mirror of
https://github.com/searxng/searxng.git
synced 2025-12-22 04:47:25 -05:00
593 lines
63 KiB
HTML
593 lines
63 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.brave — SearXNG Documentation (2025.12.17+896863802)</title>
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
|
|
<script src="../../../_static/documentation_options.js?v=b7594045"></script>
|
|
<script src="../../../_static/doctools.js?v=9bcbadda"></script>
|
|
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script data-project="searxng" data-version="2025.12.17+896863802" 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 (2025.12.17+896863802)</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.brave</a></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="document">
|
|
<div class="documentwrapper">
|
|
<div class="bodywrapper">
|
|
<div class="body" role="main">
|
|
|
|
<h1>Source code for searx.engines.brave</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
|
<span class="sd">"""Brave supports the categories listed in :py:obj:`brave_category` (General,</span>
|
|
<span class="sd">news, videos, images). The support of :py:obj:`paging` and :py:obj:`time range</span>
|
|
<span class="sd"><time_range_support>` is limited (see remarks).</span>
|
|
|
|
<span class="sd">Configured ``brave`` engines:</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> - name: brave</span>
|
|
<span class="sd"> engine: brave</span>
|
|
<span class="sd"> ...</span>
|
|
<span class="sd"> brave_category: search</span>
|
|
<span class="sd"> time_range_support: true</span>
|
|
<span class="sd"> paging: true</span>
|
|
|
|
<span class="sd"> - name: brave.images</span>
|
|
<span class="sd"> engine: brave</span>
|
|
<span class="sd"> ...</span>
|
|
<span class="sd"> brave_category: images</span>
|
|
|
|
<span class="sd"> - name: brave.videos</span>
|
|
<span class="sd"> engine: brave</span>
|
|
<span class="sd"> ...</span>
|
|
<span class="sd"> brave_category: videos</span>
|
|
|
|
<span class="sd"> - name: brave.news</span>
|
|
<span class="sd"> engine: brave</span>
|
|
<span class="sd"> ...</span>
|
|
<span class="sd"> brave_category: news</span>
|
|
|
|
<span class="sd"> - name: brave.goggles</span>
|
|
<span class="sd"> time_range_support: true</span>
|
|
<span class="sd"> paging: true</span>
|
|
<span class="sd"> ...</span>
|
|
<span class="sd"> brave_category: goggles</span>
|
|
|
|
|
|
<span class="sd">.. _brave regions:</span>
|
|
|
|
<span class="sd">Brave regions</span>
|
|
<span class="sd">=============</span>
|
|
|
|
<span class="sd">Brave uses two-digit tags for the regions like ``ca`` while SearXNG deals with</span>
|
|
<span class="sd">locales. To get a mapping, all *officiat de-facto* languages of the Brave</span>
|
|
<span class="sd">region are mapped to regions in SearXNG (see :py:obj:`babel</span>
|
|
<span class="sd"><babel.languages.get_official_languages>`):</span>
|
|
|
|
<span class="sd">.. code:: python</span>
|
|
|
|
<span class="sd"> "regions": {</span>
|
|
<span class="sd"> ..</span>
|
|
<span class="sd"> "en-CA": "ca",</span>
|
|
<span class="sd"> "fr-CA": "ca",</span>
|
|
<span class="sd"> ..</span>
|
|
<span class="sd"> }</span>
|
|
|
|
|
|
<span class="sd">.. note::</span>
|
|
|
|
<span class="sd"> The language (aka region) support of Brave's index is limited to very basic</span>
|
|
<span class="sd"> languages. The search results for languages like Chinese or Arabic are of</span>
|
|
<span class="sd"> low quality.</span>
|
|
|
|
|
|
<span class="sd">.. _brave googles:</span>
|
|
|
|
<span class="sd">Brave Goggles</span>
|
|
<span class="sd">=============</span>
|
|
|
|
<span class="sd">.. _list of Goggles: https://search.brave.com/goggles/discover</span>
|
|
<span class="sd">.. _Goggles Whitepaper: https://brave.com/static-assets/files/goggles.pdf</span>
|
|
<span class="sd">.. _Goggles Quickstart: https://github.com/brave/goggles-quickstart</span>
|
|
|
|
<span class="sd">Goggles allow you to choose, alter, or extend the ranking of Brave Search</span>
|
|
<span class="sd">results (`Goggles Whitepaper`_). Goggles are openly developed by the community</span>
|
|
<span class="sd">of Brave Search users.</span>
|
|
|
|
<span class="sd">Select from the `list of Goggles`_ people have published, or create your own</span>
|
|
<span class="sd">(`Goggles Quickstart`_).</span>
|
|
|
|
|
|
<span class="sd">.. _brave languages:</span>
|
|
|
|
<span class="sd">Brave languages</span>
|
|
<span class="sd">===============</span>
|
|
|
|
<span class="sd">Brave's language support is limited to the UI (menus, area local notations,</span>
|
|
<span class="sd">etc). Brave's index only seems to support a locale, but it does not seem to</span>
|
|
<span class="sd">support any languages in its index. The choice of available languages is very</span>
|
|
<span class="sd">small (and its not clear to me where the difference in UI is when switching</span>
|
|
<span class="sd">from en-us to en-ca or en-gb).</span>
|
|
|
|
<span class="sd">In the :py:obj:`EngineTraits object <searx.enginelib.traits.EngineTraits>` the</span>
|
|
<span class="sd">UI languages are stored in a custom field named ``ui_lang``:</span>
|
|
|
|
<span class="sd">.. code:: python</span>
|
|
|
|
<span class="sd"> "custom": {</span>
|
|
<span class="sd"> "ui_lang": {</span>
|
|
<span class="sd"> "ca": "ca",</span>
|
|
<span class="sd"> "de-DE": "de-de",</span>
|
|
<span class="sd"> "en-CA": "en-ca",</span>
|
|
<span class="sd"> "en-GB": "en-gb",</span>
|
|
<span class="sd"> "en-US": "en-us",</span>
|
|
<span class="sd"> "es": "es",</span>
|
|
<span class="sd"> "fr-CA": "fr-ca",</span>
|
|
<span class="sd"> "fr-FR": "fr-fr",</span>
|
|
<span class="sd"> "ja-JP": "ja-jp",</span>
|
|
<span class="sd"> "pt-BR": "pt-br",</span>
|
|
<span class="sd"> "sq-AL": "sq-al"</span>
|
|
<span class="sd"> }</span>
|
|
<span class="sd"> },</span>
|
|
|
|
<span class="sd">Implementations</span>
|
|
<span class="sd">===============</span>
|
|
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="nn">t</span>
|
|
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">urllib.parse</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
|
|
<span class="n">urlencode</span><span class="p">,</span>
|
|
<span class="n">urlparse</span><span class="p">,</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">dateutil</span><span class="w"> </span><span class="kn">import</span> <span class="n">parser</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">lxml</span><span class="w"> </span><span class="kn">import</span> <span class="n">html</span>
|
|
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx</span><span class="w"> </span><span class="kn">import</span> <span class="n">locales</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.utils</span><span class="w"> </span><span class="kn">import</span> <span class="p">(</span>
|
|
<span class="n">extract_text</span><span class="p">,</span>
|
|
<span class="n">eval_xpath_list</span><span class="p">,</span>
|
|
<span class="n">eval_xpath_getindex</span><span class="p">,</span>
|
|
<span class="n">js_obj_str_to_python</span><span class="p">,</span>
|
|
<span class="n">js_obj_str_to_json_str</span><span class="p">,</span>
|
|
<span class="n">get_embeded_stream_url</span><span class="p">,</span>
|
|
<span class="p">)</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.enginelib.traits</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineTraits</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.result_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineResults</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.extended_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">SXNG_Response</span>
|
|
|
|
<span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"website"</span><span class="p">:</span> <span class="s2">"https://search.brave.com/"</span><span class="p">,</span>
|
|
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s2">"Q22906900"</span><span class="p">,</span>
|
|
<span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="s2">"use_official_api"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="s2">"require_api_key"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="s2">"results"</span><span class="p">:</span> <span class="s2">"HTML"</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="n">base_url</span> <span class="o">=</span> <span class="s2">"https://search.brave.com/"</span>
|
|
<span class="n">categories</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="n">brave_category</span><span class="p">:</span> <span class="n">t</span><span class="o">.</span><span class="n">Literal</span><span class="p">[</span><span class="s2">"search"</span><span class="p">,</span> <span class="s2">"videos"</span><span class="p">,</span> <span class="s2">"images"</span><span class="p">,</span> <span class="s2">"news"</span><span class="p">,</span> <span class="s2">"goggles"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"search"</span>
|
|
<span class="sd">"""Brave supports common web-search, videos, images, news, and goggles search.</span>
|
|
|
|
<span class="sd">- ``search``: Common WEB search</span>
|
|
<span class="sd">- ``videos``: search for videos</span>
|
|
<span class="sd">- ``images``: search for images</span>
|
|
<span class="sd">- ``news``: search for news</span>
|
|
<span class="sd">- ``goggles``: Common WEB search with custom rules, requires a :py:obj:`Goggles` URL.</span>
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="n">Goggles</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">""</span>
|
|
<span class="sd">"""This should be a URL ending in ``.goggle``"""</span>
|
|
|
|
<span class="n">brave_spellcheck</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="sd">"""Brave supports some kind of spell checking. When activated, Brave tries to</span>
|
|
<span class="sd">fix typos, e.g. it searches for ``food`` when the user queries for ``fooh``. In</span>
|
|
<span class="sd">the UI of Brave the user gets warned about this, since we can not warn the user</span>
|
|
<span class="sd">in SearXNG, the spellchecking is disabled by default.</span>
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="n">send_accept_language_header</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">paging</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="sd">"""Brave only supports paging in :py:obj:`brave_category` ``search`` (UI</span>
|
|
<span class="sd">category All) and in the goggles category."""</span>
|
|
<span class="n">max_page</span> <span class="o">=</span> <span class="mi">10</span>
|
|
<span class="sd">"""Tested 9 pages maximum (``&offset=8``), to be save max is set to 10. Trying</span>
|
|
<span class="sd">to do more won't return any result and you will most likely be flagged as a bot.</span>
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="n">safesearch</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">safesearch_map</span> <span class="o">=</span> <span class="p">{</span><span class="mi">2</span><span class="p">:</span> <span class="s2">"strict"</span><span class="p">,</span> <span class="mi">1</span><span class="p">:</span> <span class="s2">"moderate"</span><span class="p">,</span> <span class="mi">0</span><span class="p">:</span> <span class="s2">"off"</span><span class="p">}</span> <span class="c1"># cookie: safesearch=off</span>
|
|
|
|
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="sd">"""Brave only supports time-range in :py:obj:`brave_category` ``search`` (UI</span>
|
|
<span class="sd">category All) and in the goggles category."""</span>
|
|
|
|
<span class="n">time_range_map</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"day"</span><span class="p">:</span> <span class="s2">"pd"</span><span class="p">,</span>
|
|
<span class="s2">"week"</span><span class="p">:</span> <span class="s2">"pw"</span><span class="p">,</span>
|
|
<span class="s2">"month"</span><span class="p">:</span> <span class="s2">"pm"</span><span class="p">,</span>
|
|
<span class="s2">"year"</span><span class="p">:</span> <span class="s2">"py"</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">params</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">])</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span>
|
|
|
|
<span class="n">args</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s2">"q"</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
|
|
<span class="s2">"source"</span><span class="p">:</span> <span class="s2">"web"</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="k">if</span> <span class="n">brave_spellcheck</span><span class="p">:</span>
|
|
<span class="n">args</span><span class="p">[</span><span class="s2">"spellcheck"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"1"</span>
|
|
|
|
<span class="k">if</span> <span class="n">brave_category</span> <span class="ow">in</span> <span class="p">(</span><span class="s2">"search"</span><span class="p">,</span> <span class="s2">"goggles"</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"pageno"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span><span class="p">:</span>
|
|
<span class="n">args</span><span class="p">[</span><span class="s2">"offset"</span><span class="p">]</span> <span class="o">=</span> <span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"pageno"</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span>
|
|
<span class="k">if</span> <span class="n">time_range_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"time_range"</span><span class="p">]):</span>
|
|
<span class="n">args</span><span class="p">[</span><span class="s2">"tf"</span><span class="p">]</span> <span class="o">=</span> <span class="n">time_range_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"time_range"</span><span class="p">])</span>
|
|
|
|
<span class="k">if</span> <span class="n">brave_category</span> <span class="o">==</span> <span class="s2">"goggles"</span><span class="p">:</span>
|
|
<span class="n">args</span><span class="p">[</span><span class="s2">"goggles_id"</span><span class="p">]</span> <span class="o">=</span> <span class="n">Goggles</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"headers"</span><span class="p">][</span><span class="s2">"Accept-Encoding"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"gzip, deflate"</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"url"</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">base_url</span><span class="si">}{</span><span class="n">brave_category</span><span class="si">}</span><span class="s2">?</span><span class="si">{</span><span class="n">urlencode</span><span class="p">(</span><span class="n">args</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"url </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="s2">"url"</span><span class="p">])</span>
|
|
|
|
<span class="c1"># set properties in the cookies</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"cookies"</span><span class="p">][</span><span class="s2">"safesearch"</span><span class="p">]</span> <span class="o">=</span> <span class="n">safesearch_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"safesearch"</span><span class="p">],</span> <span class="s2">"off"</span><span class="p">)</span>
|
|
<span class="c1"># the useLocation is IP based, we use cookie "country" for the region</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"cookies"</span><span class="p">][</span><span class="s2">"useLocation"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"0"</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"cookies"</span><span class="p">][</span><span class="s2">"summarizer"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"0"</span>
|
|
|
|
<span class="n">engine_region</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">get_region</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"searxng_locale"</span><span class="p">],</span> <span class="s2">"all"</span><span class="p">)</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"cookies"</span><span class="p">][</span><span class="s2">"country"</span><span class="p">]</span> <span class="o">=</span> <span class="n">engine_region</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">"-"</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="c1"># type: ignore</span>
|
|
|
|
<span class="n">ui_lang</span> <span class="o">=</span> <span class="n">locales</span><span class="o">.</span><span class="n">get_engine_locale</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s2">"searxng_locale"</span><span class="p">],</span> <span class="n">traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"ui_lang"</span><span class="p">],</span> <span class="s2">"en-us"</span><span class="p">)</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s2">"cookies"</span><span class="p">][</span><span class="s2">"ui_lang"</span><span class="p">]</span> <span class="o">=</span> <span class="n">ui_lang</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"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="s2">"cookies"</span><span class="p">])</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">_extract_published_date</span><span class="p">(</span><span class="n">published_date_raw</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">published_date_raw</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="kc">None</span>
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">published_date_raw</span><span class="p">)</span>
|
|
<span class="k">except</span> <span class="n">parser</span><span class="o">.</span><span class="n">ParserError</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="kc">None</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">extract_json_data</span><span class="p">(</span><span class="n">text</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]:</span>
|
|
<span class="c1"># Example script source containing the data:</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># kit.start(app, element, {</span>
|
|
<span class="c1"># node_ids: [0, 19],</span>
|
|
<span class="c1"># data: [{type:"data",data: .... ["q","goggles_id"],route:1,url:1}}]</span>
|
|
<span class="c1"># ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^</span>
|
|
<span class="n">text</span> <span class="o">=</span> <span class="n">text</span><span class="p">[</span><span class="n">text</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"<script"</span><span class="p">)</span> <span class="p">:</span> <span class="n">text</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"</script"</span><span class="p">)]</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">text</span><span class="p">:</span>
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"can't find JS/JSON data in the given text"</span><span class="p">)</span>
|
|
<span class="n">start</span> <span class="o">=</span> <span class="n">text</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"data: [{"</span><span class="p">)</span>
|
|
<span class="n">end</span> <span class="o">=</span> <span class="n">text</span><span class="o">.</span><span class="n">rindex</span><span class="p">(</span><span class="s2">"}}]"</span><span class="p">)</span>
|
|
<span class="n">js_obj_str</span> <span class="o">=</span> <span class="n">text</span><span class="p">[</span><span class="n">start</span><span class="p">:</span><span class="n">end</span><span class="p">]</span>
|
|
<span class="n">js_obj_str</span> <span class="o">=</span> <span class="s2">"{"</span> <span class="o">+</span> <span class="n">js_obj_str</span> <span class="o">+</span> <span class="s2">"}}]}"</span>
|
|
<span class="c1"># js_obj_str = js_obj_str.replace("\xa0", "") # remove ASCII for &nbsp;</span>
|
|
<span class="c1"># js_obj_str = js_obj_str.replace(r"\u003C", "<").replace(r"\u003c", "<") # fix broken HTML tags in strings</span>
|
|
<span class="n">json_str</span> <span class="o">=</span> <span class="n">js_obj_str_to_json_str</span><span class="p">(</span><span class="n">js_obj_str</span><span class="p">)</span>
|
|
<span class="n">data</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">json_str</span><span class="p">)</span>
|
|
<span class="k">return</span> <span class="n">data</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">:</span> <span class="n">SXNG_Response</span><span class="p">)</span> <span class="o">-></span> <span class="n">EngineResults</span><span class="p">:</span>
|
|
|
|
<span class="k">if</span> <span class="n">brave_category</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'search'</span><span class="p">,</span> <span class="s1">'goggles'</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="n">_parse_search</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="n">brave_category</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'news'</span><span class="p">):</span>
|
|
<span class="k">return</span> <span class="n">_parse_news</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span>
|
|
|
|
<span class="c1"># Example script source containing the data:</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># kit.start(app, element, {</span>
|
|
<span class="c1"># node_ids: [0, 19],</span>
|
|
<span class="c1"># data: [{type:"data",data: .... ["q","goggles_id"],route:1,url:1}}]</span>
|
|
<span class="c1"># ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^</span>
|
|
<span class="n">json_data</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="n">extract_json_data</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">json_resp</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">]</span> <span class="o">=</span> <span class="n">json_data</span><span class="p">[</span><span class="s1">'data'</span><span class="p">][</span><span class="mi">1</span><span class="p">][</span><span class="s2">"data"</span><span class="p">][</span><span class="s1">'body'</span><span class="p">][</span><span class="s1">'response'</span><span class="p">]</span>
|
|
|
|
<span class="k">if</span> <span class="n">brave_category</span> <span class="o">==</span> <span class="s1">'images'</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">_parse_images</span><span class="p">(</span><span class="n">json_resp</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">brave_category</span> <span class="o">==</span> <span class="s1">'videos'</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="n">_parse_videos</span><span class="p">(</span><span class="n">json_resp</span><span class="p">)</span>
|
|
|
|
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Unsupported brave category: </span><span class="si">{</span><span class="n">brave_category</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">_parse_search</span><span class="p">(</span><span class="n">resp</span><span class="p">:</span> <span class="n">SXNG_Response</span><span class="p">)</span> <span class="o">-></span> <span class="n">EngineResults</span><span class="p">:</span>
|
|
<span class="n">res</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
|
|
<span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
|
|
|
|
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s2">"//div[contains(@class, 'snippet ')]"</span><span class="p">):</span>
|
|
|
|
<span class="n">url</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//a/@href"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
|
|
<span class="n">title_tag</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//div[contains(@class, 'title')]"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">url</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">title_tag</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">url</span><span class="p">)</span><span class="o">.</span><span class="n">netloc</span><span class="p">:</span> <span class="c1"># partial url likely means it's an ad</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="n">content</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">""</span>
|
|
<span class="n">pub_date</span> <span class="o">=</span> <span class="kc">None</span>
|
|
|
|
<span class="c1"># there are other classes like 'site-name-content' we don't want to match,</span>
|
|
<span class="c1"># however only using contains(@class, 'content') would e.g. also match `site-name-content`</span>
|
|
<span class="c1"># thus, we explicitly also require the spaces as class separator</span>
|
|
<span class="n">_content</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//div[contains(concat(' ', @class, ' '), ' content ')]"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">_content</span><span class="p">):</span>
|
|
<span class="n">content</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">_content</span><span class="p">)</span> <span class="c1"># type: ignore</span>
|
|
<span class="n">_pub_date</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span>
|
|
<span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">_content</span><span class="p">,</span> <span class="s2">".//span[contains(@class, 't-secondary')]"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span>
|
|
<span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">_pub_date</span><span class="p">:</span>
|
|
<span class="n">pub_date</span> <span class="o">=</span> <span class="n">_extract_published_date</span><span class="p">(</span><span class="n">_pub_date</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">lstrip</span><span class="p">(</span><span class="n">_pub_date</span><span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">(</span><span class="s2">"- </span><span class="se">\n\t</span><span class="s2">"</span><span class="p">)</span>
|
|
|
|
<span class="n">thumbnail</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//a[contains(@class, 'thumbnail')]//img/@src"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span>
|
|
|
|
<span class="n">item</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">LegacyResult</span><span class="p">(</span>
|
|
<span class="n">template</span><span class="o">=</span><span class="s2">"default.html"</span><span class="p">,</span>
|
|
<span class="n">url</span><span class="o">=</span><span class="n">url</span><span class="p">,</span>
|
|
<span class="n">title</span><span class="o">=</span><span class="n">extract_text</span><span class="p">(</span><span class="n">title_tag</span><span class="p">),</span>
|
|
<span class="n">content</span><span class="o">=</span><span class="n">content</span><span class="p">,</span>
|
|
<span class="n">publishedDate</span><span class="o">=</span><span class="n">pub_date</span><span class="p">,</span>
|
|
<span class="n">thumbnail</span><span class="o">=</span><span class="n">thumbnail</span><span class="p">,</span>
|
|
<span class="p">)</span>
|
|
<span class="n">res</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">item</span><span class="p">)</span>
|
|
|
|
<span class="n">video_tag</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span>
|
|
<span class="n">result</span><span class="p">,</span> <span class="s2">".//div[contains(@class, 'video-snippet') and @data-macro='video']"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="p">[]</span>
|
|
<span class="p">)</span>
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">video_tag</span><span class="p">):</span>
|
|
<span class="c1"># In my tests a video tag in the WEB search was most often not a</span>
|
|
<span class="c1"># video, except the ones from youtube ..</span>
|
|
<span class="n">iframe_src</span> <span class="o">=</span> <span class="n">get_embeded_stream_url</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">iframe_src</span><span class="p">:</span>
|
|
<span class="n">item</span><span class="p">[</span><span class="s2">"iframe_src"</span><span class="p">]</span> <span class="o">=</span> <span class="n">iframe_src</span>
|
|
<span class="n">item</span><span class="p">[</span><span class="s2">"template"</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"videos.html"</span>
|
|
|
|
<span class="k">return</span> <span class="n">res</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">_parse_news</span><span class="p">(</span><span class="n">resp</span><span class="p">:</span> <span class="n">SXNG_Response</span><span class="p">)</span> <span class="o">-></span> <span class="n">EngineResults</span><span class="p">:</span>
|
|
<span class="n">res</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
|
|
<span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
|
|
|
|
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s2">"//div[contains(@class, 'results')]//div[@data-type='news']"</span><span class="p">):</span>
|
|
|
|
<span class="n">url</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//a[contains(@class, 'result-header')]/@href"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">url</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="n">title</span> <span class="o">=</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//span[contains(@class, 'snippet-title')]"</span><span class="p">)</span>
|
|
<span class="n">content</span> <span class="o">=</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//p[contains(@class, 'desc')]"</span><span class="p">)</span>
|
|
<span class="n">thumbnail</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s2">".//div[contains(@class, 'image-wrapper')]//img/@src"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span>
|
|
|
|
<span class="n">item</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">LegacyResult</span><span class="p">(</span>
|
|
<span class="n">template</span><span class="o">=</span><span class="s2">"default.html"</span><span class="p">,</span>
|
|
<span class="n">url</span><span class="o">=</span><span class="n">url</span><span class="p">,</span>
|
|
<span class="n">title</span><span class="o">=</span><span class="n">extract_text</span><span class="p">(</span><span class="n">title</span><span class="p">),</span>
|
|
<span class="n">thumbnail</span><span class="o">=</span><span class="n">thumbnail</span><span class="p">,</span>
|
|
<span class="n">content</span><span class="o">=</span><span class="n">extract_text</span><span class="p">(</span><span class="n">content</span><span class="p">),</span>
|
|
<span class="p">)</span>
|
|
<span class="n">res</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">item</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="n">res</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">_parse_images</span><span class="p">(</span><span class="n">json_resp</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">])</span> <span class="o">-></span> <span class="n">EngineResults</span><span class="p">:</span>
|
|
<span class="n">res</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
|
|
|
|
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">json_resp</span><span class="p">[</span><span class="s2">"results"</span><span class="p">]:</span>
|
|
<span class="n">item</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">LegacyResult</span><span class="p">(</span>
|
|
<span class="n">template</span><span class="o">=</span><span class="s2">"images.html"</span><span class="p">,</span>
|
|
<span class="n">url</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"url"</span><span class="p">],</span>
|
|
<span class="n">title</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"title"</span><span class="p">],</span>
|
|
<span class="n">source</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"source"</span><span class="p">],</span>
|
|
<span class="n">img_src</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"properties"</span><span class="p">][</span><span class="s2">"url"</span><span class="p">],</span>
|
|
<span class="n">thumbnail_src</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"thumbnail"</span><span class="p">][</span><span class="s2">"src"</span><span class="p">],</span>
|
|
<span class="p">)</span>
|
|
<span class="n">res</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">item</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="n">res</span>
|
|
|
|
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">_parse_videos</span><span class="p">(</span><span class="n">json_resp</span><span class="p">:</span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">t</span><span class="o">.</span><span class="n">Any</span><span class="p">])</span> <span class="o">-></span> <span class="n">EngineResults</span><span class="p">:</span>
|
|
<span class="n">res</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
|
|
|
|
<span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">json_resp</span><span class="p">[</span><span class="s2">"results"</span><span class="p">]:</span>
|
|
<span class="n">item</span> <span class="o">=</span> <span class="n">res</span><span class="o">.</span><span class="n">types</span><span class="o">.</span><span class="n">LegacyResult</span><span class="p">(</span>
|
|
<span class="n">template</span><span class="o">=</span><span class="s2">"videos.html"</span><span class="p">,</span>
|
|
<span class="n">url</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"url"</span><span class="p">],</span>
|
|
<span class="n">title</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"title"</span><span class="p">],</span>
|
|
<span class="n">content</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"description"</span><span class="p">],</span>
|
|
<span class="n">length</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"video"</span><span class="p">][</span><span class="s2">"duration"</span><span class="p">],</span>
|
|
<span class="n">duration</span><span class="o">=</span><span class="n">result</span><span class="p">[</span><span class="s2">"video"</span><span class="p">][</span><span class="s2">"duration"</span><span class="p">],</span>
|
|
<span class="n">publishedDate</span><span class="o">=</span><span class="n">_extract_published_date</span><span class="p">(</span><span class="n">result</span><span class="p">[</span><span class="s2">"age"</span><span class="p">]),</span>
|
|
<span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">result</span><span class="p">[</span><span class="s2">"thumbnail"</span><span class="p">]</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="n">item</span><span class="p">[</span><span class="s2">"thumbnail"</span><span class="p">]</span> <span class="o">=</span> <span class="n">result</span><span class="p">[</span><span class="s2">"thumbnail"</span><span class="p">][</span><span class="s2">"src"</span><span class="p">]</span>
|
|
<span class="n">iframe_src</span> <span class="o">=</span> <span class="n">get_embeded_stream_url</span><span class="p">(</span><span class="n">result</span><span class="p">[</span><span class="s2">"url"</span><span class="p">])</span>
|
|
<span class="k">if</span> <span class="n">iframe_src</span><span class="p">:</span>
|
|
<span class="n">item</span><span class="p">[</span><span class="s2">"iframe_src"</span><span class="p">]</span> <span class="o">=</span> <span class="n">iframe_src</span>
|
|
|
|
<span class="n">res</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">item</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="n">res</span>
|
|
|
|
|
|
<div class="viewcode-block" id="fetch_traits">
|
|
<a class="viewcode-back" href="../../../dev/engines/online/brave.html#searx.engines.brave.fetch_traits">[docs]</a>
|
|
<span class="k">def</span><span class="w"> </span><span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""Fetch :ref:`languages <brave languages>` and :ref:`regions <brave</span>
|
|
<span class="sd"> regions>` from Brave."""</span>
|
|
|
|
<span class="c1"># pylint: disable=import-outside-toplevel, too-many-branches</span>
|
|
|
|
<span class="kn">import</span><span class="w"> </span><span class="nn">babel.languages</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.locales</span><span class="w"> </span><span class="kn">import</span> <span class="n">region_tag</span><span class="p">,</span> <span class="n">language_tag</span>
|
|
<span class="kn">from</span><span class="w"> </span><span class="nn">searx.network</span><span class="w"> </span><span class="kn">import</span> <span class="n">get</span> <span class="c1"># see https://github.com/searxng/searxng/issues/762</span>
|
|
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"ui_lang"</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
|
|
|
|
<span class="n">lang_map</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'no'</span><span class="p">:</span> <span class="s1">'nb'</span><span class="p">}</span> <span class="c1"># norway</span>
|
|
|
|
<span class="c1"># languages (UI)</span>
|
|
|
|
<span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s1">'https://search.brave.com/settings'</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="nb">print</span><span class="p">(</span><span class="s2">"ERROR: response from Brave is not OK."</span><span class="p">)</span>
|
|
<span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
|
|
|
|
<span class="k">for</span> <span class="n">option</span> <span class="ow">in</span> <span class="n">dom</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s2">"//section//option[@value='en-us']/../option"</span><span class="p">):</span>
|
|
|
|
<span class="n">ui_lang</span> <span class="o">=</span> <span class="n">option</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"value"</span><span class="p">)</span>
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="n">l</span> <span class="o">=</span> <span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">ui_lang</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">"-"</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">l</span><span class="o">.</span><span class="n">territory</span><span class="p">:</span>
|
|
<span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">region_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">ui_lang</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">"-"</span><span class="p">))</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">sxng_tag</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">ui_lang</span><span class="p">,</span> <span class="n">sep</span><span class="o">=</span><span class="s2">"-"</span><span class="p">))</span>
|
|
|
|
<span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span>
|
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"ERROR: can't determine babel locale of Brave's (UI) language </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="n">ui_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">custom</span><span class="p">[</span><span class="s2">"ui_lang"</span><span class="p">]</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="c1"># type: ignore</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">ui_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">ui_lang</span><span class="p">))</span>
|
|
<span class="k">continue</span>
|
|
<span class="n">engine_traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s2">"ui_lang"</span><span class="p">][</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">ui_lang</span>
|
|
|
|
<span class="c1"># search regions of brave</span>
|
|
|
|
<span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s2">"https://cdn.search.brave.com/serp/v2/_app/immutable/chunks/parameters.734c106a.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="nb">print</span><span class="p">(</span><span class="s2">"ERROR: response from Brave is not OK."</span><span class="p">)</span>
|
|
|
|
<span class="n">country_js</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">resp</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"options:{all"</span><span class="p">)</span> <span class="o">+</span> <span class="nb">len</span><span class="p">(</span><span class="s2">"options:"</span><span class="p">)</span> <span class="p">:]</span>
|
|
<span class="n">country_js</span> <span class="o">=</span> <span class="n">country_js</span><span class="p">[:</span> <span class="n">country_js</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s2">"},k={default"</span><span class="p">)]</span>
|
|
<span class="n">country_tags</span> <span class="o">=</span> <span class="n">js_obj_str_to_python</span><span class="p">(</span><span class="n">country_js</span><span class="p">)</span>
|
|
|
|
<span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">country_tags</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
|
|
<span class="k">if</span> <span class="n">k</span> <span class="o">==</span> <span class="s2">"all"</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="s2">"all"</span>
|
|
<span class="k">continue</span>
|
|
<span class="n">country_tag</span> <span class="o">=</span> <span class="n">v</span><span class="p">[</span><span class="s2">"value"</span><span class="p">]</span>
|
|
|
|
<span class="c1"># add official languages of the country ..</span>
|
|
<span class="k">for</span> <span class="n">lang_tag</span> <span class="ow">in</span> <span class="n">babel</span><span class="o">.</span><span class="n">languages</span><span class="o">.</span><span class="n">get_official_languages</span><span class="p">(</span><span class="n">country_tag</span><span class="p">,</span> <span class="n">de_facto</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
|
|
<span class="n">lang_tag</span> <span class="o">=</span> <span class="n">lang_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">lang_tag</span><span class="p">,</span> <span class="n">lang_tag</span><span class="p">)</span>
|
|
<span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">region_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2">_</span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">lang_tag</span><span class="p">,</span> <span class="n">country_tag</span><span class="o">.</span><span class="n">upper</span><span class="p">())))</span>
|
|
<span class="c1"># print("%-20s: %s <-- %s" % (v["label"], country_tag, sxng_tag))</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">country_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">country_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">country_tag</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> |