bing.html 44 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391
  1. <!DOCTYPE html>
  2. <html lang="en" data-content_root="../../../">
  3. <head>
  4. <meta charset="utf-8" />
  5. <meta name="viewport" content="width=device-width, initial-scale=1.0" />
  6. <meta name="viewport" content="width=device-width, initial-scale=1">
  7. <title>searx.engines.bing &#8212; SearXNG Documentation (2025.4.30+fd33559cf)</title>
  8. <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
  9. <link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
  10. <script src="../../../_static/documentation_options.js?v=b12b0e12"></script>
  11. <script src="../../../_static/doctools.js?v=9a2dae69"></script>
  12. <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
  13. <script data-project="searxng" data-version="2025.4.30+fd33559cf" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
  14. <link rel="index" title="Index" href="../../../genindex.html" />
  15. <link rel="search" title="Search" href="../../../search.html" />
  16. </head><body>
  17. <div class="related" role="navigation" aria-label="Related">
  18. <h3>Navigation</h3>
  19. <ul>
  20. <li class="right" style="margin-right: 10px">
  21. <a href="../../../genindex.html" title="General Index"
  22. accesskey="I">index</a></li>
  23. <li class="right" >
  24. <a href="../../../py-modindex.html" title="Python Module Index"
  25. >modules</a> |</li>
  26. <li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2025.4.30+fd33559cf)</a> &#187;</li>
  27. <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li>
  28. <li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> &#187;</li>
  29. <li class="nav-item nav-item-this"><a href="">searx.engines.bing</a></li>
  30. </ul>
  31. </div>
  32. <div class="document">
  33. <div class="documentwrapper">
  34. <div class="bodywrapper">
  35. <div class="body" role="main">
  36. <h1>Source code for searx.engines.bing</h1><div class="highlight"><pre>
  37. <span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
  38. <span class="sd">&quot;&quot;&quot;This is the implementation of the Bing-WEB engine. Some of this</span>
  39. <span class="sd">implementations are shared by other engines:</span>
  40. <span class="sd">- :ref:`bing images engine`</span>
  41. <span class="sd">- :ref:`bing news engine`</span>
  42. <span class="sd">- :ref:`bing videos engine`</span>
  43. <span class="sd">On the `preference page`_ Bing offers a lot of languages an regions (see section</span>
  44. <span class="sd">LANGUAGE and COUNTRY/REGION). The Language is the language of the UI, we need</span>
  45. <span class="sd">in SearXNG to get the translations of data such as *&quot;published last week&quot;*.</span>
  46. <span class="sd">There is a description of the official search-APIs_, unfortunately this is not</span>
  47. <span class="sd">the API we can use or that bing itself would use. You can look up some things</span>
  48. <span class="sd">in the API to get a better picture of bing, but the value specifications like</span>
  49. <span class="sd">the market codes are usually outdated or at least no longer used by bing itself.</span>
  50. <span class="sd">The market codes have been harmonized and are identical for web, video and</span>
  51. <span class="sd">images. The news area has also been harmonized with the other categories. Only</span>
  52. <span class="sd">political adjustments still seem to be made -- for example, there is no news</span>
  53. <span class="sd">category for the Chinese market.</span>
  54. <span class="sd">.. _preference page: https://www.bing.com/account/general</span>
  55. <span class="sd">.. _search-APIs: https://learn.microsoft.com/en-us/bing/search-apis/</span>
  56. <span class="sd">&quot;&quot;&quot;</span>
  57. <span class="c1"># pylint: disable=too-many-branches, invalid-name</span>
  58. <span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">TYPE_CHECKING</span>
  59. <span class="kn">import</span><span class="w"> </span><span class="nn">base64</span>
  60. <span class="kn">import</span><span class="w"> </span><span class="nn">re</span>
  61. <span class="kn">import</span><span class="w"> </span><span class="nn">time</span>
  62. <span class="kn">from</span><span class="w"> </span><span class="nn">urllib.parse</span><span class="w"> </span><span class="kn">import</span> <span class="n">parse_qs</span><span class="p">,</span> <span class="n">urlencode</span><span class="p">,</span> <span class="n">urlparse</span>
  63. <span class="kn">from</span><span class="w"> </span><span class="nn">lxml</span><span class="w"> </span><span class="kn">import</span> <span class="n">html</span>
  64. <span class="kn">import</span><span class="w"> </span><span class="nn">babel</span>
  65. <span class="kn">import</span><span class="w"> </span><span class="nn">babel.languages</span>
  66. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.utils</span><span class="w"> </span><span class="kn">import</span> <span class="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>
  67. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.locales</span><span class="w"> </span><span class="kn">import</span> <span class="n">language_tag</span><span class="p">,</span> <span class="n">region_tag</span>
  68. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.enginelib.traits</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineTraits</span>
  69. <span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
  70. <span class="kn">import</span><span class="w"> </span><span class="nn">logging</span>
  71. <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>
  72. <span class="n">traits</span><span class="p">:</span> <span class="n">EngineTraits</span>
  73. <span class="n">about</span> <span class="o">=</span> <span class="p">{</span>
  74. <span class="s2">&quot;website&quot;</span><span class="p">:</span> <span class="s1">&#39;https://www.bing.com&#39;</span><span class="p">,</span>
  75. <span class="s2">&quot;wikidata_id&quot;</span><span class="p">:</span> <span class="s1">&#39;Q182496&#39;</span><span class="p">,</span>
  76. <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-web-search-api&#39;</span><span class="p">,</span>
  77. <span class="s2">&quot;use_official_api&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  78. <span class="s2">&quot;require_api_key&quot;</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
  79. <span class="s2">&quot;results&quot;</span><span class="p">:</span> <span class="s1">&#39;HTML&#39;</span><span class="p">,</span>
  80. <span class="p">}</span>
  81. <span class="c1"># engine dependent config</span>
  82. <span class="n">categories</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;general&#39;</span><span class="p">,</span> <span class="s1">&#39;web&#39;</span><span class="p">]</span>
  83. <span class="n">paging</span> <span class="o">=</span> <span class="kc">True</span>
  84. <span class="n">max_page</span> <span class="o">=</span> <span class="mi">200</span>
  85. <span class="sd">&quot;&quot;&quot;200 pages maximum (``&amp;first=1991``)&quot;&quot;&quot;</span>
  86. <span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">True</span>
  87. <span class="n">safesearch</span> <span class="o">=</span> <span class="kc">True</span>
  88. <span class="sd">&quot;&quot;&quot;Bing results are always SFW. To get NSFW links from bing some age</span>
  89. <span class="sd">verification by a cookie is needed / thats not possible in SearXNG.</span>
  90. <span class="sd">&quot;&quot;&quot;</span>
  91. <span class="n">base_url</span> <span class="o">=</span> <span class="s1">&#39;https://www.bing.com/search&#39;</span>
  92. <span class="sd">&quot;&quot;&quot;Bing (Web) search URL&quot;&quot;&quot;</span>
  93. <span class="k">def</span><span class="w"> </span><span class="nf">_page_offset</span><span class="p">(</span><span class="n">pageno</span><span class="p">):</span>
  94. <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>
  95. <span class="k">def</span><span class="w"> </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>
  96. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">][</span><span class="s1">&#39;_EDGE_CD&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">&#39;m=</span><span class="si">{</span><span class="n">engine_region</span><span class="si">}</span><span class="s1">&amp;u=</span><span class="si">{</span><span class="n">engine_language</span><span class="si">}</span><span class="s1">&#39;</span>
  97. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">][</span><span class="s1">&#39;_EDGE_S&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="sa">f</span><span class="s1">&#39;mkt=</span><span class="si">{</span><span class="n">engine_region</span><span class="si">}</span><span class="s1">&amp;ui=</span><span class="si">{</span><span class="n">engine_language</span><span class="si">}</span><span class="s1">&#39;</span>
  98. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;bing cookies: </span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">])</span>
  99. <div class="viewcode-block" id="request">
  100. <a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.request">[docs]</a>
  101. <span class="k">def</span><span class="w"> </span><span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
  102. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Assemble a Bing-Web request.&quot;&quot;&quot;</span>
  103. <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>
  104. <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>
  105. <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>
  106. <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">&#39;pageno&#39;</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span>
  107. <span class="n">query_params</span> <span class="o">=</span> <span class="p">{</span>
  108. <span class="s1">&#39;q&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
  109. <span class="c1"># if arg &#39;pq&#39; is missed, sometimes on page 4 we get results from page 1,</span>
  110. <span class="c1"># don&#39;t ask why it is only sometimes / its M$ and they have never been</span>
  111. <span class="c1"># deterministic ;)</span>
  112. <span class="s1">&#39;pq&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">,</span>
  113. <span class="p">}</span>
  114. <span class="c1"># To get correct page, arg first and this arg FORM is needed, the value PERE</span>
  115. <span class="c1"># is on page 2, on page 3 its PERE1 and on page 4 its PERE2 .. and so forth.</span>
  116. <span class="c1"># The &#39;first&#39; arg should never send on page 1.</span>
  117. <span class="k">if</span> <span class="n">page</span> <span class="o">&gt;</span> <span class="mi">1</span><span class="p">:</span>
  118. <span class="n">query_params</span><span class="p">[</span><span class="s1">&#39;first&#39;</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>
  119. <span class="k">if</span> <span class="n">page</span> <span class="o">==</span> <span class="mi">2</span><span class="p">:</span>
  120. <span class="n">query_params</span><span class="p">[</span><span class="s1">&#39;FORM&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;PERE&#39;</span>
  121. <span class="k">elif</span> <span class="n">page</span> <span class="o">&gt;</span> <span class="mi">2</span><span class="p">:</span>
  122. <span class="n">query_params</span><span class="p">[</span><span class="s1">&#39;FORM&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;PERE</span><span class="si">%s</span><span class="s1">&#39;</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>
  123. <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="sa">f</span><span class="s1">&#39;</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">&#39;</span>
  124. <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">&#39;time_range&#39;</span><span class="p">):</span>
  125. <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>
  126. <span class="n">time_ranges</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;day&#39;</span><span class="p">:</span> <span class="s1">&#39;1&#39;</span><span class="p">,</span> <span class="s1">&#39;week&#39;</span><span class="p">:</span> <span class="s1">&#39;2&#39;</span><span class="p">,</span> <span class="s1">&#39;month&#39;</span><span class="p">:</span> <span class="s1">&#39;3&#39;</span><span class="p">,</span> <span class="s1">&#39;year&#39;</span><span class="p">:</span> <span class="sa">f</span><span class="s1">&#39;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">&#39;</span><span class="p">}</span>
  127. <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="sa">f</span><span class="s1">&#39;&amp;filters=ex1:&quot;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">&quot;time_range&quot;</span><span class="p">]]</span><span class="si">}</span><span class="s1">&quot;&#39;</span>
  128. <span class="k">return</span> <span class="n">params</span></div>
  129. <span class="k">def</span><span class="w"> </span><span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">):</span>
  130. <span class="c1"># pylint: disable=too-many-locals</span>
  131. <span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
  132. <span class="n">result_len</span> <span class="o">=</span> <span class="mi">0</span>
  133. <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>
  134. <span class="c1"># parse results again if nothing is found yet</span>
  135. <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">&#39;//ol[@id=&quot;b_results&quot;]/li[contains(@class, &quot;b_algo&quot;)]&#39;</span><span class="p">):</span>
  136. <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">&#39;.//h2/a&#39;</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
  137. <span class="k">if</span> <span class="n">link</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  138. <span class="k">continue</span>
  139. <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>
  140. <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>
  141. <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">&#39;.//p&#39;</span><span class="p">)</span>
  142. <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">content</span><span class="p">:</span>
  143. <span class="c1"># Make sure that the element is free of:</span>
  144. <span class="c1"># &lt;span class=&quot;algoSlug_icon&quot; # data-priority=&quot;2&quot;&gt;Web&lt;/span&gt;</span>
  145. <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">&#39;.//span[@class=&quot;algoSlug_icon&quot;]&#39;</span><span class="p">):</span>
  146. <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>
  147. <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>
  148. <span class="c1"># get the real URL</span>
  149. <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">&#39;https://www.bing.com/ck/a?&#39;</span><span class="p">):</span>
  150. <span class="c1"># get the first value of u parameter</span>
  151. <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>
  152. <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>
  153. <span class="n">param_u</span> <span class="o">=</span> <span class="n">parsed_url_query</span><span class="p">[</span><span class="s2">&quot;u&quot;</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
  154. <span class="c1"># remove &quot;a1&quot; in front</span>
  155. <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>
  156. <span class="c1"># add padding</span>
  157. <span class="n">encoded_url</span> <span class="o">=</span> <span class="n">encoded_url</span> <span class="o">+</span> <span class="s1">&#39;=&#39;</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>
  158. <span class="c1"># decode base64 encoded URL</span>
  159. <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>
  160. <span class="c1"># append result</span>
  161. <span class="n">results</span><span class="o">.</span><span class="n">append</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>
  162. <span class="c1"># get number_of_results</span>
  163. <span class="k">try</span><span class="p">:</span>
  164. <span class="n">result_len_container</span> <span class="o">=</span> <span class="s2">&quot;&quot;</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">&#39;//span[@class=&quot;sb_count&quot;]//text()&#39;</span><span class="p">))</span>
  165. <span class="k">if</span> <span class="s2">&quot;-&quot;</span> <span class="ow">in</span> <span class="n">result_len_container</span><span class="p">:</span>
  166. <span class="c1"># Remove the part &quot;from-to&quot; for paginated request ...</span>
  167. <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">&quot;-&quot;</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>
  168. <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">&#39;[^0-9]&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="n">result_len_container</span><span class="p">)</span>
  169. <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">&gt;</span> <span class="mi">0</span><span class="p">:</span>
  170. <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>
  171. <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>
  172. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s1">&#39;result error :</span><span class="se">\n</span><span class="si">%s</span><span class="s1">&#39;</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
  173. <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">&quot;pageno&quot;</span><span class="p">,</span> <span class="mi">0</span><span class="p">))</span> <span class="o">&gt;</span> <span class="n">result_len</span><span class="p">:</span>
  174. <span class="c1"># Avoid reading more results than available.</span>
  175. <span class="c1"># For example, if there is 100 results from some search and we try to get results from 120 to 130,</span>
  176. <span class="c1"># Bing will send back the results from 0 to 10 and no error.</span>
  177. <span class="c1"># If we compare results count with the first parameter of the request we can avoid this &quot;invalid&quot; results.</span>
  178. <span class="k">return</span> <span class="p">[]</span>
  179. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">&#39;number_of_results&#39;</span><span class="p">:</span> <span class="n">result_len</span><span class="p">})</span>
  180. <span class="k">return</span> <span class="n">results</span>
  181. <div class="viewcode-block" id="fetch_traits">
  182. <a class="viewcode-back" href="../../../dev/engines/online/bing.html#searx.engines.bing.fetch_traits">[docs]</a>
  183. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_traits</span><span class="p">(</span><span class="n">engine_traits</span><span class="p">:</span> <span class="n">EngineTraits</span><span class="p">):</span>
  184. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Fetch languages and regions from Bing-Web.&quot;&quot;&quot;</span>
  185. <span class="c1"># pylint: disable=import-outside-toplevel</span>
  186. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.network</span><span class="w"> </span><span class="kn">import</span> <span class="n">get</span> <span class="c1"># see https://github.com/searxng/searxng/issues/762</span>
  187. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">gen_useragent</span>
  188. <span class="n">headers</span> <span class="o">=</span> <span class="p">{</span>
  189. <span class="s2">&quot;User-Agent&quot;</span><span class="p">:</span> <span class="n">gen_useragent</span><span class="p">(),</span>
  190. <span class="s2">&quot;Accept&quot;</span><span class="p">:</span> <span class="s2">&quot;text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8&quot;</span><span class="p">,</span>
  191. <span class="s2">&quot;Accept-Language&quot;</span><span class="p">:</span> <span class="s2">&quot;en-US;q=0.5,en;q=0.3&quot;</span><span class="p">,</span>
  192. <span class="s2">&quot;Accept-Encoding&quot;</span><span class="p">:</span> <span class="s2">&quot;gzip, deflate, br&quot;</span><span class="p">,</span>
  193. <span class="s2">&quot;DNT&quot;</span><span class="p">:</span> <span class="s2">&quot;1&quot;</span><span class="p">,</span>
  194. <span class="s2">&quot;Connection&quot;</span><span class="p">:</span> <span class="s2">&quot;keep-alive&quot;</span><span class="p">,</span>
  195. <span class="s2">&quot;Upgrade-Insecure-Requests&quot;</span><span class="p">:</span> <span class="s2">&quot;1&quot;</span><span class="p">,</span>
  196. <span class="s2">&quot;Sec-GPC&quot;</span><span class="p">:</span> <span class="s2">&quot;1&quot;</span><span class="p">,</span>
  197. <span class="s2">&quot;Cache-Control&quot;</span><span class="p">:</span> <span class="s2">&quot;max-age=0&quot;</span><span class="p">,</span>
  198. <span class="p">}</span>
  199. <span class="n">resp</span> <span class="o">=</span> <span class="n">get</span><span class="p">(</span><span class="s2">&quot;https://www.bing.com/account/general&quot;</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="n">headers</span><span class="p">)</span>
  200. <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>
  201. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: response from bing is not OK.&quot;</span><span class="p">)</span>
  202. <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>
  203. <span class="c1"># languages</span>
  204. <span class="n">engine_traits</span><span class="o">.</span><span class="n">languages</span><span class="p">[</span><span class="s1">&#39;zh&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;zh-hans&#39;</span>
  205. <span class="n">map_lang</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;prs&#39;</span><span class="p">:</span> <span class="s1">&#39;fa-AF&#39;</span><span class="p">,</span> <span class="s1">&#39;en&#39;</span><span class="p">:</span> <span class="s1">&#39;en-us&#39;</span><span class="p">}</span>
  206. <span class="n">bing_ui_lang_map</span> <span class="o">=</span> <span class="p">{</span>
  207. <span class="c1"># HINT: this list probably needs to be supplemented</span>
  208. <span class="s1">&#39;en&#39;</span><span class="p">:</span> <span class="s1">&#39;us&#39;</span><span class="p">,</span> <span class="c1"># en --&gt; en-us</span>
  209. <span class="s1">&#39;da&#39;</span><span class="p">:</span> <span class="s1">&#39;dk&#39;</span><span class="p">,</span> <span class="c1"># da --&gt; da-dk</span>
  210. <span class="p">}</span>
  211. <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">&#39;//div[@id=&quot;language-section-content&quot;]//div[@class=&quot;languageItem&quot;]/a/@href&#39;</span><span class="p">):</span>
  212. <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">&#39;setlang&#39;</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
  213. <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>
  214. <span class="k">try</span><span class="p">:</span>
  215. <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">&#39;-&#39;</span><span class="p">,</span> <span class="s1">&#39;_&#39;</span><span class="p">)))</span>
  216. <span class="k">except</span> <span class="n">babel</span><span class="o">.</span><span class="n">UnknownLocaleError</span><span class="p">:</span>
  217. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;ERROR: language (</span><span class="si">%s</span><span class="s2">) is unknown by babel&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">babel_lang</span><span class="p">))</span>
  218. <span class="k">continue</span>
  219. <span class="c1"># Language (e.g. &#39;en&#39; or &#39;de&#39;) from https://www.bing.com/account/general</span>
  220. <span class="c1"># is converted by bing to &#39;en-us&#39; or &#39;de-de&#39;. But only if there is not</span>
  221. <span class="c1"># already a &#39;-&#39; delemitter in the language. For instance &#39;pt-PT&#39; --&gt;</span>
  222. <span class="c1"># &#39;pt-pt&#39; and &#39;pt-br&#39; --&gt; &#39;pt-br&#39;</span>
  223. <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>
  224. <span class="k">if</span> <span class="s1">&#39;-&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">bing_ui_lang</span><span class="p">:</span>
  225. <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">&#39;-&#39;</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>
  226. <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>
  227. <span class="k">if</span> <span class="n">conflict</span><span class="p">:</span>
  228. <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>
  229. <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;CONFLICT: babel </span><span class="si">{</span><span class="n">sxng_tag</span><span class="si">}</span><span class="s2"> --&gt; </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">&quot;</span><span class="p">)</span>
  230. <span class="k">continue</span>
  231. <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>
  232. <span class="c1"># regions (aka &quot;market codes&quot;)</span>
  233. <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;zh-cn&#39;</span>
  234. <span class="n">map_market_codes</span> <span class="o">=</span> <span class="p">{</span>
  235. <span class="s1">&#39;zh-hk&#39;</span><span class="p">:</span> <span class="s1">&#39;en-hk&#39;</span><span class="p">,</span> <span class="c1"># not sure why, but at M$ this is the market code for Hongkong</span>
  236. <span class="p">}</span>
  237. <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">&#39;//div[@id=&quot;region-section-content&quot;]//div[@class=&quot;regionItem&quot;]/a/@href&#39;</span><span class="p">):</span>
  238. <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">&#39;cc&#39;</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span>
  239. <span class="k">if</span> <span class="n">cc_tag</span> <span class="o">==</span> <span class="s1">&#39;clear&#39;</span><span class="p">:</span>
  240. <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>
  241. <span class="k">continue</span>
  242. <span class="c1"># add market codes from official languages of the country ..</span>
  243. <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>
  244. <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>
  245. <span class="c1"># print(&quot;ignore lang: %s &lt;-- %s&quot; % (cc_tag, lang_tag))</span>
  246. <span class="k">continue</span>
  247. <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">&#39;_&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="c1"># zh_Hant --&gt; zh</span>
  248. <span class="n">market_code</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;</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">&quot;</span> <span class="c1"># zh-tw</span>
  249. <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>
  250. <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">&#39;</span><span class="si">%s</span><span class="s1">_</span><span class="si">%s</span><span class="s1">&#39;</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>
  251. <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>
  252. <span class="k">if</span> <span class="n">conflict</span><span class="p">:</span>
  253. <span class="k">if</span> <span class="n">conflict</span> <span class="o">!=</span> <span class="n">market_code</span><span class="p">:</span>
  254. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot;CONFLICT: babel </span><span class="si">%s</span><span class="s2"> --&gt; </span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2">&quot;</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>
  255. <span class="k">continue</span>
  256. <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>
  257. </pre></div>
  258. <div class="clearer"></div>
  259. </div>
  260. </div>
  261. </div>
  262. <span id="sidebar-top"></span>
  263. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  264. <div class="sphinxsidebarwrapper">
  265. <p class="logo"><a href="../../../index.html">
  266. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  267. </a></p>
  268. <h3><a href="../../../index.html">Table of Contents</a></h3>
  269. <ul>
  270. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  271. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  272. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  273. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  274. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  275. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  276. </ul>
  277. <h3>Project Links</h3>
  278. <ul>
  279. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  280. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  281. <li><a href="https://searx.space">Public instances</a>
  282. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  283. </ul><h3>Navigation</h3>
  284. <ul>
  285. <li><a href="../../../index.html">Overview</a>
  286. <ul>
  287. <li><a href="../../index.html">Module code</a>
  288. <ul>
  289. <li><a href="../engines.html">searx.engines</a>
  290. </ul>
  291. </li></ul>
  292. </li>
  293. </ul>
  294. </li>
  295. </ul>
  296. <search id="searchbox" style="display: none" role="search">
  297. <h3 id="searchlabel">Quick search</h3>
  298. <div class="searchformwrapper">
  299. <form class="search" action="../../../search.html" method="get">
  300. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  301. <input type="submit" value="Go" />
  302. </form>
  303. </div>
  304. </search>
  305. <script>document.getElementById('searchbox').style.display = "block"</script>
  306. </div>
  307. </div>
  308. <div class="clearer"></div>
  309. </div>
  310. <div class="footer" role="contentinfo">
  311. &#169; Copyright SearXNG team.
  312. </div>
  313. </body>
  314. </html>