forked from Archives/searxng
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
494 lines
49 KiB
HTML
494 lines
49 KiB
HTML
|
|
<!DOCTYPE html>
|
|
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
|
<meta name="viewport" content="width=device-width, initial-scale=1">
|
|
<title>searx.engines.google — SearXNG Documentation (2023.1.23+522ba9a1)</title>
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/tabs.css" />
|
|
<script data-url_root="../../../" id="documentation_options" src="../../../_static/documentation_options.js"></script>
|
|
<script src="../../../_static/jquery.js"></script>
|
|
<script src="../../../_static/underscore.js"></script>
|
|
<script src="../../../_static/_sphinx_javascript_frameworks_compat.js"></script>
|
|
<script src="../../../_static/doctools.js"></script>
|
|
<script src="../../../_static/sphinx_highlight.js"></script>
|
|
<script src="../../../_static/tabs.js"></script>
|
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../search.html" />
|
|
</head><body>
|
|
<div class="related" role="navigation" aria-label="related navigation">
|
|
<h3>Navigation</h3>
|
|
<ul>
|
|
<li class="right" style="margin-right: 10px">
|
|
<a href="../../../genindex.html" title="General Index"
|
|
accesskey="I">index</a></li>
|
|
<li class="right" >
|
|
<a href="../../../py-modindex.html" title="Python Module Index"
|
|
>modules</a> |</li>
|
|
<li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2023.1.23+522ba9a1)</a> »</li>
|
|
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> »</li>
|
|
<li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> »</li>
|
|
<li class="nav-item nav-item-this"><a href="">searx.engines.google</a></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="document">
|
|
<div class="documentwrapper">
|
|
<div class="bodywrapper">
|
|
<div class="body" role="main">
|
|
|
|
<h1>Source code for searx.engines.google</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
|
<span class="c1"># lint: pylint</span>
|
|
<span class="sd">"""This is the implementation of the google WEB engine. Some of this</span>
|
|
<span class="sd">implementations are shared by other engines:</span>
|
|
|
|
<span class="sd">- :ref:`google images engine`</span>
|
|
<span class="sd">- :ref:`google news engine`</span>
|
|
<span class="sd">- :ref:`google videos engine`</span>
|
|
|
|
<span class="sd">The google WEB engine itself has a special setup option:</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> - name: google</span>
|
|
<span class="sd"> ...</span>
|
|
<span class="sd"> use_mobile_ui: false</span>
|
|
|
|
<span class="sd">``use_mobile_ui``: (default: ``false``)</span>
|
|
<span class="sd"> Enables to use *mobile endpoint* to bypass the google blocking (see</span>
|
|
<span class="sd"> :issue:`159`). On the mobile UI of Google Search, the button :guilabel:`More</span>
|
|
<span class="sd"> results` is not affected by Google rate limiting and we can still do requests</span>
|
|
<span class="sd"> while actively blocked by the original Google search. By activate</span>
|
|
<span class="sd"> ``use_mobile_ui`` this behavior is simulated by adding the parameter</span>
|
|
<span class="sd"> ``async=use_ac:true,_fmt:pc`` to the :py:func:`request`.</span>
|
|
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">urlencode</span>
|
|
<span class="kn">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.utils</span> <span class="kn">import</span> <span class="n">match_language</span><span class="p">,</span> <span class="n">extract_text</span><span class="p">,</span> <span class="n">eval_xpath</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">,</span> <span class="n">eval_xpath_getindex</span>
|
|
<span class="kn">from</span> <span class="nn">searx.exceptions</span> <span class="kn">import</span> <span class="n">SearxEngineCaptchaException</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://www.google.com'</span><span class="p">,</span>
|
|
<span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s1">'Q9366'</span><span class="p">,</span>
|
|
<span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="s1">'https://developers.google.com/custom-search/'</span><span class="p">,</span>
|
|
<span class="s2">"use_official_api"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="s2">"require_api_key"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
|
|
<span class="s2">"results"</span><span class="p">:</span> <span class="s1">'HTML'</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="c1"># engine dependent config</span>
|
|
<span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'general'</span><span class="p">,</span> <span class="s1">'web'</span><span class="p">]</span>
|
|
<span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">safesearch</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">send_accept_language_header</span> <span class="o">=</span> <span class="kc">True</span>
|
|
<span class="n">use_mobile_ui</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="n">supported_languages_url</span> <span class="o">=</span> <span class="s1">'https://www.google.com/preferences?#languages'</span>
|
|
|
|
<span class="c1"># based on https://en.wikipedia.org/wiki/List_of_Google_domains and tests</span>
|
|
<span class="n">google_domains</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s1">'BG'</span><span class="p">:</span> <span class="s1">'google.bg'</span><span class="p">,</span> <span class="c1"># Bulgaria</span>
|
|
<span class="s1">'CZ'</span><span class="p">:</span> <span class="s1">'google.cz'</span><span class="p">,</span> <span class="c1"># Czech Republic</span>
|
|
<span class="s1">'DE'</span><span class="p">:</span> <span class="s1">'google.de'</span><span class="p">,</span> <span class="c1"># Germany</span>
|
|
<span class="s1">'DK'</span><span class="p">:</span> <span class="s1">'google.dk'</span><span class="p">,</span> <span class="c1"># Denmark</span>
|
|
<span class="s1">'AT'</span><span class="p">:</span> <span class="s1">'google.at'</span><span class="p">,</span> <span class="c1"># Austria</span>
|
|
<span class="s1">'CH'</span><span class="p">:</span> <span class="s1">'google.ch'</span><span class="p">,</span> <span class="c1"># Switzerland</span>
|
|
<span class="s1">'GR'</span><span class="p">:</span> <span class="s1">'google.gr'</span><span class="p">,</span> <span class="c1"># Greece</span>
|
|
<span class="s1">'AU'</span><span class="p">:</span> <span class="s1">'google.com.au'</span><span class="p">,</span> <span class="c1"># Australia</span>
|
|
<span class="s1">'CA'</span><span class="p">:</span> <span class="s1">'google.ca'</span><span class="p">,</span> <span class="c1"># Canada</span>
|
|
<span class="s1">'GB'</span><span class="p">:</span> <span class="s1">'google.co.uk'</span><span class="p">,</span> <span class="c1"># United Kingdom</span>
|
|
<span class="s1">'ID'</span><span class="p">:</span> <span class="s1">'google.co.id'</span><span class="p">,</span> <span class="c1"># Indonesia</span>
|
|
<span class="s1">'IE'</span><span class="p">:</span> <span class="s1">'google.ie'</span><span class="p">,</span> <span class="c1"># Ireland</span>
|
|
<span class="s1">'IN'</span><span class="p">:</span> <span class="s1">'google.co.in'</span><span class="p">,</span> <span class="c1"># India</span>
|
|
<span class="s1">'MY'</span><span class="p">:</span> <span class="s1">'google.com.my'</span><span class="p">,</span> <span class="c1"># Malaysia</span>
|
|
<span class="s1">'NZ'</span><span class="p">:</span> <span class="s1">'google.co.nz'</span><span class="p">,</span> <span class="c1"># New Zealand</span>
|
|
<span class="s1">'PH'</span><span class="p">:</span> <span class="s1">'google.com.ph'</span><span class="p">,</span> <span class="c1"># Philippines</span>
|
|
<span class="s1">'SG'</span><span class="p">:</span> <span class="s1">'google.com.sg'</span><span class="p">,</span> <span class="c1"># Singapore</span>
|
|
<span class="s1">'US'</span><span class="p">:</span> <span class="s1">'google.com'</span><span class="p">,</span> <span class="c1"># United States (google.us) redirects to .com</span>
|
|
<span class="s1">'ZA'</span><span class="p">:</span> <span class="s1">'google.co.za'</span><span class="p">,</span> <span class="c1"># South Africa</span>
|
|
<span class="s1">'AR'</span><span class="p">:</span> <span class="s1">'google.com.ar'</span><span class="p">,</span> <span class="c1"># Argentina</span>
|
|
<span class="s1">'CL'</span><span class="p">:</span> <span class="s1">'google.cl'</span><span class="p">,</span> <span class="c1"># Chile</span>
|
|
<span class="s1">'ES'</span><span class="p">:</span> <span class="s1">'google.es'</span><span class="p">,</span> <span class="c1"># Spain</span>
|
|
<span class="s1">'MX'</span><span class="p">:</span> <span class="s1">'google.com.mx'</span><span class="p">,</span> <span class="c1"># Mexico</span>
|
|
<span class="s1">'EE'</span><span class="p">:</span> <span class="s1">'google.ee'</span><span class="p">,</span> <span class="c1"># Estonia</span>
|
|
<span class="s1">'FI'</span><span class="p">:</span> <span class="s1">'google.fi'</span><span class="p">,</span> <span class="c1"># Finland</span>
|
|
<span class="s1">'BE'</span><span class="p">:</span> <span class="s1">'google.be'</span><span class="p">,</span> <span class="c1"># Belgium</span>
|
|
<span class="s1">'FR'</span><span class="p">:</span> <span class="s1">'google.fr'</span><span class="p">,</span> <span class="c1"># France</span>
|
|
<span class="s1">'IL'</span><span class="p">:</span> <span class="s1">'google.co.il'</span><span class="p">,</span> <span class="c1"># Israel</span>
|
|
<span class="s1">'HR'</span><span class="p">:</span> <span class="s1">'google.hr'</span><span class="p">,</span> <span class="c1"># Croatia</span>
|
|
<span class="s1">'HU'</span><span class="p">:</span> <span class="s1">'google.hu'</span><span class="p">,</span> <span class="c1"># Hungary</span>
|
|
<span class="s1">'IT'</span><span class="p">:</span> <span class="s1">'google.it'</span><span class="p">,</span> <span class="c1"># Italy</span>
|
|
<span class="s1">'JP'</span><span class="p">:</span> <span class="s1">'google.co.jp'</span><span class="p">,</span> <span class="c1"># Japan</span>
|
|
<span class="s1">'KR'</span><span class="p">:</span> <span class="s1">'google.co.kr'</span><span class="p">,</span> <span class="c1"># South Korea</span>
|
|
<span class="s1">'LT'</span><span class="p">:</span> <span class="s1">'google.lt'</span><span class="p">,</span> <span class="c1"># Lithuania</span>
|
|
<span class="s1">'LV'</span><span class="p">:</span> <span class="s1">'google.lv'</span><span class="p">,</span> <span class="c1"># Latvia</span>
|
|
<span class="s1">'NO'</span><span class="p">:</span> <span class="s1">'google.no'</span><span class="p">,</span> <span class="c1"># Norway</span>
|
|
<span class="s1">'NL'</span><span class="p">:</span> <span class="s1">'google.nl'</span><span class="p">,</span> <span class="c1"># Netherlands</span>
|
|
<span class="s1">'PL'</span><span class="p">:</span> <span class="s1">'google.pl'</span><span class="p">,</span> <span class="c1"># Poland</span>
|
|
<span class="s1">'BR'</span><span class="p">:</span> <span class="s1">'google.com.br'</span><span class="p">,</span> <span class="c1"># Brazil</span>
|
|
<span class="s1">'PT'</span><span class="p">:</span> <span class="s1">'google.pt'</span><span class="p">,</span> <span class="c1"># Portugal</span>
|
|
<span class="s1">'RO'</span><span class="p">:</span> <span class="s1">'google.ro'</span><span class="p">,</span> <span class="c1"># Romania</span>
|
|
<span class="s1">'RU'</span><span class="p">:</span> <span class="s1">'google.ru'</span><span class="p">,</span> <span class="c1"># Russia</span>
|
|
<span class="s1">'SK'</span><span class="p">:</span> <span class="s1">'google.sk'</span><span class="p">,</span> <span class="c1"># Slovakia</span>
|
|
<span class="s1">'SI'</span><span class="p">:</span> <span class="s1">'google.si'</span><span class="p">,</span> <span class="c1"># Slovenia</span>
|
|
<span class="s1">'SE'</span><span class="p">:</span> <span class="s1">'google.se'</span><span class="p">,</span> <span class="c1"># Sweden</span>
|
|
<span class="s1">'TH'</span><span class="p">:</span> <span class="s1">'google.co.th'</span><span class="p">,</span> <span class="c1"># Thailand</span>
|
|
<span class="s1">'TR'</span><span class="p">:</span> <span class="s1">'google.com.tr'</span><span class="p">,</span> <span class="c1"># Turkey</span>
|
|
<span class="s1">'UA'</span><span class="p">:</span> <span class="s1">'google.com.ua'</span><span class="p">,</span> <span class="c1"># Ukraine</span>
|
|
<span class="s1">'CN'</span><span class="p">:</span> <span class="s1">'google.com.hk'</span><span class="p">,</span> <span class="c1"># There is no google.cn, we use .com.hk for zh-CN</span>
|
|
<span class="s1">'HK'</span><span class="p">:</span> <span class="s1">'google.com.hk'</span><span class="p">,</span> <span class="c1"># Hong Kong</span>
|
|
<span class="s1">'TW'</span><span class="p">:</span> <span class="s1">'google.com.tw'</span><span class="p">,</span> <span class="c1"># Taiwan</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="n">time_range_dict</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'day'</span><span class="p">:</span> <span class="s1">'d'</span><span class="p">,</span> <span class="s1">'week'</span><span class="p">:</span> <span class="s1">'w'</span><span class="p">,</span> <span class="s1">'month'</span><span class="p">:</span> <span class="s1">'m'</span><span class="p">,</span> <span class="s1">'year'</span><span class="p">:</span> <span class="s1">'y'</span><span class="p">}</span>
|
|
|
|
<span class="c1"># Filter results. 0: None, 1: Moderate, 2: Strict</span>
|
|
<span class="n">filter_mapping</span> <span class="o">=</span> <span class="p">{</span><span class="mi">0</span><span class="p">:</span> <span class="s1">'off'</span><span class="p">,</span> <span class="mi">1</span><span class="p">:</span> <span class="s1">'medium'</span><span class="p">,</span> <span class="mi">2</span><span class="p">:</span> <span class="s1">'high'</span><span class="p">}</span>
|
|
|
|
<span class="c1"># specific xpath variables</span>
|
|
<span class="c1"># ------------------------</span>
|
|
|
|
<span class="n">results_xpath</span> <span class="o">=</span> <span class="s1">'.//div[@data-sokoban-container]'</span>
|
|
<span class="n">title_xpath</span> <span class="o">=</span> <span class="s1">'.//a/h3[1]'</span>
|
|
<span class="n">href_xpath</span> <span class="o">=</span> <span class="s1">'.//a[h3]/@href'</span>
|
|
<span class="n">content_xpath</span> <span class="o">=</span> <span class="s1">'.//div[@data-content-feature=1]'</span>
|
|
|
|
<span class="c1"># google *sections* are no usual *results*, we ignore them</span>
|
|
<span class="n">g_section_with_header</span> <span class="o">=</span> <span class="s1">'./g-section-with-header'</span>
|
|
|
|
|
|
<span class="c1"># Suggestions are links placed in a *card-section*, we extract only the text</span>
|
|
<span class="c1"># from the links not the links itself.</span>
|
|
<span class="n">suggestion_xpath</span> <span class="o">=</span> <span class="s1">'//div[contains(@class, "EIaa9b")]//a'</span>
|
|
|
|
|
|
<div class="viewcode-block" id="get_lang_info"><a class="viewcode-back" href="../../../src/searx.engines.google.html#searx.engines.google.get_lang_info">[docs]</a><span class="k">def</span> <span class="nf">get_lang_info</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">lang_list</span><span class="p">,</span> <span class="n">custom_aliases</span><span class="p">,</span> <span class="n">supported_any_language</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""Composing various language properties for the google engines.</span>
|
|
|
|
<span class="sd"> This function is called by the various google engines (:ref:`google web</span>
|
|
<span class="sd"> engine`, :ref:`google images engine`, :ref:`google news engine` and</span>
|
|
<span class="sd"> :ref:`google videos engine`).</span>
|
|
|
|
<span class="sd"> :param dict param: request parameters of the engine</span>
|
|
|
|
<span class="sd"> :param list lang_list: list of supported languages of the engine</span>
|
|
<span class="sd"> :py:obj:`ENGINES_LANGUAGES[engine-name] <searx.data.ENGINES_LANGUAGES>`</span>
|
|
|
|
<span class="sd"> :param dict lang_list: custom aliases for non standard language codes</span>
|
|
<span class="sd"> (used when calling :py:func:`searx.utils.match_language`)</span>
|
|
|
|
<span class="sd"> :param bool supported_any_language: When a language is not specified, the</span>
|
|
<span class="sd"> language interpretation is left up to Google to decide how the search</span>
|
|
<span class="sd"> results should be delivered. This argument is ``True`` for the google</span>
|
|
<span class="sd"> engine and ``False`` for the other engines (google-images, -news,</span>
|
|
<span class="sd"> -scholar, -videos).</span>
|
|
|
|
<span class="sd"> :rtype: dict</span>
|
|
<span class="sd"> :returns:</span>
|
|
<span class="sd"> Py-Dictionary with the key/value pairs:</span>
|
|
|
|
<span class="sd"> language:</span>
|
|
<span class="sd"> Return value from :py:func:`searx.utils.match_language`</span>
|
|
|
|
<span class="sd"> country:</span>
|
|
<span class="sd"> The country code (e.g. US, AT, CA, FR, DE ..)</span>
|
|
|
|
<span class="sd"> subdomain:</span>
|
|
<span class="sd"> Google subdomain :py:obj:`google_domains` that fits to the country</span>
|
|
<span class="sd"> code.</span>
|
|
|
|
<span class="sd"> params:</span>
|
|
<span class="sd"> Py-Dictionary with additional request arguments (can be passed to</span>
|
|
<span class="sd"> :py:func:`urllib.parse.urlencode`).</span>
|
|
|
|
<span class="sd"> headers:</span>
|
|
<span class="sd"> Py-Dictionary with additional HTTP headers (can be passed to</span>
|
|
<span class="sd"> request's headers)</span>
|
|
<span class="sd"> """</span>
|
|
<span class="n">ret_val</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s1">'language'</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="s1">'country'</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="s1">'subdomain'</span><span class="p">:</span> <span class="kc">None</span><span class="p">,</span>
|
|
<span class="s1">'params'</span><span class="p">:</span> <span class="p">{},</span>
|
|
<span class="s1">'headers'</span><span class="p">:</span> <span class="p">{},</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="c1"># language ...</span>
|
|
|
|
<span class="n">_lang</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s1">'language'</span><span class="p">]</span>
|
|
<span class="n">_any_language</span> <span class="o">=</span> <span class="n">_lang</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="s1">'all'</span>
|
|
<span class="k">if</span> <span class="n">_any_language</span><span class="p">:</span>
|
|
<span class="n">_lang</span> <span class="o">=</span> <span class="s1">'en-US'</span>
|
|
<span class="n">language</span> <span class="o">=</span> <span class="n">match_language</span><span class="p">(</span><span class="n">_lang</span><span class="p">,</span> <span class="n">lang_list</span><span class="p">,</span> <span class="n">custom_aliases</span><span class="p">)</span>
|
|
<span class="n">ret_val</span><span class="p">[</span><span class="s1">'language'</span><span class="p">]</span> <span class="o">=</span> <span class="n">language</span>
|
|
|
|
<span class="c1"># country ...</span>
|
|
|
|
<span class="n">_l</span> <span class="o">=</span> <span class="n">_lang</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'-'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">_l</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
|
|
<span class="n">country</span> <span class="o">=</span> <span class="n">_l</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">country</span> <span class="o">=</span> <span class="n">_l</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">upper</span><span class="p">()</span>
|
|
<span class="k">if</span> <span class="n">country</span> <span class="o">==</span> <span class="s1">'EN'</span><span class="p">:</span>
|
|
<span class="n">country</span> <span class="o">=</span> <span class="s1">'US'</span>
|
|
<span class="n">ret_val</span><span class="p">[</span><span class="s1">'country'</span><span class="p">]</span> <span class="o">=</span> <span class="n">country</span>
|
|
|
|
<span class="c1"># subdomain ...</span>
|
|
|
|
<span class="n">ret_val</span><span class="p">[</span><span class="s1">'subdomain'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'www.'</span> <span class="o">+</span> <span class="n">google_domains</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">country</span><span class="o">.</span><span class="n">upper</span><span class="p">(),</span> <span class="s1">'google.com'</span><span class="p">)</span>
|
|
|
|
<span class="c1"># params & headers</span>
|
|
|
|
<span class="n">lang_country</span> <span class="o">=</span> <span class="s1">'</span><span class="si">%s</span><span class="s1">-</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="n">language</span><span class="p">,</span> <span class="n">country</span><span class="p">)</span> <span class="c1"># (en-US, en-EN, de-DE, de-AU, fr-FR ..)</span>
|
|
|
|
<span class="c1"># hl parameter:</span>
|
|
<span class="c1"># https://developers.google.com/custom-search/docs/xml_results#hlsp The</span>
|
|
<span class="c1"># Interface Language:</span>
|
|
<span class="c1"># https://developers.google.com/custom-search/docs/xml_results_appendices#interfaceLanguages</span>
|
|
|
|
<span class="n">ret_val</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'hl'</span><span class="p">]</span> <span class="o">=</span> <span class="n">lang_list</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">lang_country</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
|
|
<span class="c1"># lr parameter:</span>
|
|
<span class="c1"># The lr (language restrict) parameter restricts search results to</span>
|
|
<span class="c1"># documents written in a particular language.</span>
|
|
<span class="c1"># https://developers.google.com/custom-search/docs/xml_results#lrsp</span>
|
|
<span class="c1"># Language Collection Values:</span>
|
|
<span class="c1"># https://developers.google.com/custom-search/docs/xml_results_appendices#languageCollections</span>
|
|
|
|
<span class="k">if</span> <span class="n">_any_language</span> <span class="ow">and</span> <span class="n">supported_any_language</span><span class="p">:</span>
|
|
|
|
<span class="c1"># interpretation is left up to Google (based on whoogle)</span>
|
|
<span class="c1">#</span>
|
|
<span class="c1"># - add parameter ``source=lnt``</span>
|
|
<span class="c1"># - don't use parameter ``lr``</span>
|
|
<span class="c1"># - don't add a ``Accept-Language`` HTTP header.</span>
|
|
|
|
<span class="n">ret_val</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'source'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'lnt'</span>
|
|
|
|
<span class="k">else</span><span class="p">:</span>
|
|
|
|
<span class="c1"># restricts search results to documents written in a particular</span>
|
|
<span class="c1"># language.</span>
|
|
<span class="n">ret_val</span><span class="p">[</span><span class="s1">'params'</span><span class="p">][</span><span class="s1">'lr'</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"lang_"</span> <span class="o">+</span> <span class="n">lang_list</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">lang_country</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
|
|
|
|
<span class="k">return</span> <span class="n">ret_val</span></div>
|
|
|
|
|
|
<span class="k">def</span> <span class="nf">detect_google_sorry</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
|
|
<span class="k">if</span> <span class="n">resp</span><span class="o">.</span><span class="n">url</span><span class="o">.</span><span class="n">host</span> <span class="o">==</span> <span class="s1">'sorry.google.com'</span> <span class="ow">or</span> <span class="n">resp</span><span class="o">.</span><span class="n">url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'/sorry'</span><span class="p">):</span>
|
|
<span class="k">raise</span> <span class="n">SearxEngineCaptchaException</span><span class="p">()</span>
|
|
|
|
|
|
<div class="viewcode-block" id="request"><a class="viewcode-back" href="../../../src/searx.engines.google.html#searx.engines.google.request">[docs]</a><span class="k">def</span> <span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""Google search request"""</span>
|
|
|
|
<span class="n">offset</span> <span class="o">=</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">'pageno'</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="mi">10</span>
|
|
|
|
<span class="n">lang_info</span> <span class="o">=</span> <span class="n">get_lang_info</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">supported_languages</span><span class="p">,</span> <span class="n">language_aliases</span><span class="p">,</span> <span class="kc">True</span><span class="p">)</span>
|
|
|
|
<span class="n">additional_parameters</span> <span class="o">=</span> <span class="p">{}</span>
|
|
<span class="k">if</span> <span class="n">use_mobile_ui</span><span class="p">:</span>
|
|
<span class="n">additional_parameters</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s1">'asearch'</span><span class="p">:</span> <span class="s1">'arc'</span><span class="p">,</span>
|
|
<span class="s1">'async'</span><span class="p">:</span> <span class="s1">'use_ac:true,_fmt:prog'</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="c1"># https://www.google.de/search?q=corona&hl=de&lr=lang_de&start=0&tbs=qdr%3Ad&safe=medium</span>
|
|
<span class="n">query_url</span> <span class="o">=</span> <span class="p">(</span>
|
|
<span class="s1">'https://'</span>
|
|
<span class="o">+</span> <span class="n">lang_info</span><span class="p">[</span><span class="s1">'subdomain'</span><span class="p">]</span>
|
|
<span class="o">+</span> <span class="s1">'/search'</span>
|
|
<span class="o">+</span> <span class="s2">"?"</span>
|
|
<span class="o">+</span> <span class="n">urlencode</span><span class="p">(</span>
|
|
<span class="p">{</span>
|
|
<span class="s1">'q'</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
|
|
<span class="o">**</span><span class="n">lang_info</span><span class="p">[</span><span class="s1">'params'</span><span class="p">],</span>
|
|
<span class="s1">'ie'</span><span class="p">:</span> <span class="s2">"utf8"</span><span class="p">,</span>
|
|
<span class="s1">'oe'</span><span class="p">:</span> <span class="s2">"utf8"</span><span class="p">,</span>
|
|
<span class="s1">'start'</span><span class="p">:</span> <span class="n">offset</span><span class="p">,</span>
|
|
<span class="s1">'filter'</span><span class="p">:</span> <span class="s1">'0'</span><span class="p">,</span>
|
|
<span class="o">**</span><span class="n">additional_parameters</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="p">)</span>
|
|
<span class="p">)</span>
|
|
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'time_range'</span><span class="p">]</span> <span class="ow">in</span> <span class="n">time_range_dict</span><span class="p">:</span>
|
|
<span class="n">query_url</span> <span class="o">+=</span> <span class="s1">'&'</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">({</span><span class="s1">'tbs'</span><span class="p">:</span> <span class="s1">'qdr:'</span> <span class="o">+</span> <span class="n">time_range_dict</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s1">'time_range'</span><span class="p">]]})</span>
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'safesearch'</span><span class="p">]:</span>
|
|
<span class="n">query_url</span> <span class="o">+=</span> <span class="s1">'&'</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">({</span><span class="s1">'safe'</span><span class="p">:</span> <span class="n">filter_mapping</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s1">'safesearch'</span><span class="p">]]})</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]</span> <span class="o">=</span> <span class="n">query_url</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">][</span><span class="s1">'CONSENT'</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"YES+"</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">lang_info</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">])</span>
|
|
<span class="k">if</span> <span class="n">use_mobile_ui</span><span class="p">:</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">][</span><span class="s1">'Accept'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'*/*'</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">][</span><span class="s1">'Accept'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'</span>
|
|
|
|
<span class="k">return</span> <span class="n">params</span></div>
|
|
|
|
|
|
<div class="viewcode-block" id="response"><a class="viewcode-back" href="../../../src/searx.engines.google.html#searx.engines.google.response">[docs]</a><span class="k">def</span> <span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
|
|
<span class="w"> </span><span class="sd">"""Get response from google's search request"""</span>
|
|
|
|
<span class="n">detect_google_sorry</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span>
|
|
|
|
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
|
|
|
|
<span class="c1"># convert the text to dom</span>
|
|
<span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
|
|
<span class="c1"># results --> answer</span>
|
|
<span class="n">answer_list</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">'//div[contains(@class, "LGOjhe")]'</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">answer_list</span><span class="p">:</span>
|
|
<span class="n">answer_list</span> <span class="o">=</span> <span class="p">[</span><span class="n">_</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s2">"normalize-space()"</span><span class="p">)</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="n">answer_list</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="s1">' '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">answer_list</span><span class="p">)})</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"did not find 'answer'"</span><span class="p">)</span>
|
|
|
|
<span class="c1"># results --> number_of_results</span>
|
|
<span class="k">if</span> <span class="ow">not</span> <span class="n">use_mobile_ui</span><span class="p">:</span>
|
|
<span class="k">try</span><span class="p">:</span>
|
|
<span class="n">_txt</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">'//div[@id="result-stats"]//text()'</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span>
|
|
<span class="n">_digit</span> <span class="o">=</span> <span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">n</span> <span class="k">for</span> <span class="n">n</span> <span class="ow">in</span> <span class="n">_txt</span> <span class="k">if</span> <span class="n">n</span><span class="o">.</span><span class="n">isdigit</span><span class="p">()])</span>
|
|
<span class="n">number_of_results</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">_digit</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">'number_of_results'</span><span class="p">:</span> <span class="n">number_of_results</span><span class="p">})</span>
|
|
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"did not 'number_of_results'"</span><span class="p">)</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">exc_info</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
|
|
<span class="c1"># parse results</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="n">results_xpath</span><span class="p">):</span>
|
|
|
|
<span class="c1"># google *sections*</span>
|
|
<span class="k">if</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">g_section_with_header</span><span class="p">)):</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"ignoring <g-section-with-header>"</span><span class="p">)</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="k">try</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="n">title_xpath</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">title_tag</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="c1"># this not one of the common google results *section*</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">'ignoring item from the result_xpath list: missing title'</span><span class="p">)</span>
|
|
<span class="k">continue</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">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="n">href_xpath</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">url</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
|
|
<span class="k">continue</span>
|
|
<span class="n">content</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">result</span><span class="p">,</span> <span class="n">content_xpath</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">allow_none</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="n">content</span> <span class="ow">is</span> <span class="kc">None</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">'ignoring item from the result_xpath list: missing content of title "</span><span class="si">%s</span><span class="s1">"'</span><span class="p">,</span> <span class="n">title</span><span class="p">)</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">'add link to results: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">title</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">url</span><span class="p">,</span> <span class="s1">'title'</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span> <span class="s1">'content'</span><span class="p">:</span> <span class="n">content</span><span class="p">})</span>
|
|
|
|
<span class="k">except</span> <span class="ne">Exception</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span>
|
|
<span class="n">logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="n">exc_info</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
|
<span class="k">continue</span>
|
|
|
|
<span class="c1"># parse suggestion</span>
|
|
<span class="k">for</span> <span class="n">suggestion</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="n">suggestion_xpath</span><span class="p">):</span>
|
|
<span class="c1"># append suggestion</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">extract_text</span><span class="p">(</span><span class="n">suggestion</span><span class="p">)})</span>
|
|
|
|
<span class="c1"># return results</span>
|
|
<span class="k">return</span> <span class="n">results</span></div>
|
|
|
|
|
|
<span class="c1"># get supported languages from their site</span>
|
|
<span class="k">def</span> <span class="nf">_fetch_supported_languages</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
|
|
<span class="n">ret_val</span> <span class="o">=</span> <span class="p">{}</span>
|
|
<span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
|
|
|
|
<span class="n">radio_buttons</span> <span class="o">=</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">'//*[@id="langSec"]//input[@name="lr"]'</span><span class="p">)</span>
|
|
|
|
<span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">radio_buttons</span><span class="p">:</span>
|
|
<span class="n">name</span> <span class="o">=</span> <span class="n">x</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"data-name"</span><span class="p">)</span>
|
|
<span class="n">code</span> <span class="o">=</span> <span class="n">x</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="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'_'</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
|
|
<span class="n">ret_val</span><span class="p">[</span><span class="n">code</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"name"</span><span class="p">:</span> <span class="n">name</span><span class="p">}</span>
|
|
|
|
<span class="k">return</span> <span class="n">ret_val</span>
|
|
</pre></div>
|
|
|
|
<div class="clearer"></div>
|
|
</div>
|
|
</div>
|
|
</div>
|
|
<span id="sidebar-top"></span>
|
|
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
|
<div class="sphinxsidebarwrapper">
|
|
|
|
|
|
<p class="logo"><a href="../../../index.html">
|
|
<img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo"/>
|
|
</a></p>
|
|
|
|
|
|
<h3><a href="../../../index.html">Table of Contents</a></h3>
|
|
<p class="caption" role="heading"><span class="caption-text">Contents</span></p>
|
|
<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>
|
|
<li class="toctree-l1"><a class="reference internal" href="../../../donate.html">Donate to searxng.org</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>
|
|
<div 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>
|
|
</div>
|
|
<script>document.getElementById('searchbox').style.display = "block"</script>
|
|
</div>
|
|
</div>
|
|
<div class="clearer"></div>
|
|
</div>
|
|
|
|
<div class="footer" role="contentinfo">
|
|
© Copyright 2021 SearXNG team, 2015-2021 Adam Tauber, Noémi Ványi.
|
|
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 5.3.0.
|
|
</div>
|
|
<script src="../../../_static/version_warning_offset.js"></script>
|
|
|
|
</body>
|
|
</html> |