mirror of https://github.com/searxng/searxng.git
425 lines
32 KiB
HTML
425 lines
32 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.xpath — SearXNG Documentation (2024.11.22+b8f1a329d)</title>
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=4f649999" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
|
|
<link rel="stylesheet" type="text/css" href="../../../_static/autodoc_pydantic.css" />
|
|
<script src="../../../_static/documentation_options.js?v=16d153d8"></script>
|
|
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
|
|
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
|
<script data-project="searxng" data-version="2024.11.22+b8f1a329d" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
|
|
<link rel="index" title="Index" href="../../../genindex.html" />
|
|
<link rel="search" title="Search" href="../../../search.html" />
|
|
</head><body>
|
|
<div class="related" role="navigation" aria-label="Related">
|
|
<h3>Navigation</h3>
|
|
<ul>
|
|
<li class="right" style="margin-right: 10px">
|
|
<a href="../../../genindex.html" title="General Index"
|
|
accesskey="I">index</a></li>
|
|
<li class="right" >
|
|
<a href="../../../py-modindex.html" title="Python Module Index"
|
|
>modules</a> |</li>
|
|
<li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2024.11.22+b8f1a329d)</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.xpath</a></li>
|
|
</ul>
|
|
</div>
|
|
|
|
<div class="document">
|
|
<div class="documentwrapper">
|
|
<div class="bodywrapper">
|
|
<div class="body" role="main">
|
|
|
|
<h1>Source code for searx.engines.xpath</h1><div class="highlight"><pre>
|
|
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
|
|
<span class="sd">"""The XPath engine is a *generic* engine with which it is possible to configure</span>
|
|
<span class="sd">engines in the settings.</span>
|
|
|
|
<span class="sd">.. _XPath selector: https://quickref.me/xpath.html#xpath-selectors</span>
|
|
|
|
<span class="sd">Configuration</span>
|
|
<span class="sd">=============</span>
|
|
|
|
<span class="sd">Request:</span>
|
|
|
|
<span class="sd">- :py:obj:`search_url`</span>
|
|
<span class="sd">- :py:obj:`lang_all`</span>
|
|
<span class="sd">- :py:obj:`soft_max_redirects`</span>
|
|
<span class="sd">- :py:obj:`cookies`</span>
|
|
<span class="sd">- :py:obj:`headers`</span>
|
|
|
|
<span class="sd">Paging:</span>
|
|
|
|
<span class="sd">- :py:obj:`paging`</span>
|
|
<span class="sd">- :py:obj:`page_size`</span>
|
|
<span class="sd">- :py:obj:`first_page_num`</span>
|
|
|
|
<span class="sd">Time Range:</span>
|
|
|
|
<span class="sd">- :py:obj:`time_range_support`</span>
|
|
<span class="sd">- :py:obj:`time_range_url`</span>
|
|
<span class="sd">- :py:obj:`time_range_map`</span>
|
|
|
|
<span class="sd">Safe-Search:</span>
|
|
|
|
<span class="sd">- :py:obj:`safe_search_support`</span>
|
|
<span class="sd">- :py:obj:`safe_search_map`</span>
|
|
|
|
<span class="sd">Response:</span>
|
|
|
|
<span class="sd">- :py:obj:`no_result_for_http_status`</span>
|
|
|
|
<span class="sd">`XPath selector`_:</span>
|
|
|
|
<span class="sd">- :py:obj:`results_xpath`</span>
|
|
<span class="sd">- :py:obj:`url_xpath`</span>
|
|
<span class="sd">- :py:obj:`title_xpath`</span>
|
|
<span class="sd">- :py:obj:`content_xpath`</span>
|
|
<span class="sd">- :py:obj:`thumbnail_xpath`</span>
|
|
<span class="sd">- :py:obj:`suggestion_xpath`</span>
|
|
|
|
|
|
<span class="sd">Example</span>
|
|
<span class="sd">=======</span>
|
|
|
|
<span class="sd">Here is a simple example of a XPath engine configured in the :ref:`settings</span>
|
|
<span class="sd">engine` section, further read :ref:`engines-dev`.</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> - name : bitbucket</span>
|
|
<span class="sd"> engine : xpath</span>
|
|
<span class="sd"> paging : True</span>
|
|
<span class="sd"> search_url : https://bitbucket.org/repo/all/{pageno}?name={query}</span>
|
|
<span class="sd"> url_xpath : //article[@class="repo-summary"]//a[@class="repo-link"]/@href</span>
|
|
<span class="sd"> title_xpath : //article[@class="repo-summary"]//a[@class="repo-link"]</span>
|
|
<span class="sd"> content_xpath : //article[@class="repo-summary"]/p</span>
|
|
|
|
<span class="sd">Implementations</span>
|
|
<span class="sd">===============</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">extract_text</span><span class="p">,</span> <span class="n">extract_url</span><span class="p">,</span> <span class="n">eval_xpath</span><span class="p">,</span> <span class="n">eval_xpath_list</span>
|
|
<span class="kn">from</span> <span class="nn">searx.network</span> <span class="kn">import</span> <span class="n">raise_for_httperror</span>
|
|
|
|
<span class="n">search_url</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="sd">"""</span>
|
|
<span class="sd">Search URL of the engine. Example::</span>
|
|
|
|
<span class="sd"> https://example.org/?search={query}&page={pageno}{time_range}{safe_search}</span>
|
|
|
|
<span class="sd">Replacements are:</span>
|
|
|
|
<span class="sd">``{query}``:</span>
|
|
<span class="sd"> Search terms from user.</span>
|
|
|
|
<span class="sd">``{pageno}``:</span>
|
|
<span class="sd"> Page number if engine supports paging :py:obj:`paging`</span>
|
|
|
|
<span class="sd">``{lang}``:</span>
|
|
<span class="sd"> ISO 639-1 language code (en, de, fr ..)</span>
|
|
|
|
<span class="sd">``{time_range}``:</span>
|
|
<span class="sd"> :py:obj:`URL parameter <time_range_url>` if engine :py:obj:`supports time</span>
|
|
<span class="sd"> range <time_range_support>`. The value for the parameter is taken from</span>
|
|
<span class="sd"> :py:obj:`time_range_map`.</span>
|
|
|
|
<span class="sd">``{safe_search}``:</span>
|
|
<span class="sd"> Safe-search :py:obj:`URL parameter <safe_search_map>` if engine</span>
|
|
<span class="sd"> :py:obj:`supports safe-search <safe_search_support>`. The ``{safe_search}``</span>
|
|
<span class="sd"> replacement is taken from the :py:obj:`safes_search_map`. Filter results::</span>
|
|
|
|
<span class="sd"> 0: none, 1: moderate, 2:strict</span>
|
|
|
|
<span class="sd"> If not supported, the URL parameter is an empty string.</span>
|
|
|
|
<span class="sd">"""</span>
|
|
|
|
<span class="n">lang_all</span> <span class="o">=</span> <span class="s1">'en'</span>
|
|
<span class="sd">'''Replacement ``{lang}`` in :py:obj:`search_url` if language ``all`` is</span>
|
|
<span class="sd">selected.</span>
|
|
<span class="sd">'''</span>
|
|
|
|
<span class="n">no_result_for_http_status</span> <span class="o">=</span> <span class="p">[]</span>
|
|
<span class="sd">'''Return empty result for these HTTP status codes instead of throwing an error.</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> no_result_for_http_status: []</span>
|
|
<span class="sd">'''</span>
|
|
|
|
<span class="n">soft_max_redirects</span> <span class="o">=</span> <span class="mi">0</span>
|
|
<span class="sd">'''Maximum redirects, soft limit. Record an error but don't stop the engine'''</span>
|
|
|
|
<span class="n">results_xpath</span> <span class="o">=</span> <span class="s1">''</span>
|
|
<span class="sd">'''`XPath selector`_ for the list of result items'''</span>
|
|
|
|
<span class="n">url_xpath</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="sd">'''`XPath selector`_ of result's ``url``.'''</span>
|
|
|
|
<span class="n">content_xpath</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="sd">'''`XPath selector`_ of result's ``content``.'''</span>
|
|
|
|
<span class="n">title_xpath</span> <span class="o">=</span> <span class="kc">None</span>
|
|
<span class="sd">'''`XPath selector`_ of result's ``title``.'''</span>
|
|
|
|
<span class="n">thumbnail_xpath</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="sd">'''`XPath selector`_ of result's ``thumbnail``.'''</span>
|
|
|
|
<span class="n">suggestion_xpath</span> <span class="o">=</span> <span class="s1">''</span>
|
|
<span class="sd">'''`XPath selector`_ of result's ``suggestion``.'''</span>
|
|
|
|
<span class="n">cached_xpath</span> <span class="o">=</span> <span class="s1">''</span>
|
|
<span class="n">cached_url</span> <span class="o">=</span> <span class="s1">''</span>
|
|
|
|
<span class="n">cookies</span> <span class="o">=</span> <span class="p">{}</span>
|
|
<span class="sd">'''Some engines might offer different result based on cookies.</span>
|
|
<span class="sd">Possible use-case: To set safesearch cookie.'''</span>
|
|
|
|
<span class="n">headers</span> <span class="o">=</span> <span class="p">{}</span>
|
|
<span class="sd">'''Some engines might offer different result based headers. Possible use-case:</span>
|
|
<span class="sd">To set header to moderate.'''</span>
|
|
|
|
<span class="n">paging</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="sd">'''Engine supports paging [True or False].'''</span>
|
|
|
|
<span class="n">page_size</span> <span class="o">=</span> <span class="mi">1</span>
|
|
<span class="sd">'''Number of results on each page. Only needed if the site requires not a page</span>
|
|
<span class="sd">number, but an offset.'''</span>
|
|
|
|
<span class="n">first_page_num</span> <span class="o">=</span> <span class="mi">1</span>
|
|
<span class="sd">'''Number of the first page (usually 0 or 1).'''</span>
|
|
|
|
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="sd">'''Engine supports search time range.'''</span>
|
|
|
|
<span class="n">time_range_url</span> <span class="o">=</span> <span class="s1">'&hours=</span><span class="si">{time_range_val}</span><span class="s1">'</span>
|
|
<span class="sd">'''Time range URL parameter in the in :py:obj:`search_url`. If no time range is</span>
|
|
<span class="sd">requested by the user, the URL parameter is an empty string. The</span>
|
|
<span class="sd">``{time_range_val}`` replacement is taken from the :py:obj:`time_range_map`.</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> time_range_url : '&days={time_range_val}'</span>
|
|
<span class="sd">'''</span>
|
|
|
|
<span class="n">time_range_map</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s1">'day'</span><span class="p">:</span> <span class="mi">24</span><span class="p">,</span>
|
|
<span class="s1">'week'</span><span class="p">:</span> <span class="mi">24</span> <span class="o">*</span> <span class="mi">7</span><span class="p">,</span>
|
|
<span class="s1">'month'</span><span class="p">:</span> <span class="mi">24</span> <span class="o">*</span> <span class="mi">30</span><span class="p">,</span>
|
|
<span class="s1">'year'</span><span class="p">:</span> <span class="mi">24</span> <span class="o">*</span> <span class="mi">365</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="sd">'''Maps time range value from user to ``{time_range_val}`` in</span>
|
|
<span class="sd">:py:obj:`time_range_url`.</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> time_range_map:</span>
|
|
<span class="sd"> day: 1</span>
|
|
<span class="sd"> week: 7</span>
|
|
<span class="sd"> month: 30</span>
|
|
<span class="sd"> year: 365</span>
|
|
<span class="sd">'''</span>
|
|
|
|
<span class="n">safe_search_support</span> <span class="o">=</span> <span class="kc">False</span>
|
|
<span class="sd">'''Engine supports safe-search.'''</span>
|
|
|
|
<span class="n">safe_search_map</span> <span class="o">=</span> <span class="p">{</span><span class="mi">0</span><span class="p">:</span> <span class="s1">'&filter=none'</span><span class="p">,</span> <span class="mi">1</span><span class="p">:</span> <span class="s1">'&filter=moderate'</span><span class="p">,</span> <span class="mi">2</span><span class="p">:</span> <span class="s1">'&filter=strict'</span><span class="p">}</span>
|
|
<span class="sd">'''Maps safe-search value to ``{safe_search}`` in :py:obj:`search_url`.</span>
|
|
|
|
<span class="sd">.. code:: yaml</span>
|
|
|
|
<span class="sd"> safesearch: true</span>
|
|
<span class="sd"> safes_search_map:</span>
|
|
<span class="sd"> 0: '&filter=none'</span>
|
|
<span class="sd"> 1: '&filter=moderate'</span>
|
|
<span class="sd"> 2: '&filter=strict'</span>
|
|
|
|
<span class="sd">'''</span>
|
|
|
|
|
|
<div class="viewcode-block" id="request">
|
|
<a class="viewcode-back" href="../../../dev/engines/xpath.html#searx.engines.xpath.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">'''Build request parameters (see :ref:`engine request`).'''</span>
|
|
<span class="n">lang</span> <span class="o">=</span> <span class="n">lang_all</span>
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'language'</span><span class="p">]</span> <span class="o">!=</span> <span class="s1">'all'</span><span class="p">:</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="mi">2</span><span class="p">]</span>
|
|
|
|
<span class="n">time_range</span> <span class="o">=</span> <span class="s1">''</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="s1">'time_range'</span><span class="p">):</span>
|
|
<span class="n">time_range_val</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="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'time_range'</span><span class="p">))</span>
|
|
<span class="n">time_range</span> <span class="o">=</span> <span class="n">time_range_url</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">time_range_val</span><span class="o">=</span><span class="n">time_range_val</span><span class="p">)</span>
|
|
|
|
<span class="n">safe_search</span> <span class="o">=</span> <span class="s1">''</span>
|
|
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">'safesearch'</span><span class="p">]:</span>
|
|
<span class="n">safe_search</span> <span class="o">=</span> <span class="n">safe_search_map</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">fargs</span> <span class="o">=</span> <span class="p">{</span>
|
|
<span class="s1">'query'</span><span class="p">:</span> <span class="n">urlencode</span><span class="p">({</span><span class="s1">'q'</span><span class="p">:</span> <span class="n">query</span><span class="p">})[</span><span class="mi">2</span><span class="p">:],</span>
|
|
<span class="s1">'lang'</span><span class="p">:</span> <span class="n">lang</span><span class="p">,</span>
|
|
<span class="s1">'pageno'</span><span class="p">:</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="n">page_size</span> <span class="o">+</span> <span class="n">first_page_num</span><span class="p">,</span>
|
|
<span class="s1">'time_range'</span><span class="p">:</span> <span class="n">time_range</span><span class="p">,</span>
|
|
<span class="s1">'safe_search'</span><span class="p">:</span> <span class="n">safe_search</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">cookies</span><span class="p">)</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'headers'</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">headers</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">search_url</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="n">fargs</span><span class="p">)</span>
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'soft_max_redirects'</span><span class="p">]</span> <span class="o">=</span> <span class="n">soft_max_redirects</span>
|
|
|
|
<span class="n">params</span><span class="p">[</span><span class="s1">'raise_for_httperror'</span><span class="p">]</span> <span class="o">=</span> <span class="kc">False</span>
|
|
|
|
<span class="k">return</span> <span class="n">params</span></div>
|
|
|
|
|
|
|
|
<div class="viewcode-block" id="response">
|
|
<a class="viewcode-back" href="../../../dev/engines/xpath.html#searx.engines.xpath.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="c1"># pylint: disable=too-many-branches</span>
|
|
<span class="w"> </span><span class="sd">'''Scrap *results* from the response (see :ref:`engine results`).'''</span>
|
|
<span class="k">if</span> <span class="n">no_result_for_http_status</span> <span class="ow">and</span> <span class="n">resp</span><span class="o">.</span><span class="n">status_code</span> <span class="ow">in</span> <span class="n">no_result_for_http_status</span><span class="p">:</span>
|
|
<span class="k">return</span> <span class="p">[]</span>
|
|
|
|
<span class="n">raise_for_httperror</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="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">is_onion</span> <span class="o">=</span> <span class="s1">'onions'</span> <span class="ow">in</span> <span class="n">categories</span>
|
|
|
|
<span class="k">if</span> <span class="n">results_xpath</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="n">results_xpath</span><span class="p">):</span>
|
|
|
|
<span class="n">url</span> <span class="o">=</span> <span class="n">extract_url</span><span class="p">(</span><span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">url_xpath</span><span class="p">,</span> <span class="n">min_len</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span> <span class="n">search_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">eval_xpath_list</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="n">min_len</span><span class="o">=</span><span class="mi">1</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">eval_xpath_list</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="n">tmp_result</span> <span class="o">=</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="c1"># add thumbnail if available</span>
|
|
<span class="k">if</span> <span class="n">thumbnail_xpath</span><span class="p">:</span>
|
|
<span class="n">thumbnail_xpath_result</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="n">thumbnail_xpath</span><span class="p">)</span>
|
|
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">thumbnail_xpath_result</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span>
|
|
<span class="n">tmp_result</span><span class="p">[</span><span class="s1">'thumbnail'</span><span class="p">]</span> <span class="o">=</span> <span class="n">extract_url</span><span class="p">(</span><span class="n">thumbnail_xpath_result</span><span class="p">,</span> <span class="n">search_url</span><span class="p">)</span>
|
|
|
|
<span class="c1"># add alternative cached url if available</span>
|
|
<span class="k">if</span> <span class="n">cached_xpath</span><span class="p">:</span>
|
|
<span class="n">tmp_result</span><span class="p">[</span><span class="s1">'cached_url'</span><span class="p">]</span> <span class="o">=</span> <span class="n">cached_url</span> <span class="o">+</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">result</span><span class="p">,</span> <span class="n">cached_xpath</span><span class="p">,</span> <span class="n">min_len</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
|
|
|
|
<span class="k">if</span> <span class="n">is_onion</span><span class="p">:</span>
|
|
<span class="n">tmp_result</span><span class="p">[</span><span class="s1">'is_onion'</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span>
|
|
|
|
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">tmp_result</span><span class="p">)</span>
|
|
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="k">if</span> <span class="n">cached_xpath</span><span class="p">:</span>
|
|
<span class="k">for</span> <span class="n">url</span><span class="p">,</span> <span class="n">title</span><span class="p">,</span> <span class="n">content</span><span class="p">,</span> <span class="n">cached</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span>
|
|
<span class="p">(</span><span class="n">extract_url</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">search_url</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</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">url_xpath</span><span class="p">)),</span>
|
|
<span class="nb">map</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">dom</span><span class="p">,</span> <span class="n">title_xpath</span><span class="p">)),</span>
|
|
<span class="nb">map</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">dom</span><span class="p">,</span> <span class="n">content_xpath</span><span class="p">)),</span>
|
|
<span class="nb">map</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">dom</span><span class="p">,</span> <span class="n">cached_xpath</span><span class="p">)),</span>
|
|
<span class="p">):</span>
|
|
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
|
|
<span class="p">{</span>
|
|
<span class="s1">'url'</span><span class="p">:</span> <span class="n">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="s1">'cached_url'</span><span class="p">:</span> <span class="n">cached_url</span> <span class="o">+</span> <span class="n">cached</span><span class="p">,</span>
|
|
<span class="s1">'is_onion'</span><span class="p">:</span> <span class="n">is_onion</span><span class="p">,</span>
|
|
<span class="p">}</span>
|
|
<span class="p">)</span>
|
|
<span class="k">else</span><span class="p">:</span>
|
|
<span class="k">for</span> <span class="n">url</span><span class="p">,</span> <span class="n">title</span><span class="p">,</span> <span class="n">content</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span>
|
|
<span class="p">(</span><span class="n">extract_url</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">search_url</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</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">url_xpath</span><span class="p">)),</span>
|
|
<span class="nb">map</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">dom</span><span class="p">,</span> <span class="n">title_xpath</span><span class="p">)),</span>
|
|
<span class="nb">map</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">dom</span><span class="p">,</span> <span class="n">content_xpath</span><span class="p">)),</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="s1">'is_onion'</span><span class="p">:</span> <span class="n">is_onion</span><span class="p">})</span>
|
|
|
|
<span class="k">if</span> <span class="n">suggestion_xpath</span><span class="p">:</span>
|
|
<span class="k">for</span> <span class="n">suggestion</span> <span class="ow">in</span> <span class="n">eval_xpath</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="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="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"found </span><span class="si">%s</span><span class="s2"> results"</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">results</span><span class="p">))</span>
|
|
<span class="k">return</span> <span class="n">results</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> |