searxng/_modules/searx/engines/bing_news.html
2024-04-24 14:03:54 +00:00

279 lines
23 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.bing_news &#8212; SearXNG Documentation (2024.4.24+e0214412f)</title>
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=4f649999" />
<link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
<link rel="stylesheet" type="text/css" href="../../../_static/tabs.css?v=a5c4661c" />
<script src="../../../_static/documentation_options.js?v=68e7c2e2"></script>
<script src="../../../_static/doctools.js?v=888ff710"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/tabs.js?v=3030b3cb"></script>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
</head><body>
<div class="related" role="navigation" aria-label="related navigation">
<h3>Navigation</h3>
<ul>
<li class="right" style="margin-right: 10px">
<a href="../../../genindex.html" title="General Index"
accesskey="I">index</a></li>
<li class="right" >
<a href="../../../py-modindex.html" title="Python Module Index"
>modules</a> |</li>
<li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2024.4.24+e0214412f)</a> &#187;</li>
<li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li>
<li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> &#187;</li>
<li class="nav-item nav-item-this"><a href="">searx.engines.bing_news</a></li>
</ul>
</div>
<div class="document">
<div class="documentwrapper">
<div class="bodywrapper">
<div class="body" role="main">
<h1>Source code for searx.engines.bing_news</h1><div class="highlight"><pre>
<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
<span class="sd">&quot;&quot;&quot;Bing-News: description see :py:obj:`searx.engines.bing`.</span>
<span class="sd">.. hint::</span>
<span class="sd"> Bing News is *different* in some ways!</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="c1"># pylint: disable=invalid-name</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">TYPE_CHECKING</span>
<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">urlencode</span>
<span class="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">eval_xpath</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="kn">from</span> <span class="nn">searx.enginelib.traits</span> <span class="kn">import</span> <span class="n">EngineTraits</span>
<span class="kn">from</span> <span class="nn">searx.engines.bing</span> <span class="kn">import</span> <span class="n">set_bing_cookies</span>
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="n">logger</span><span class="p">:</span> <span class="n">logging</span><span class="o">.</span><span class="n">Logger</span>
<span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
<span class="c1"># about</span>
<span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="s1">&#39;https://www.bing.com/news&#39;</span><span class="p">,</span>
<span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s1">&#39;Q2878637&#39;</span><span class="p">,</span>
<span class="s2">&quot;official_api_documentation&quot;</span><span class="p">:</span> <span class="s1">&#39;https://www.microsoft.com/en-us/bing/apis/bing-news-search-api&#39;</span><span class="p">,</span>
<span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
<span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
<span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s1">&#39;RSS&#39;</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">&#39;news&#39;</span><span class="p">]</span>
<span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
<span class="sd">&quot;&quot;&quot;If go through the pages and there are actually no new results for another</span>
<span class="sd">page, then bing returns the results from the last page again.&quot;&quot;&quot;</span>
<span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
<span class="n">time_map</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;day&#39;</span><span class="p">:</span> <span class="s1">&#39;interval=&quot;4&quot;&#39;</span><span class="p">,</span>
<span class="s1">&#39;week&#39;</span><span class="p">:</span> <span class="s1">&#39;interval=&quot;7&quot;&#39;</span><span class="p">,</span>
<span class="s1">&#39;month&#39;</span><span class="p">:</span> <span class="s1">&#39;interval=&quot;9&quot;&#39;</span><span class="p">,</span>
<span class="p">}</span>
<span class="sd">&quot;&quot;&quot;A string &#39;4&#39; means *last hour*. We use *last hour* for ``day`` here since the</span>
<span class="sd">difference of *last day* and *last week* in the result list is just marginally.</span>
<span class="sd">Bing does not have news range ``year`` / we use ``month`` instead.&quot;&quot;&quot;</span>
<span class="n">base_url</span> <span class="o">=</span> <span class="s1">&#39;https://www.bing.com/news/infinitescrollajax&#39;</span>
<span class="sd">&quot;&quot;&quot;Bing (News) search URL&quot;&quot;&quot;</span>
<div class="viewcode-block" id="request">
<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing_news.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">&quot;&quot;&quot;Assemble a Bing-News request.&quot;&quot;&quot;</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="s1">&#39;searxng_locale&#39;</span><span class="p">],</span> <span class="n">traits</span><span class="o">.</span><span class="n">all_locale</span><span class="p">)</span> <span class="c1"># type: ignore</span>
<span class="n">engine_language</span> <span class="o">=</span> <span class="n">traits</span><span class="o">.</span><span class="n">get_language</span><span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;searxng_locale&#39;</span><span class="p">],</span> <span class="s1">&#39;en&#39;</span><span class="p">)</span> <span class="c1"># type: ignore</span>
<span class="n">set_bing_cookies</span><span class="p">(</span><span class="n">params</span><span class="p">,</span> <span class="n">engine_language</span><span class="p">,</span> <span class="n">engine_region</span><span class="p">)</span>
<span class="c1"># build URL query</span>
<span class="c1">#</span>
<span class="c1"># example: https://www.bing.com/news/infinitescrollajax?q=london&amp;first=1</span>
<span class="n">page</span> <span class="o">=</span> <span class="nb">int</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">&#39;pageno&#39;</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="n">query_params</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">&#39;q&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
<span class="s1">&#39;InfiniteScroll&#39;</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span>
<span class="c1"># to simplify the page count lets use the default of 10 images per page</span>
<span class="s1">&#39;first&#39;</span><span class="p">:</span> <span class="n">page</span> <span class="o">*</span> <span class="mi">10</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span>
<span class="s1">&#39;SFX&#39;</span><span class="p">:</span> <span class="n">page</span><span class="p">,</span>
<span class="s1">&#39;form&#39;</span><span class="p">:</span> <span class="s1">&#39;PTFTNR&#39;</span><span class="p">,</span>
<span class="s1">&#39;setlang&#39;</span><span class="p">:</span> <span class="n">engine_region</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;-&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">],</span>
<span class="s1">&#39;cc&#39;</span><span class="p">:</span> <span class="n">engine_region</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;-&#39;</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</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">&#39;time_range&#39;</span><span class="p">]:</span>
<span class="n">query_params</span><span class="p">[</span><span class="s1">&#39;qft&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">time_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="s1">&#39;time_range&#39;</span><span class="p">],</span> <span class="s1">&#39;interval=&quot;9&quot;&#39;</span><span class="p">)</span>
<span class="n">params</span><span class="p">[</span><span class="s1">&#39;url&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">base_url</span> <span class="o">+</span> <span class="s1">&#39;?&#39;</span> <span class="o">+</span> <span class="n">urlencode</span><span class="p">(</span><span class="n">query_params</span><span class="p">)</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/online/bing.html#searx.engines.bing_news.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">&quot;&quot;&quot;Get response from Bing-Video&quot;&quot;&quot;</span>
<span class="n">results</span> <span class="o">=</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="ow">or</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">:</span>
<span class="k">return</span> <span class="n">results</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">newsitem</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="s1">&#39;//div[contains(@class, &quot;newsitem&quot;)]&#39;</span><span class="p">):</span>
<span class="n">link</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">newsitem</span><span class="p">,</span> <span class="s1">&#39;.//a[@class=&quot;title&quot;]&#39;</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">link</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">continue</span>
<span class="n">url</span> <span class="o">=</span> <span class="n">link</span><span class="o">.</span><span class="n">attrib</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;href&#39;</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">link</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</span><span class="p">(</span><span class="n">newsitem</span><span class="p">,</span> <span class="s1">&#39;.//div[@class=&quot;snippet&quot;]&#39;</span><span class="p">))</span>
<span class="n">metadata</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">source</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">newsitem</span><span class="p">,</span> <span class="s1">&#39;.//div[contains(@class, &quot;source&quot;)]&#39;</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">source</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">for</span> <span class="n">item</span> <span class="ow">in</span> <span class="p">(</span>
<span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">source</span><span class="p">,</span> <span class="s1">&#39;.//span[@aria-label]/@aria-label&#39;</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="c1"># eval_xpath_getindex(source, &#39;.//a&#39;, 0, None),</span>
<span class="c1"># eval_xpath_getindex(source, &#39;./div/span&#39;, 3, None),</span>
<span class="n">link</span><span class="o">.</span><span class="n">attrib</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;data-author&#39;</span><span class="p">),</span>
<span class="p">):</span>
<span class="k">if</span> <span class="n">item</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">t</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">item</span><span class="p">)</span>
<span class="k">if</span> <span class="n">t</span> <span class="ow">and</span> <span class="n">t</span><span class="o">.</span><span class="n">strip</span><span class="p">():</span>
<span class="n">metadata</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">t</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span>
<span class="n">metadata</span> <span class="o">=</span> <span class="s1">&#39; | &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">metadata</span><span class="p">)</span>
<span class="n">thumbnail</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">imagelink</span> <span class="o">=</span> <span class="n">eval_xpath_getindex</span><span class="p">(</span><span class="n">newsitem</span><span class="p">,</span> <span class="s1">&#39;.//a[@class=&quot;imagelink&quot;]//img&#39;</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">imagelink</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">thumbnail</span> <span class="o">=</span> <span class="s1">&#39;https://www.bing.com/&#39;</span> <span class="o">+</span> <span class="n">imagelink</span><span class="o">.</span><span class="n">attrib</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;src&#39;</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">&#39;url&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span>
<span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
<span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span>
<span class="s1">&#39;img_src&#39;</span><span class="p">:</span> <span class="n">thumbnail</span><span class="p">,</span>
<span class="s1">&#39;metadata&#39;</span><span class="p">:</span> <span class="n">metadata</span><span class="p">,</span>
<span class="p">}</span>
<span class="p">)</span>
<span class="k">return</span> <span class="n">results</span></div>
<div class="viewcode-block" id="fetch_traits">
<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing_news.fetch_traits">[docs]</a>
<span class="k">def</span> <span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Fetch languages and regions from Bing-News.&quot;&quot;&quot;</span>
<span class="c1"># pylint: disable=import-outside-toplevel</span>
<span class="kn">from</span> <span class="nn">searx.engines.bing</span> <span class="kn">import</span> <span class="n">fetch_traits</span> <span class="k">as</span> <span class="n">_f</span>
<span class="n">_f</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">)</span>
<span class="c1"># fix market codes not known by bing news:</span>
<span class="c1"># In bing the market code &#39;zh-cn&#39; exists, but there is no &#39;news&#39; category in</span>
<span class="c1"># bing for this market. Alternatively we use the the market code from Honk</span>
<span class="c1"># Kong. Even if this is not correct, it is better than having no hits at</span>
<span class="c1"># all, or sending false queries to bing that could raise the suspicion of a</span>
<span class="c1"># bot.</span>
<span class="c1"># HINT: &#39;en-hk&#39; is the region code it does not indicate the language en!!</span>
<span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="p">[</span><span class="s1">&#39;zh-CN&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;en-hk&#39;</span></div>
</pre></div>
<div class="clearer"></div>
</div>
</div>
</div>
<span id="sidebar-top"></span>
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
<div class="sphinxsidebarwrapper">
<p class="logo"><a href="../../../index.html">
<img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo"/>
</a></p>
<h3><a href="../../../index.html">Table of Contents</a></h3>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
</ul>
<h3>Project Links</h3>
<ul>
<li><a href="https://github.com/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">
&#169; Copyright SearXNG team.
</div>
<script src="../../../_static/version_warning_offset.js"></script>
</body>
</html>