <span class="o">=</span> <span class="n">result_to_text</span><span class="p">(</span><span class="n">topic_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Text'</span><span class="p">),</span> <span class="n">topic_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Result'</span><span class="p">))</span>
|
||
|
<span class="k">if</span> <span class="n">suggestion</span> <span class="o">!=</span> <span class="n">heading</span> <span class="ow">and</span> <span class="n">suggestion</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
<span class="n">suggestions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">suggestion</span><span class="p">)</span>
|
||
|
|
||
|
<span class="c1"># abstract</span>
|
||
|
<span class="n">abstractURL</span> <span class="o">=</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'AbstractURL'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="n">abstractURL</span> <span class="o">!=</span> <span class="s1">''</span><span class="p">:</span>
|
||
|
<span class="c1"># add as result ? problem always in english</span>
|
||
|
<span class="n">infobox_id</span> <span class="o">=</span> <span class="n">abstractURL</span>
|
||
|
<span class="n">urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'title'</span><span class="p">:</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'AbstractSource'</span><span class="p">),</span> <span class="s1">'url'</span><span class="p">:</span> <span class="n">abstractURL</span><span class="p">,</span> <span class="s1">'official'</span><span class="p">:</span> <span class="kc">True</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="s1">'url'</span><span class="p">:</span> <span class="n">abstractURL</span><span class="p">,</span> <span class="s1">'title'</span><span class="p">:</span> <span class="n">heading</span><span class="p">})</span>
|
||
|
|
||
|
<span class="c1"># definition</span>
|
||
|
<span class="n">definitionURL</span> <span class="o">=</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'DefinitionURL'</span><span class="p">,</span> <span class="s1">''</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="n">definitionURL</span> <span class="o">!=</span> <span class="s1">''</span><span class="p">:</span>
|
||
|
<span class="c1"># add as result ? as answer ? problem always in english</span>
|
||
|
<span class="n">infobox_id</span> <span class="o">=</span> <span class="n">definitionURL</span>
|
||
|
<span class="n">urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'title'</span><span class="p">:</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'DefinitionSource'</span><span class="p">),</span> <span class="s1">'url'</span><span class="p">:</span> <span class="n">definitionURL</span><span class="p">})</span>
|
||
|
|
||
|
<span class="c1"># to merge with wikidata's infobox</span>
|
||
|
<span class="k">if</span> <span class="n">infobox_id</span><span class="p">:</span>
|
||
|
<span class="n">infobox_id</span> <span class="o">=</span> <span class="n">replace_http_by_https</span><span class="p">(</span><span class="n">infobox_id</span><span class="p">)</span>
|
||
|
|
||
|
<span class="c1"># attributes</span>
|
||
|
<span class="c1"># some will be converted to urls</span>
|
||
|
<span class="k">if</span> <span class="s1">'Infobox'</span> <span class="ow">in</span> <span class="n">search_res</span><span class="p">:</span>
|
||
|
<span class="n">infobox</span> <span class="o">=</span> <span class="n">search_res</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'Infobox'</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="s1">'content'</span> <span class="ow">in</span> <span class="n">infobox</span><span class="p">:</span>
|
||
|
<span class="n">osm_zoom</span> <span class="o">=</span> <span class="mi">17</span>
|
||
|
<span class="n">coordinates</span> <span class="o">=</span> <span class="kc">None</span>
|
||
|
<span class="k">for</span> <span class="n">info</span> <span class="ow">in</span> <span class="n">infobox</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'content'</span><span class="p">):</span>
|
||
|
<span class="n">data_type</span> <span class="o">=</span> <span class="n">info</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'data_type'</span><span class="p">)</span>
|
||
|
<span class="n">data_label</span> <span class="o">=</span> <span class="n">info</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'label'</span><span class="p">)</span>
|
||
|
<span class="n">data_value</span> <span class="o">=</span> <span class="n">info</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'value'</span><span class="p">)</span>
|
||
|
|
||
|
<span class="c1"># Workaround: ddg may return a double quote</span>
|
||
|
<span class="k">if</span> <span class="n">data_value</span> <span class="o">==</span> <span class="s1">'""'</span><span class="p">:</span>
|
||
|
<span class="k">continue</span>
|
||
|
|
||
|
<span class="c1"># Is it an external URL ?</span>
|
||
|
<span class="c1"># * imdb_id / facebook_profile / youtube_channel / youtube_video / twitter_profile</span>
|
||
|
<span class="c1"># * instagram_profile / rotten_tomatoes / spotify_artist_id / itunes_artist_id / soundcloud_id</span>
|
||
|
<span class="c1"># * netflix_id</span>
|
||
|
<span class="n">external_url</span> <span class="o">=</span> <span class="n">get_external_url</span><span class="p">(</span><span class="n">data_type</span><span class="p">,</span> <span class="n">data_value</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="n">external_url</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
<span class="n">urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'title'</span><span class="p">:</span> <span class="n">data_label</span><span class="p">,</span> <span class="s1">'url'</span><span class="p">:</span> <span class="n">external_url</span><span class="p">})</span>
|
||
|
<span class="k">elif</span> <span class="n">data_type</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'instance'</span><span class="p">,</span> <span class="s1">'wiki_maps_trigger'</span><span class="p">,</span> <span class="s1">'google_play_artist_id'</span><span class="p">]:</span>
|
||
|
<span class="c1"># ignore instance: Wikidata value from "Instance Of" (Qxxxx)</span>
|
||
|
<span class="c1"># ignore wiki_maps_trigger: reference to a javascript</span>
|
||
|
<span class="c1"># ignore google_play_artist_id: service shutdown</span>
|
||
|
<span class="k">pass</span>
|
||
|
<span class="k">elif</span> <span class="n">data_type</span> <span class="o">==</span> <span class="s1">'string'</span> <span class="ow">and</span> <span class="n">data_label</span> <span class="o">==</span> <span class="s1">'Website'</span><span class="p">:</span>
|
||
|
<span class="c1"># There is already an URL for the website</span>
|
||
|
<span class="k">pass</span>
|
||
|
<span class="k">elif</span> <span class="n">data_type</span> <span class="o">==</span> <span class="s1">'area'</span><span class="p">:</span>
|
||
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'label'</span><span class="p">:</span> <span class="n">data_label</span><span class="p">,</span> <span class="s1">'value'</span><span class="p">:</span> <span class="n">area_to_str</span><span class="p">(</span><span class="n">data_value</span><span class="p">),</span> <span class="s1">'entity'</span><span class="p">:</span> <span class="s1">'P2046'</span><span class="p">})</span>
|
||
|
<span class="n">osm_zoom</span> <span class="o">=</span> <span class="n">area_to_osm_zoom</span><span class="p">(</span><span class="n">data_value</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'amount'</span><span class="p">))</span>
|
||
|
<span class="k">elif</span> <span class="n">data_type</span> <span class="o">==</span> <span class="s1">'coordinates'</span><span class="p">:</span>
|
||
|
<span class="k">if</span> <span class="n">data_value</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'globe'</span><span class="p">)</span> <span class="o">==</span> <span class="s1">'http://www.wikidata.org/entity/Q2'</span><span class="p">:</span>
|
||
|
<span class="c1"># coordinate on Earth</span>
|
||
|
<span class="c1"># get the zoom information from the area</span>
|
||
|
<span class="n">coordinates</span> <span class="o">=</span> <span class="n">info</span>
|
||
|
<span class="k">else</span><span class="p">:</span>
|
||
|
<span class="c1"># coordinate NOT on Earth</span>
|
||
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'label'</span><span class="p">:</span> <span class="n">data_label</span><span class="p">,</span> <span class="s1">'value'</span><span class="p">:</span> <span class="n">data_value</span><span class="p">,</span> <span class="s1">'entity'</span><span class="p">:</span> <span class="s1">'P625'</span><span class="p">})</span>
|
||
|
<span class="k">elif</span> <span class="n">data_type</span> <span class="o">==</span> <span class="s1">'string'</span><span class="p">:</span>
|
||
|
<span class="n">attributes</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'label'</span><span class="p">:</span> <span class="n">data_label</span><span class="p">,</span> <span class="s1">'value'</span><span class="p">:</span> <span class="n">data_value</span><span class="p">})</span>
|
||
|
|
||
|
<span class="k">if</span> <span class="n">coordinates</span><span class="p">:</span>
|
||
|
<span class="n">data_label</span> <span class="o">=</span> <span class="n">coordinates</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'label'</span><span class="p">)</span>
|
||
|
<span class="n">data_value</span> <span class="o">=</span> <span class="n">coordinates</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'value'</span><span class="p">)</span>
|
||
|
<span class="n">latitude</span> <span class="o">=</span> <span class="n">data_value</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'latitude'</span><span class="p">)</span>
|
||
|
<span class="n">longitude</span> <span class="o">=</span> <span class="n">data_value</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'longitude'</span><span class="p">)</span>
|
||
|
<span class="n">url</span> <span class="o">=</span> <span class="n">get_earth_coordinates_url</span><span class="p">(</span><span class="n">latitude</span><span class="p">,</span> <span class="n">longitude</span><span class="p">,</span> <span class="n">osm_zoom</span><span class="p">)</span>
|
||
|
<span class="n">urls</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">'title'</span><span class="p">:</span> <span class="s1">'OpenStreetMap'</span><span class="p">,</span> <span class="s1">'url'</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span> <span class="s1">'entity'</span><span class="p">:</span> <span class="s1">'P625'</span><span class="p">})</span>
|
||
|
|
||
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">heading</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
||
|
<span class="c1"># TODO get infobox.meta.value where .label='article_title' # pylint: disable=fixme</span>
|
||
|
<span class="k">if</span> <span class="n">image</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">attributes</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">urls</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">relatedTopics</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">content</span><span class="p">)</span> <span class="o">==</span> <span class="mi">0</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="s1">'url'</span><span class="p">:</span> <span class="n">urls</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="s1">'url'</span><span class="p">],</span> <span class="s1">'title'</span><span class="p">:</span> <span class="n">heading</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="k">else</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">'infobox'</span><span class="p">:</span> <span class="n">heading</span><span class="p">,</span>
|
||
|
<span class="s1">'id'</span><span class="p">:</span> <span class="n">infobox_id</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">image</span><span class="p">,</span>
|
||
|
<span class="s1">'attributes'</span><span class="p">:</span> <span class="n">attributes</span><span class="p">,</span>
|
||
|
<span class="s1">'urls'</span><span class="p">:</span> <span class="n">urls</span><span class="p">,</span>
|
||
|
<span class="s1">'relatedTopics'</span><span class="p">:</span> <span class="n">relatedTopics</span><span class="p">,</span>
|
||
|
<span class="p">}</span>
|
||
|
<span class="p">)</span>
|
||
|
|
||
|
<span class="k">return</span> <span class="n">results</span>
|
||
|
|
||
|
|
||
|
<span class="k">def</span> <span class="nf">unit_to_str</span><span class="p">(</span><span class="n">unit</span><span class="p">):</span>
|
||
|
<span class="k">for</span> <span class="n">prefix</span> <span class="ow">in</span> <span class="n">WIKIDATA_PREFIX</span><span class="p">:</span>
|
||
|
<span class="k">if</span> <span class="n">unit</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="n">prefix</span><span class="p">):</span>
|
||
|
<span class="n">wikidata_entity</span> <span class="o">=</span> <span class="n">unit</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">prefix</span><span class="p">)</span> <span class="p">:]</span>
|
||
|
<span class="n">real_unit</span> <span class="o">=</span> <span class="n">WIKIDATA_UNITS</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">wikidata_entity</span><span class="p">)</span>
|
||
|
<span class="k">if</span> <span class="n">real_unit</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
<span class="k">return</span> <span class="n">unit</span>
|
||
|
<span class="k">return</span> <span class="n">real_unit</span><span class="p">[</span><span class="s1">'symbol'</span><span class="p">]</span>
|
||
|
<span class="k">return</span> <span class="n">unit</span>
|
||
|
|
||
|
|
||
|
<div class="viewcode-block" id="area_to_str">
|
||
|
<a class="viewcode-back" href="../../../dev/engines/online/duckduckgo.html#searx.engines.duckduckgo_definitions.area_to_str">[docs]</a>
|
||
|
<span class="k">def</span> <span class="nf">area_to_str</span><span class="p">(</span><span class="n">area</span><span class="p">):</span>
|
||
|
<span class="w"> </span><span class="sd">"""parse ``{'unit': 'https://www.wikidata.org/entity/Q712226', 'amount': '+20.99'}``"""</span>
|
||
|
<span class="n">unit</span> <span class="o">=</span> <span class="n">unit_to_str</span><span class="p">(</span><span class="n">area</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'unit'</span><span class="p">))</span>
|
||
|
<span class="k">if</span> <span class="n">unit</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
||
|
<span class="k">try</span><span class="p">:</span>
|
||
|
<span class="n">amount</span> <span class="o">=</span> <span class="nb">float</span><span class="p">(</span><span class="n">area</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'amount'</span><span class="p">))</span>
|
||
|
<span class="k">return</span> <span class="s1">'</span><span class="si">{}</span><span class="s1"> </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">amount</span><span class="p">,</span> <span class="n">unit</span><span class="p">)</span>
|
||
|
<span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
|
||
|
<span class="k">pass</span>
|
||
|
<span class="k">return</span> <span class="s1">'</span><span class="si">{}</span><span class="s1"> </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">area</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'amount'</span><span class="p">,</span> <span class="s1">''</span><span class="p">),</span> <span class="n">area</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'unit'</span><span class="p">,</span> <span class="s1">''</span><span class="p">))</span></div>
|
||
|
|
||
|
</pre></div>
|
||
|
|
||
|
<div class="clearer"></div>
|
||
|
</div>
|
||
|
</div>
|
||
|
</div>
|
||
|
<span id="sidebar-top"></span>
|
||
|
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||
|
<div class="sphinxsidebarwrapper">
|
||
|
|
||
|
|
||
|
<p class="logo"><a href="../../../index.html">
|
||
|
<img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
|
||
|
</a></p>
|
||
|
|
||
|
|
||
|
<h3><a href="../../../index.html">Table of Contents</a></h3>
|
||
|
<ul>
|
||
|
<li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
|
||
|
<li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
|
||
|
<li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
|
||
|
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
|
||
|
<li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
|
||
|
<li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
|
||
|
</ul>
|
||
|
|
||
|
<h3>Project Links</h3>
|
||
|
<ul>
|
||
|
<li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
|
||
|
|
||
|
<li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
|
||
|
|
||
|
<li><a href="https://searx.space">Public instances</a>
|
||
|
|
||
|
<li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
|
||
|
</ul><h3>Navigation</h3>
|
||
|
<ul>
|
||
|
<li><a href="../../../index.html">Overview</a>
|
||
|
<ul>
|
||
|
<li><a href="../../index.html">Module code</a>
|
||
|
<ul>
|
||
|
<li><a href="../engines.html">searx.engines</a>
|
||
|
|
||
|
|
||
|
</ul>
|
||
|
</li></ul>
|
||
|
</li>
|
||
|
</ul>
|
||
|
</li>
|
||
|
</ul>
|
||
|
<search id="searchbox" style="display: none" role="search">
|
||
|
<h3 id="searchlabel">Quick search</h3>
|
||
|
<div class="searchformwrapper">
|
||
|
<form class="search" action="../../../search.html" method="get">
|
||
|
<input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
|
||
|
<input type="submit" value="Go" />
|
||
|
</form>
|
||
|
</div>
|
||
|
</search>
|
||
|
<script>document.getElementById('searchbox').style.display = "block"</script>
|
||
|
</div>
|
||
|
</div>
|
||
|
<div class="clearer"></div>
|
||
|
</div>
|
||
|
<div class="footer" role="contentinfo">
|
||
|
© Copyright SearXNG team.
|
||
|
</div>
|
||
|
</body>
|
||
|
</html>
|