diff options
Diffstat (limited to '_modules/searx/engines/bing.html')
-rw-r--r-- | _modules/searx/engines/bing.html | 391 |
1 files changed, 391 insertions, 0 deletions
diff --git a/_modules/searx/engines/bing.html b/_modules/searx/engines/bing.html new file mode 100644 index 000000000..5f897597b --- /dev/null +++ b/_modules/searx/engines/bing.html @@ -0,0 +1,391 @@ +<!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 — SearXNG Documentation (2025.1.6+6dab7fe78)</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" /> + <script src="../../../_static/documentation_options.js?v=ef740023"></script> + <script src="../../../_static/doctools.js?v=9a2dae69"></script> + <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script> + <script data-project="searxng" data-version="2025.1.6+6dab7fe78" src="../../../_static/describe_version.js?v=fa7f30d0"></script> + <link rel="index" title="Index" href="../../../genindex.html" /> + <link rel="search" title="Search" href="../../../search.html" /> + </head><body> + <div class="related" role="navigation" aria-label="Related"> + <h3>Navigation</h3> + <ul> + <li class="right" style="margin-right: 10px"> + <a href="../../../genindex.html" title="General Index" + accesskey="I">index</a></li> + <li class="right" > + <a href="../../../py-modindex.html" title="Python Module Index" + >modules</a> |</li> + <li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2025.1.6+6dab7fe78)</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.bing</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</h1><div class="highlight"><pre> +<span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span> +<span class="sd">"""This is the implementation of the Bing-WEB engine. Some of this</span> +<span class="sd">implementations are shared by other engines:</span> + +<span class="sd">- :ref:`bing images engine`</span> +<span class="sd">- :ref:`bing news engine`</span> +<span class="sd">- :ref:`bing videos engine`</span> + +<span class="sd">On the `preference page`_ Bing offers a lot of languages an regions (see section</span> +<span class="sd">LANGUAGE and COUNTRY/REGION). The Language is the language of the UI, we need</span> +<span class="sd">in SearXNG to get the translations of data such as *"published last week"*.</span> + +<span class="sd">There is a description of the official search-APIs_, unfortunately this is not</span> +<span class="sd">the API we can use or that bing itself would use. You can look up some things</span> +<span class="sd">in the API to get a better picture of bing, but the value specifications like</span> +<span class="sd">the market codes are usually outdated or at least no longer used by bing itself.</span> + +<span class="sd">The market codes have been harmonized and are identical for web, video and</span> +<span class="sd">images. The news area has also been harmonized with the other categories. Only</span> +<span class="sd">political adjustments still seem to be made -- for example, there is no news</span> +<span class="sd">category for the Chinese market.</span> + +<span class="sd">.. _preference page: https://www.bing.com/account/general</span> +<span class="sd">.. _search-APIs: https://learn.microsoft.com/en-us/bing/search-apis/</span> + +<span class="sd">"""</span> +<span class="c1"># pylint: disable=too-many-branches, 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">import</span> <span class="nn">base64</span> +<span class="kn">import</span> <span class="nn">re</span> +<span class="kn">import</span> <span class="nn">time</span> +<span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="kn">import</span> <span class="n">parse_qs</span><span class="p">,</span> <span class="n">urlencode</span><span class="p">,</span> <span class="n">urlparse</span> +<span class="kn">from</span> <span class="nn">lxml</span> <span class="kn">import</span> <span class="n">html</span> +<span class="kn">import</span> <span class="nn">babel</span> +<span class="kn">import</span> <span class="nn">babel.languages</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.locales</span> <span class="kn">import</span> <span class="n">language_tag</span><span class="p">,</span> <span class="n">region_tag</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="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="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">()</span> + +<span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</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.bing.com'</span><span class="p">,</span> + <span class="s2">"wikidata_id"</span><span class="p">:</span> <span class="s1">'Q182496'</span><span class="p">,</span> + <span class="s2">"official_api_documentation"</span><span class="p">:</span> <span class="s1">'https://www.microsoft.com/en-us/bing/apis/bing-web-search-api'</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">max_page</span> <span class="o">=</span> <span class="mi">200</span> +<span class="sd">"""200 pages maximum (``&first=1991``)"""</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="sd">"""Bing results are always SFW. To get NSFW links from bing some age</span> +<span class="sd">verification by a cookie is needed / thats not possible in SearXNG.</span> +<span class="sd">"""</span> + +<span class="n">base_url</span> <span class="o">=</span> <span class="s1">'https://www.bing.com/search'</span> +<span class="sd">"""Bing (Web) search URL"""</span> + + +<span class="k">def</span> <span class="nf">_page_offset</span><span class="p">(</span><span class="n">pageno</span><span class="p">):</span> + <span class="k">return</span> <span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">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="o">+</span> <span class="mi">1</span> + + +<span class="k">def</span> <span class="nf">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="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">][</span><span class="s1">'_EDGE_CD'</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">'m=</span><span class="si">{</span><span class="n">engine_region</span><span class="si">}</span><span class="s1">&u=</span><span class="si">{</span><span class="n">engine_language</span><span class="si">}</span><span class="s1">'</span> + <span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">][</span><span class="s1">'_EDGE_S'</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">'mkt=</span><span class="si">{</span><span class="n">engine_region</span><span class="si">}</span><span class="s1">&ui=</span><span class="si">{</span><span class="n">engine_language</span><span class="si">}</span><span class="s1">'</span> + <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"bing cookies: </span><span class="si">%s</span><span class="s2">"</span><span class="p">,</span> <span class="n">params</span><span class="p">[</span><span class="s1">'cookies'</span><span class="p">])</span> + + +<div class="viewcode-block" id="request"> +<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.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">"""Assemble a Bing-Web request."""</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">'searxng_locale'</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">'searxng_locale'</span><span class="p">],</span> <span class="s1">'en'</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="n">page</span> <span class="o">=</span> <span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'pageno'</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> + <span class="n">query_params</span> <span class="o">=</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="c1"># if arg 'pq' is missed, sometimes on page 4 we get results from page 1,</span> + <span class="c1"># don't ask why it is only sometimes / its M$ and they have never been</span> + <span class="c1"># deterministic ;)</span> + <span class="s1">'pq'</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span> + <span class="p">}</span> + + <span class="c1"># To get correct page, arg first and this arg FORM is needed, the value PERE</span> + <span class="c1"># is on page 2, on page 3 its PERE1 and on page 4 its PERE2 .. and so forth.</span> + <span class="c1"># The 'first' arg should never send on page 1.</span> + + <span class="k">if</span> <span class="n">page</span> <span class="o">></span> <span class="mi">1</span><span class="p">:</span> + <span class="n">query_params</span><span class="p">[</span><span class="s1">'first'</span><span class="p">]</span> <span class="o">=</span> <span class="n">_page_offset</span><span class="p">(</span><span class="n">page</span><span class="p">)</span> <span class="c1"># see also arg FORM</span> + <span class="k">if</span> <span class="n">page</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span> + <span class="n">query_params</span><span class="p">[</span><span class="s1">'FORM'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'PERE'</span> + <span class="k">elif</span> <span class="n">page</span> <span class="o">></span> <span class="mi">2</span><span class="p">:</span> + <span class="n">query_params</span><span class="p">[</span><span class="s1">'FORM'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'PERE</span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="n">page</span> <span class="o">-</span> <span class="mi">2</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="sa">f</span><span class="s1">'</span><span class="si">{</span><span class="n">base_url</span><span class="si">}</span><span class="s1">?</span><span class="si">{</span><span class="n">urlencode</span><span class="p">(</span><span class="n">query_params</span><span class="p">)</span><span class="si">}</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">unix_day</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">/</span> <span class="mi">86400</span><span class="p">)</span> + <span class="n">time_ranges</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'day'</span><span class="p">:</span> <span class="s1">'1'</span><span class="p">,</span> <span class="s1">'week'</span><span class="p">:</span> <span class="s1">'2'</span><span class="p">,</span> <span class="s1">'month'</span><span class="p">:</span> <span class="s1">'3'</span><span class="p">,</span> <span class="s1">'year'</span><span class="p">:</span> <span class="sa">f</span><span class="s1">'5_</span><span class="si">{</span><span class="n">unix_day</span><span class="o">-</span><span class="mi">365</span><span class="si">}</span><span class="s1">_</span><span class="si">{</span><span class="n">unix_day</span><span class="si">}</span><span class="s1">'</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="sa">f</span><span class="s1">'&filters=ex1:"ez</span><span class="si">{</span><span class="n">time_ranges</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s2">"time_range"</span><span class="p">]]</span><span class="si">}</span><span class="s1">"'</span> + + <span class="k">return</span> <span class="n">params</span></div> + + + +<span class="k">def</span> <span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span> + <span class="c1"># pylint: disable=too-many-locals</span> + + <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span> + <span class="n">result_len</span> <span class="o">=</span> <span class="mi">0</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"># parse results again if nothing is found yet</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="s1">'//ol[@id="b_results"]/li[contains(@class, "b_algo")]'</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">result</span><span class="p">,</span> <span class="s1">'.//h2/a'</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">'href'</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">eval_xpath</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="s1">'.//p'</span><span class="p">)</span> + <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">content</span><span class="p">:</span> + <span class="c1"># Make sure that the element is free of:</span> + <span class="c1"># <span class="algoSlug_icon" # data-priority="2">Web</span></span> + <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">p</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">'.//span[@class="algoSlug_icon"]'</span><span class="p">):</span> + <span class="n">e</span><span class="o">.</span><span class="n">getparent</span><span class="p">()</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> + <span class="n">content</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">content</span><span class="p">)</span> + + <span class="c1"># get the real URL</span> + <span class="k">if</span> <span class="n">url</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'https://www.bing.com/ck/a?'</span><span class="p">):</span> + <span class="c1"># get the first value of u parameter</span> + <span class="n">url_query</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">url</span><span class="p">)</span><span class="o">.</span><span class="n">query</span> + <span class="n">parsed_url_query</span> <span class="o">=</span> <span class="n">parse_qs</span><span class="p">(</span><span class="n">url_query</span><span class="p">)</span> + <span class="n">param_u</span> <span class="o">=</span> <span class="n">parsed_url_query</span><span class="p">[</span><span class="s2">"u"</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> + <span class="c1"># remove "a1" in front</span> + <span class="n">encoded_url</span> <span class="o">=</span> <span class="n">param_u</span><span class="p">[</span><span class="mi">2</span><span class="p">:]</span> + <span class="c1"># add padding</span> + <span class="n">encoded_url</span> <span class="o">=</span> <span class="n">encoded_url</span> <span class="o">+</span> <span class="s1">'='</span> <span class="o">*</span> <span class="p">(</span><span class="o">-</span><span class="nb">len</span><span class="p">(</span><span class="n">encoded_url</span><span class="p">)</span> <span class="o">%</span> <span class="mi">4</span><span class="p">)</span> + <span class="c1"># decode base64 encoded URL</span> + <span class="n">url</span> <span class="o">=</span> <span class="n">base64</span><span class="o">.</span><span class="n">urlsafe_b64decode</span><span class="p">(</span><span class="n">encoded_url</span><span class="p">)</span><span class="o">.</span><span class="n">decode</span><span class="p">()</span> + + <span class="c1"># append result</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="c1"># get number_of_results</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">result_len_container</span> <span class="o">=</span> <span class="s2">""</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">eval_xpath</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="s1">'//span[@class="sb_count"]//text()'</span><span class="p">))</span> + <span class="k">if</span> <span class="s2">"-"</span> <span class="ow">in</span> <span class="n">result_len_container</span><span class="p">:</span> + + <span class="c1"># Remove the part "from-to" for paginated request ...</span> + <span class="n">result_len_container</span> <span class="o">=</span> <span class="n">result_len_container</span><span class="p">[</span><span class="n">result_len_container</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">"-"</span><span class="p">)</span> <span class="o">*</span> <span class="mi">2</span> <span class="o">+</span> <span class="mi">2</span> <span class="p">:]</span> + + <span class="n">result_len_container</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="s1">'[^0-9]'</span><span class="p">,</span> <span class="s1">''</span><span class="p">,</span> <span class="n">result_len_container</span><span class="p">)</span> + + <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">result_len_container</span><span class="p">)</span> <span class="o">></span> <span class="mi">0</span><span class="p">:</span> + <span class="n">result_len</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">result_len_container</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="s1">'result error :</span><span class="se">\n</span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span> + + <span class="k">if</span> <span class="n">result_len</span> <span class="ow">and</span> <span class="n">_page_offset</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">search_params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"pageno"</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span> <span class="o">></span> <span class="n">result_len</span><span class="p">:</span> + <span class="c1"># Avoid reading more results than available.</span> + <span class="c1"># For example, if there is 100 results from some search and we try to get results from 120 to 130,</span> + <span class="c1"># Bing will send back the results from 0 to 10 and no error.</span> + <span class="c1"># If we compare results count with the first parameter of the request we can avoid this "invalid" results.</span> + <span class="k">return</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">result_len</span><span class="p">})</span> + <span class="k">return</span> <span class="n">results</span> + + +<div class="viewcode-block" id="fetch_traits"> +<a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.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">"""Fetch languages and regions from Bing-Web."""</span> + <span class="c1"># pylint: disable=import-outside-toplevel</span> + + <span class="kn">from</span> <span class="nn">searx.network</span> <span class="kn">import</span> <span class="n">get</span> <span class="c1"># see https://github.com/searxng/searxng/issues/762</span> + <span class="kn">from</span> <span class="nn">searx.utils</span> <span class="kn">import</span> <span class="n">gen_useragent</span> + + <span class="n">headers</span> <span class="o">=</span> <span class="p">{</span> + <span class="s2">"User-Agent"</span><span class="p">:</span> <span class="n">gen_useragent</span><span class="p">(),</span> + <span class="s2">"Accept"</span><span class="p">:</span> <span class="s2">"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8"</span><span class="p">,</span> + <span class="s2">"Accept-Language"</span><span class="p">:</span> <span class="s2">"en-US;q=0.5,en;q=0.3"</span><span class="p">,</span> + <span class="s2">"Accept-Encoding"</span><span class="p">:</span> <span class="s2">"gzip, deflate, br"</span><span class="p">,</span> + <span class="s2">"DNT"</span><span class="p">:</span> <span class="s2">"1"</span><span class="p">,</span> + <span class="s2">"Connection"</span><span class="p">:</span> <span class="s2">"keep-alive"</span><span class="p">,</span> + <span class="s2">"Upgrade-Insecure-Requests"</span><span class="p">:</span> <span class="s2">"1"</span><span class="p">,</span> + <span class="s2">"Sec-GPC"</span><span class="p">:</span> <span class="s2">"1"</span><span class="p">,</span> + <span class="s2">"Cache-Control"</span><span class="p">:</span> <span class="s2">"max-age=0"</span><span class="p">,</span> + <span class="p">}</span> + + <span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s2">"https://www.bing.com/account/general"</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="n">headers</span><span class="p">)</span> + <span class="k">if</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">ok</span><span class="p">:</span> <span class="c1"># type: ignore</span> + <span class="nb">print</span><span class="p">(</span><span class="s2">"ERROR: response from bing is not OK."</span><span class="p">)</span> + + <span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span> <span class="c1"># type: ignore</span> + + <span class="c1"># languages</span> + + <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="s1">'zh'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'zh-hans'</span> + + <span class="n">map_lang</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'prs'</span><span class="p">:</span> <span class="s1">'fa-AF'</span><span class="p">,</span> <span class="s1">'en'</span><span class="p">:</span> <span class="s1">'en-us'</span><span class="p">}</span> + <span class="n">bing_ui_lang_map</span> <span class="o">=</span> <span class="p">{</span> + <span class="c1"># HINT: this list probably needs to be supplemented</span> + <span class="s1">'en'</span><span class="p">:</span> <span class="s1">'us'</span><span class="p">,</span> <span class="c1"># en --> en-us</span> + <span class="s1">'da'</span><span class="p">:</span> <span class="s1">'dk'</span><span class="p">,</span> <span class="c1"># da --> da-dk</span> + <span class="p">}</span> + + <span class="k">for</span> <span class="n">href</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="s1">'//div[@id="language-section"]//li/a/@href'</span><span class="p">):</span> + <span class="n">eng_lang</span> <span class="o">=</span> <span class="n">parse_qs</span><span class="p">(</span><span class="n">urlparse</span><span class="p">(</span><span class="n">href</span><span class="p">)</span><span class="o">.</span><span class="n">query</span><span class="p">)[</span><span class="s1">'setlang'</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> + <span class="n">babel_lang</span> <span class="o">=</span> <span class="n">map_lang</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">eng_lang</span><span class="p">,</span> <span class="n">eng_lang</span><span class="p">)</span> + <span class="k">try</span><span class="p">:</span> + <span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">language_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">babel_lang</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'-'</span><span class="p">,</span> <span class="s1">'_'</span><span class="p">)))</span> + <span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span> + <span class="nb">print</span><span class="p">(</span><span class="s2">"ERROR: language (</span><span class="si">%s</span><span class="s2">) is unknown by babel"</span> <span class="o">%</span> <span class="p">(</span><span class="n">babel_lang</span><span class="p">))</span> + <span class="k">continue</span> + <span class="c1"># Language (e.g. 'en' or 'de') from https://www.bing.com/account/general</span> + <span class="c1"># is converted by bing to 'en-us' or 'de-de'. But only if there is not</span> + <span class="c1"># already a '-' delemitter in the language. For instance 'pt-PT' --></span> + <span class="c1"># 'pt-pt' and 'pt-br' --> 'pt-br'</span> + <span class="n">bing_ui_lang</span> <span class="o">=</span> <span class="n">eng_lang</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> + <span class="k">if</span> <span class="s1">'-'</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">bing_ui_lang</span><span class="p">:</span> + <span class="n">bing_ui_lang</span> <span class="o">=</span> <span class="n">bing_ui_lang</span> <span class="o">+</span> <span class="s1">'-'</span> <span class="o">+</span> <span class="n">bing_ui_lang_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">bing_ui_lang</span><span class="p">,</span> <span class="n">bing_ui_lang</span><span class="p">)</span> + + <span class="n">conflict</span> <span class="o">=</span> <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_tag</span><span class="p">)</span> + <span class="k">if</span> <span class="n">conflict</span><span class="p">:</span> + <span class="k">if</span> <span class="n">conflict</span> <span class="o">!=</span> <span class="n">bing_ui_lang</span><span class="p">:</span> + <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"CONFLICT: babel </span><span class="si">{</span><span class="n">sxng_tag</span><span class="si">}</span><span class="s2"> --> </span><span class="si">{</span><span class="n">conflict</span><span class="si">}</span><span class="s2">, </span><span class="si">{</span><span class="n">bing_ui_lang</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> + <span class="k">continue</span> + <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">bing_ui_lang</span> + + <span class="c1"># regions (aka "market codes")</span> + + <span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="p">[</span><span class="s1">'zh-CN'</span><span class="p">]</span> <span class="o">=</span> <span class="s1">'zh-cn'</span> + + <span class="n">map_market_codes</span> <span class="o">=</span> <span class="p">{</span> + <span class="s1">'zh-hk'</span><span class="p">:</span> <span class="s1">'en-hk'</span><span class="p">,</span> <span class="c1"># not sure why, but at M$ this is the market code for Hongkong</span> + <span class="p">}</span> + <span class="k">for</span> <span class="n">href</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="s1">'//div[@id="region-section"]//li/a/@href'</span><span class="p">):</span> + <span class="n">cc_tag</span> <span class="o">=</span> <span class="n">parse_qs</span><span class="p">(</span><span class="n">urlparse</span><span class="p">(</span><span class="n">href</span><span class="p">)</span><span class="o">.</span><span class="n">query</span><span class="p">)[</span><span class="s1">'cc'</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span> + <span class="k">if</span> <span class="n">cc_tag</span> <span class="o">==</span> <span class="s1">'clear'</span><span class="p">:</span> + <span class="n">engine_traits</span><span class="o">.</span><span class="n">all_locale</span> <span class="o">=</span> <span class="n">cc_tag</span> + <span class="k">continue</span> + + <span class="c1"># add market codes from official languages of the country ..</span> + <span class="k">for</span> <span class="n">lang_tag</span> <span class="ow">in</span> <span class="n">babel</span><span class="o">.</span><span class="n">languages</span><span class="o">.</span><span class="n">get_official_languages</span><span class="p">(</span><span class="n">cc_tag</span><span class="p">,</span> <span class="n">de_facto</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> + <span class="k">if</span> <span class="n">lang_tag</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span> + <span class="c1"># print("ignore lang: %s <-- %s" % (cc_tag, lang_tag))</span> + <span class="k">continue</span> + <span class="n">lang_tag</span> <span class="o">=</span> <span class="n">lang_tag</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'_'</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="c1"># zh_Hant --> zh</span> + <span class="n">market_code</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">lang_tag</span><span class="si">}</span><span class="s2">-</span><span class="si">{</span><span class="n">cc_tag</span><span class="si">}</span><span class="s2">"</span> <span class="c1"># zh-tw</span> + + <span class="n">market_code</span> <span class="o">=</span> <span class="n">map_market_codes</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">market_code</span><span class="p">,</span> <span class="n">market_code</span><span class="p">)</span> + <span class="n">sxng_tag</span> <span class="o">=</span> <span class="n">region_tag</span><span class="p">(</span><span class="n">babel</span><span class="o">.</span><span class="n">Locale</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="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">lang_tag</span><span class="p">,</span> <span class="n">cc_tag</span><span class="o">.</span><span class="n">upper</span><span class="p">())))</span> + <span class="n">conflict</span> <span class="o">=</span> <span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_tag</span><span class="p">)</span> + <span class="k">if</span> <span class="n">conflict</span><span class="p">:</span> + <span class="k">if</span> <span class="n">conflict</span> <span class="o">!=</span> <span class="n">market_code</span><span class="p">:</span> + <span class="nb">print</span><span class="p">(</span><span class="s2">"CONFLICT: babel </span><span class="si">%s</span><span class="s2"> --> </span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span><span class="n">sxng_tag</span><span class="p">,</span> <span class="n">conflict</span><span class="p">,</span> <span class="n">market_code</span><span class="p">))</span> + <span class="k">continue</span> + <span class="n">engine_traits</span><span class="o">.</span><span class="n">regions</span><span class="p">[</span><span class="n">sxng_tag</span><span class="p">]</span> <span class="o">=</span> <span class="n">market_code</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>
\ No newline at end of file |