update_engine_descriptions.html 58 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478
  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>searxng_extra.update.update_engine_descriptions &#8212; SearXNG Documentation (2025.5.1+1a1628149)</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=cc9fc81d"></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="2025.5.1+1a1628149" 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 (2025.5.1+1a1628149)</a> &#187;</li>
  27. <li class="nav-item nav-item-1"><a href="../../index.html" accesskey="U">Module code</a> &#187;</li>
  28. <li class="nav-item nav-item-this"><a href="">searxng_extra.update.update_engine_descriptions</a></li>
  29. </ul>
  30. </div>
  31. <div class="document">
  32. <div class="documentwrapper">
  33. <div class="bodywrapper">
  34. <div class="body" role="main">
  35. <h1>Source code for searxng_extra.update.update_engine_descriptions</h1><div class="highlight"><pre>
  36. <span></span><span class="ch">#!/usr/bin/env python</span>
  37. <span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
  38. <span class="sd">&quot;&quot;&quot;Fetch website description from websites and from</span>
  39. <span class="sd">:origin:`searx/engines/wikidata.py` engine.</span>
  40. <span class="sd">Output file: :origin:`searx/data/engine_descriptions.json`.</span>
  41. <span class="sd">&quot;&quot;&quot;</span>
  42. <span class="c1"># pylint: disable=invalid-name, global-statement</span>
  43. <span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
  44. <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">urlparse</span>
  45. <span class="kn">from</span><span class="w"> </span><span class="nn">os.path</span><span class="w"> </span><span class="kn">import</span> <span class="n">join</span>
  46. <span class="kn">from</span><span class="w"> </span><span class="nn">lxml.html</span><span class="w"> </span><span class="kn">import</span> <span class="n">fromstring</span>
  47. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.engines</span><span class="w"> </span><span class="kn">import</span> <span class="n">wikidata</span><span class="p">,</span> <span class="n">set_loggers</span>
  48. <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">extract_text</span><span class="p">,</span> <span class="n">searx_useragent</span>
  49. <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">LOCALE_NAMES</span><span class="p">,</span> <span class="n">locales_initialize</span><span class="p">,</span> <span class="n">match_locale</span>
  50. <span class="kn">from</span><span class="w"> </span><span class="nn">searx</span><span class="w"> </span><span class="kn">import</span> <span class="n">searx_dir</span>
  51. <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><span class="p">,</span> <span class="n">detect_language</span>
  52. <span class="kn">import</span><span class="w"> </span><span class="nn">searx.search</span>
  53. <span class="kn">import</span><span class="w"> </span><span class="nn">searx.network</span>
  54. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.data</span><span class="w"> </span><span class="kn">import</span> <span class="n">data_dir</span>
  55. <span class="n">DATA_FILE</span> <span class="o">=</span> <span class="n">data_dir</span> <span class="o">/</span> <span class="s1">&#39;engine_descriptions.json&#39;</span>
  56. <span class="n">set_loggers</span><span class="p">(</span><span class="n">wikidata</span><span class="p">,</span> <span class="s1">&#39;wikidata&#39;</span><span class="p">)</span>
  57. <span class="n">locales_initialize</span><span class="p">()</span>
  58. <span class="c1"># you can run the query in https://query.wikidata.org</span>
  59. <span class="c1"># replace %IDS% by Wikidata entities separated by spaces with the prefix wd:</span>
  60. <span class="c1"># for example wd:Q182496 wd:Q1540899</span>
  61. <span class="c1"># replace %LANGUAGES_SPARQL% by languages</span>
  62. <span class="n">SPARQL_WIKIPEDIA_ARTICLE</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;</span>
  63. <span class="s2">SELECT DISTINCT ?item ?name ?article ?lang</span>
  64. <span class="s2">WHERE {</span>
  65. <span class="s2"> hint:Query hint:optimizer &quot;None&quot;.</span>
  66. <span class="s2"> VALUES ?item { %IDS% }</span>
  67. <span class="s2"> ?article schema:about ?item ;</span>
  68. <span class="s2"> schema:inLanguage ?lang ;</span>
  69. <span class="s2"> schema:name ?name ;</span>
  70. <span class="s2"> schema:isPartOf [ wikibase:wikiGroup &quot;wikipedia&quot; ] .</span>
  71. <span class="s2"> FILTER(?lang in (%LANGUAGES_SPARQL%)) .</span>
  72. <span class="s2"> FILTER (!CONTAINS(?name, &#39;:&#39;)) .</span>
  73. <span class="s2">}</span>
  74. <span class="s2">ORDER BY ?item ?lang</span>
  75. <span class="s2">&quot;&quot;&quot;</span>
  76. <span class="n">SPARQL_DESCRIPTION</span> <span class="o">=</span> <span class="s2">&quot;&quot;&quot;</span>
  77. <span class="s2">SELECT DISTINCT ?item ?itemDescription</span>
  78. <span class="s2">WHERE {</span>
  79. <span class="s2"> VALUES ?item { %IDS% }</span>
  80. <span class="s2"> ?item schema:description ?itemDescription .</span>
  81. <span class="s2"> FILTER (lang(?itemDescription) in (%LANGUAGES_SPARQL%))</span>
  82. <span class="s2">}</span>
  83. <span class="s2">ORDER BY ?itemLang</span>
  84. <span class="s2">&quot;&quot;&quot;</span>
  85. <span class="n">NOT_A_DESCRIPTION</span> <span class="o">=</span> <span class="p">[</span>
  86. <span class="s1">&#39;web site&#39;</span><span class="p">,</span>
  87. <span class="s1">&#39;site web&#39;</span><span class="p">,</span>
  88. <span class="s1">&#39;komputa serĉilo&#39;</span><span class="p">,</span>
  89. <span class="s1">&#39;interreta serĉilo&#39;</span><span class="p">,</span>
  90. <span class="s1">&#39;bilaketa motor&#39;</span><span class="p">,</span>
  91. <span class="s1">&#39;web search engine&#39;</span><span class="p">,</span>
  92. <span class="s1">&#39;wikimedia täpsustuslehekülg&#39;</span><span class="p">,</span>
  93. <span class="p">]</span>
  94. <span class="n">SKIP_ENGINE_SOURCE</span> <span class="o">=</span> <span class="p">[</span>
  95. <span class="c1"># fmt: off</span>
  96. <span class="p">(</span><span class="s1">&#39;gitlab&#39;</span><span class="p">,</span> <span class="s1">&#39;wikidata&#39;</span><span class="p">)</span>
  97. <span class="c1"># descriptions are about wikipedia disambiguation pages</span>
  98. <span class="c1"># fmt: on</span>
  99. <span class="p">]</span>
  100. <span class="n">WIKIPEDIA_LANGUAGES</span> <span class="o">=</span> <span class="p">{}</span>
  101. <span class="n">LANGUAGES_SPARQL</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  102. <span class="n">IDS</span> <span class="o">=</span> <span class="kc">None</span>
  103. <span class="n">WIKIPEDIA_LANGUAGE_VARIANTS</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;zh_Hant&#39;</span><span class="p">:</span> <span class="s1">&#39;zh-tw&#39;</span><span class="p">}</span>
  104. <span class="n">descriptions</span> <span class="o">=</span> <span class="p">{}</span>
  105. <span class="n">wd_to_engine_name</span> <span class="o">=</span> <span class="p">{}</span>
  106. <span class="k">def</span><span class="w"> </span><span class="nf">normalize_description</span><span class="p">(</span><span class="n">description</span><span class="p">):</span>
  107. <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="p">[</span><span class="nb">chr</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">31</span><span class="p">)]:</span>
  108. <span class="n">description</span> <span class="o">=</span> <span class="n">description</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="s1">&#39; &#39;</span><span class="p">)</span>
  109. <span class="n">description</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">description</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">())</span>
  110. <span class="k">return</span> <span class="n">description</span>
  111. <span class="k">def</span><span class="w"> </span><span class="nf">update_description</span><span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">lang</span><span class="p">,</span> <span class="n">description</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="n">replace</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
  112. <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">description</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
  113. <span class="k">return</span>
  114. <span class="n">description</span> <span class="o">=</span> <span class="n">normalize_description</span><span class="p">(</span><span class="n">description</span><span class="p">)</span>
  115. <span class="k">if</span> <span class="n">description</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="n">engine_name</span><span class="o">.</span><span class="n">lower</span><span class="p">():</span>
  116. <span class="k">return</span>
  117. <span class="k">if</span> <span class="n">description</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="ow">in</span> <span class="n">NOT_A_DESCRIPTION</span><span class="p">:</span>
  118. <span class="k">return</span>
  119. <span class="k">if</span> <span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">source</span><span class="p">)</span> <span class="ow">in</span> <span class="n">SKIP_ENGINE_SOURCE</span><span class="p">:</span>
  120. <span class="k">return</span>
  121. <span class="k">if</span> <span class="s1">&#39; &#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">description</span><span class="p">:</span>
  122. <span class="c1"># skip unique word description (like &quot;website&quot;)</span>
  123. <span class="k">return</span>
  124. <span class="k">if</span> <span class="n">replace</span> <span class="ow">or</span> <span class="n">lang</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">descriptions</span><span class="p">[</span><span class="n">engine_name</span><span class="p">]:</span>
  125. <span class="n">descriptions</span><span class="p">[</span><span class="n">engine_name</span><span class="p">][</span><span class="n">lang</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span><span class="n">description</span><span class="p">,</span> <span class="n">source</span><span class="p">]</span>
  126. <span class="k">def</span><span class="w"> </span><span class="nf">get_wikipedia_summary</span><span class="p">(</span><span class="n">wikipedia_url</span><span class="p">,</span> <span class="n">searxng_locale</span><span class="p">):</span>
  127. <span class="c1"># get the REST API URL from the HTML URL</span>
  128. <span class="c1"># Headers</span>
  129. <span class="n">headers</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;User-Agent&#39;</span><span class="p">:</span> <span class="n">searx_useragent</span><span class="p">()}</span>
  130. <span class="k">if</span> <span class="n">searxng_locale</span> <span class="ow">in</span> <span class="n">WIKIPEDIA_LANGUAGE_VARIANTS</span><span class="p">:</span>
  131. <span class="n">headers</span><span class="p">[</span><span class="s1">&#39;Accept-Language&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">WIKIPEDIA_LANGUAGE_VARIANTS</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">searxng_locale</span><span class="p">)</span>
  132. <span class="c1"># URL path : from HTML URL to REST API URL</span>
  133. <span class="n">parsed_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">wikipedia_url</span><span class="p">)</span>
  134. <span class="c1"># remove the /wiki/ prefix</span>
  135. <span class="n">article_name</span> <span class="o">=</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;/wiki/&#39;</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
  136. <span class="c1"># article_name is already encoded but not the / which is required for the REST API call</span>
  137. <span class="n">encoded_article_name</span> <span class="o">=</span> <span class="n">article_name</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;</span><span class="si">%2F</span><span class="s1">&#39;</span><span class="p">)</span>
  138. <span class="n">path</span> <span class="o">=</span> <span class="s1">&#39;/api/rest_v1/page/summary/&#39;</span> <span class="o">+</span> <span class="n">encoded_article_name</span>
  139. <span class="n">wikipedia_rest_url</span> <span class="o">=</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">_replace</span><span class="p">(</span><span class="n">path</span><span class="o">=</span><span class="n">path</span><span class="p">)</span><span class="o">.</span><span class="n">geturl</span><span class="p">()</span>
  140. <span class="k">try</span><span class="p">:</span>
  141. <span class="n">response</span> <span class="o">=</span> <span class="n">searx</span><span class="o">.</span><span class="n">network</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">wikipedia_rest_url</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="n">timeout</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
  142. <span class="n">response</span><span class="o">.</span><span class="n">raise_for_status</span><span class="p">()</span>
  143. <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>
  144. <span class="nb">print</span><span class="p">(</span><span class="s2">&quot; &quot;</span><span class="p">,</span> <span class="n">wikipedia_url</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span>
  145. <span class="k">return</span> <span class="kc">None</span>
  146. <span class="n">api_result</span> <span class="o">=</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
  147. <span class="k">return</span> <span class="n">api_result</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;extract&#39;</span><span class="p">)</span>
  148. <span class="k">def</span><span class="w"> </span><span class="nf">get_website_description</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">lang1</span><span class="p">,</span> <span class="n">lang2</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
  149. <span class="n">headers</span> <span class="o">=</span> <span class="p">{</span>
  150. <span class="s1">&#39;User-Agent&#39;</span><span class="p">:</span> <span class="n">gen_useragent</span><span class="p">(),</span>
  151. <span class="s1">&#39;Accept&#39;</span><span class="p">:</span> <span class="s1">&#39;text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8&#39;</span><span class="p">,</span>
  152. <span class="s1">&#39;DNT&#39;</span><span class="p">:</span> <span class="s1">&#39;1&#39;</span><span class="p">,</span>
  153. <span class="s1">&#39;Upgrade-Insecure-Requests&#39;</span><span class="p">:</span> <span class="s1">&#39;1&#39;</span><span class="p">,</span>
  154. <span class="s1">&#39;Sec-GPC&#39;</span><span class="p">:</span> <span class="s1">&#39;1&#39;</span><span class="p">,</span>
  155. <span class="s1">&#39;Cache-Control&#39;</span><span class="p">:</span> <span class="s1">&#39;max-age=0&#39;</span><span class="p">,</span>
  156. <span class="p">}</span>
  157. <span class="k">if</span> <span class="n">lang1</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
  158. <span class="n">lang_list</span> <span class="o">=</span> <span class="p">[</span><span class="n">lang1</span><span class="p">]</span>
  159. <span class="k">if</span> <span class="n">lang2</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
  160. <span class="n">lang_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">lang2</span><span class="p">)</span>
  161. <span class="n">headers</span><span class="p">[</span><span class="s1">&#39;Accept-Language&#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="s2">&quot;,&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">lang_list</span><span class="p">)</span><span class="si">}</span><span class="s1">;q=0.8&#39;</span>
  162. <span class="k">try</span><span class="p">:</span>
  163. <span class="n">response</span> <span class="o">=</span> <span class="n">searx</span><span class="o">.</span><span class="n">network</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">url</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="n">timeout</span><span class="o">=</span><span class="mi">10</span><span class="p">)</span>
  164. <span class="n">response</span><span class="o">.</span><span class="n">raise_for_status</span><span class="p">()</span>
  165. <span class="k">except</span> <span class="ne">Exception</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span>
  166. <span class="k">return</span> <span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
  167. <span class="k">try</span><span class="p">:</span>
  168. <span class="n">html</span> <span class="o">=</span> <span class="n">fromstring</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
  169. <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
  170. <span class="n">html</span> <span class="o">=</span> <span class="n">fromstring</span><span class="p">(</span><span class="n">response</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
  171. <span class="n">description</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">html</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">&#39;/html/head/meta[@name=&quot;description&quot;]/@content&#39;</span><span class="p">))</span>
  172. <span class="k">if</span> <span class="ow">not</span> <span class="n">description</span><span class="p">:</span>
  173. <span class="n">description</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">html</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">&#39;/html/head/meta[@property=&quot;og:description&quot;]/@content&#39;</span><span class="p">))</span>
  174. <span class="k">if</span> <span class="ow">not</span> <span class="n">description</span><span class="p">:</span>
  175. <span class="n">description</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">html</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">&#39;/html/head/title&#39;</span><span class="p">))</span>
  176. <span class="n">lang</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">html</span><span class="o">.</span><span class="n">xpath</span><span class="p">(</span><span class="s1">&#39;/html/@lang&#39;</span><span class="p">))</span>
  177. <span class="k">if</span> <span class="n">lang</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">lang1</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
  178. <span class="n">lang</span> <span class="o">=</span> <span class="n">lang1</span>
  179. <span class="n">lang</span> <span class="o">=</span> <span class="n">detect_language</span><span class="p">(</span><span class="n">description</span><span class="p">)</span> <span class="ow">or</span> <span class="n">lang</span> <span class="ow">or</span> <span class="s1">&#39;en&#39;</span>
  180. <span class="n">lang</span> <span class="o">=</span> <span class="n">lang</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;_&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
  181. <span class="n">lang</span> <span class="o">=</span> <span class="n">lang</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;-&#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
  182. <span class="k">return</span> <span class="p">(</span><span class="n">lang</span><span class="p">,</span> <span class="n">description</span><span class="p">)</span>
  183. <span class="k">def</span><span class="w"> </span><span class="nf">initialize</span><span class="p">():</span>
  184. <span class="k">global</span> <span class="n">IDS</span><span class="p">,</span> <span class="n">LANGUAGES_SPARQL</span>
  185. <span class="n">searx</span><span class="o">.</span><span class="n">search</span><span class="o">.</span><span class="n">initialize</span><span class="p">()</span>
  186. <span class="n">wikipedia_engine</span> <span class="o">=</span> <span class="n">searx</span><span class="o">.</span><span class="n">engines</span><span class="o">.</span><span class="n">engines</span><span class="p">[</span><span class="s1">&#39;wikipedia&#39;</span><span class="p">]</span>
  187. <span class="n">locale2lang</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;nl-BE&#39;</span><span class="p">:</span> <span class="s1">&#39;nl&#39;</span><span class="p">}</span>
  188. <span class="k">for</span> <span class="n">sxng_ui_lang</span> <span class="ow">in</span> <span class="n">LOCALE_NAMES</span><span class="p">:</span>
  189. <span class="n">sxng_ui_alias</span> <span class="o">=</span> <span class="n">locale2lang</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">sxng_ui_lang</span><span class="p">,</span> <span class="n">sxng_ui_lang</span><span class="p">)</span>
  190. <span class="n">wiki_lang</span> <span class="o">=</span> <span class="kc">None</span>
  191. <span class="k">if</span> <span class="n">sxng_ui_alias</span> <span class="ow">in</span> <span class="n">wikipedia_engine</span><span class="o">.</span><span class="n">traits</span><span class="o">.</span><span class="n">custom</span><span class="p">[</span><span class="s1">&#39;WIKIPEDIA_LANGUAGES&#39;</span><span class="p">]:</span>
  192. <span class="n">wiki_lang</span> <span class="o">=</span> <span class="n">sxng_ui_alias</span>
  193. <span class="k">if</span> <span class="ow">not</span> <span class="n">wiki_lang</span><span class="p">:</span>
  194. <span class="n">wiki_lang</span> <span class="o">=</span> <span class="n">wikipedia_engine</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">sxng_ui_alias</span><span class="p">)</span>
  195. <span class="k">if</span> <span class="ow">not</span> <span class="n">wiki_lang</span><span class="p">:</span>
  196. <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;WIKIPEDIA_LANGUAGES missing </span><span class="si">{</span><span class="n">sxng_ui_lang</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
  197. <span class="k">continue</span>
  198. <span class="n">WIKIPEDIA_LANGUAGES</span><span class="p">[</span><span class="n">sxng_ui_lang</span><span class="p">]</span> <span class="o">=</span> <span class="n">wiki_lang</span>
  199. <span class="n">LANGUAGES_SPARQL</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="sa">f</span><span class="s2">&quot;&#39;</span><span class="si">{</span><span class="n">l</span><span class="si">}</span><span class="s2">&#39;&quot;</span> <span class="k">for</span> <span class="n">l</span> <span class="ow">in</span> <span class="nb">set</span><span class="p">(</span><span class="n">WIKIPEDIA_LANGUAGES</span><span class="o">.</span><span class="n">values</span><span class="p">()))</span>
  200. <span class="k">for</span> <span class="n">engine_name</span><span class="p">,</span> <span class="n">engine</span> <span class="ow">in</span> <span class="n">searx</span><span class="o">.</span><span class="n">engines</span><span class="o">.</span><span class="n">engines</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
  201. <span class="n">descriptions</span><span class="p">[</span><span class="n">engine_name</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
  202. <span class="n">wikidata_id</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">engine</span><span class="p">,</span> <span class="s2">&quot;about&quot;</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;wikidata_id&#39;</span><span class="p">)</span>
  203. <span class="k">if</span> <span class="n">wikidata_id</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
  204. <span class="n">wd_to_engine_name</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="n">wikidata_id</span><span class="p">,</span> <span class="nb">set</span><span class="p">())</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">engine_name</span><span class="p">)</span>
  205. <span class="n">IDS</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="nb">list</span><span class="p">(</span><span class="nb">map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">wd_id</span><span class="p">:</span> <span class="s1">&#39;wd:&#39;</span> <span class="o">+</span> <span class="n">wd_id</span><span class="p">,</span> <span class="n">wd_to_engine_name</span><span class="o">.</span><span class="n">keys</span><span class="p">())))</span>
  206. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_wikidata_descriptions</span><span class="p">():</span>
  207. <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;Fetching wikidata descriptions&#39;</span><span class="p">)</span>
  208. <span class="n">searx</span><span class="o">.</span><span class="n">network</span><span class="o">.</span><span class="n">set_timeout_for_thread</span><span class="p">(</span><span class="mi">60</span><span class="p">)</span>
  209. <span class="n">result</span> <span class="o">=</span> <span class="n">wikidata</span><span class="o">.</span><span class="n">send_wikidata_query</span><span class="p">(</span>
  210. <span class="n">SPARQL_DESCRIPTION</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;%IDS%&#39;</span><span class="p">,</span> <span class="n">IDS</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;%LANGUAGES_SPARQL%&#39;</span><span class="p">,</span> <span class="n">LANGUAGES_SPARQL</span><span class="p">)</span>
  211. <span class="p">)</span>
  212. <span class="k">if</span> <span class="n">result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
  213. <span class="k">for</span> <span class="n">binding</span> <span class="ow">in</span> <span class="n">result</span><span class="p">[</span><span class="s1">&#39;results&#39;</span><span class="p">][</span><span class="s1">&#39;bindings&#39;</span><span class="p">]:</span>
  214. <span class="n">wikidata_id</span> <span class="o">=</span> <span class="n">binding</span><span class="p">[</span><span class="s1">&#39;item&#39;</span><span class="p">][</span><span class="s1">&#39;value&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;http://www.wikidata.org/entity/&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">)</span>
  215. <span class="n">wikidata_lang</span> <span class="o">=</span> <span class="n">binding</span><span class="p">[</span><span class="s1">&#39;itemDescription&#39;</span><span class="p">][</span><span class="s1">&#39;xml:lang&#39;</span><span class="p">]</span>
  216. <span class="n">desc</span> <span class="o">=</span> <span class="n">binding</span><span class="p">[</span><span class="s1">&#39;itemDescription&#39;</span><span class="p">][</span><span class="s1">&#39;value&#39;</span><span class="p">]</span>
  217. <span class="k">for</span> <span class="n">engine_name</span> <span class="ow">in</span> <span class="n">wd_to_engine_name</span><span class="p">[</span><span class="n">wikidata_id</span><span class="p">]:</span>
  218. <span class="k">for</span> <span class="n">searxng_locale</span> <span class="ow">in</span> <span class="n">LOCALE_NAMES</span><span class="p">:</span>
  219. <span class="k">if</span> <span class="n">WIKIPEDIA_LANGUAGES</span><span class="p">[</span><span class="n">searxng_locale</span><span class="p">]</span> <span class="o">!=</span> <span class="n">wikidata_lang</span><span class="p">:</span>
  220. <span class="k">continue</span>
  221. <span class="nb">print</span><span class="p">(</span>
  222. <span class="sa">f</span><span class="s2">&quot; engine: </span><span class="si">{</span><span class="n">engine_name</span><span class="si">:</span><span class="s2">20</span><span class="si">}</span><span class="s2"> / wikidata_lang: </span><span class="si">{</span><span class="n">wikidata_lang</span><span class="si">:</span><span class="s2">5</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">,</span>
  223. <span class="sa">f</span><span class="s2">&quot;/ len(wikidata_desc): </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">desc</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">,</span>
  224. <span class="p">)</span>
  225. <span class="n">update_description</span><span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">searxng_locale</span><span class="p">,</span> <span class="n">desc</span><span class="p">,</span> <span class="s1">&#39;wikidata&#39;</span><span class="p">)</span>
  226. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_wikipedia_descriptions</span><span class="p">():</span>
  227. <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;Fetching wikipedia descriptions&#39;</span><span class="p">)</span>
  228. <span class="n">result</span> <span class="o">=</span> <span class="n">wikidata</span><span class="o">.</span><span class="n">send_wikidata_query</span><span class="p">(</span>
  229. <span class="n">SPARQL_WIKIPEDIA_ARTICLE</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;%IDS%&#39;</span><span class="p">,</span> <span class="n">IDS</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;%LANGUAGES_SPARQL%&#39;</span><span class="p">,</span> <span class="n">LANGUAGES_SPARQL</span><span class="p">)</span>
  230. <span class="p">)</span>
  231. <span class="k">if</span> <span class="n">result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
  232. <span class="k">for</span> <span class="n">binding</span> <span class="ow">in</span> <span class="n">result</span><span class="p">[</span><span class="s1">&#39;results&#39;</span><span class="p">][</span><span class="s1">&#39;bindings&#39;</span><span class="p">]:</span>
  233. <span class="n">wikidata_id</span> <span class="o">=</span> <span class="n">binding</span><span class="p">[</span><span class="s1">&#39;item&#39;</span><span class="p">][</span><span class="s1">&#39;value&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;http://www.wikidata.org/entity/&#39;</span><span class="p">,</span> <span class="s1">&#39;&#39;</span><span class="p">)</span>
  234. <span class="n">wikidata_lang</span> <span class="o">=</span> <span class="n">binding</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">][</span><span class="s1">&#39;xml:lang&#39;</span><span class="p">]</span>
  235. <span class="n">wikipedia_url</span> <span class="o">=</span> <span class="n">binding</span><span class="p">[</span><span class="s1">&#39;article&#39;</span><span class="p">][</span><span class="s1">&#39;value&#39;</span><span class="p">]</span> <span class="c1"># for example the URL https://de.wikipedia.org/wiki/PubMed</span>
  236. <span class="k">for</span> <span class="n">engine_name</span> <span class="ow">in</span> <span class="n">wd_to_engine_name</span><span class="p">[</span><span class="n">wikidata_id</span><span class="p">]:</span>
  237. <span class="k">for</span> <span class="n">searxng_locale</span> <span class="ow">in</span> <span class="n">LOCALE_NAMES</span><span class="p">:</span>
  238. <span class="k">if</span> <span class="n">WIKIPEDIA_LANGUAGES</span><span class="p">[</span><span class="n">searxng_locale</span><span class="p">]</span> <span class="o">!=</span> <span class="n">wikidata_lang</span><span class="p">:</span>
  239. <span class="k">continue</span>
  240. <span class="n">desc</span> <span class="o">=</span> <span class="n">get_wikipedia_summary</span><span class="p">(</span><span class="n">wikipedia_url</span><span class="p">,</span> <span class="n">searxng_locale</span><span class="p">)</span>
  241. <span class="k">if</span> <span class="ow">not</span> <span class="n">desc</span><span class="p">:</span>
  242. <span class="k">continue</span>
  243. <span class="nb">print</span><span class="p">(</span>
  244. <span class="sa">f</span><span class="s2">&quot; engine: </span><span class="si">{</span><span class="n">engine_name</span><span class="si">:</span><span class="s2">20</span><span class="si">}</span><span class="s2"> / wikidata_lang: </span><span class="si">{</span><span class="n">wikidata_lang</span><span class="si">:</span><span class="s2">5</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">,</span>
  245. <span class="sa">f</span><span class="s2">&quot;/ len(wikipedia_desc): </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">desc</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">,</span>
  246. <span class="p">)</span>
  247. <span class="n">update_description</span><span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">searxng_locale</span><span class="p">,</span> <span class="n">desc</span><span class="p">,</span> <span class="s1">&#39;wikipedia&#39;</span><span class="p">)</span>
  248. <span class="k">def</span><span class="w"> </span><span class="nf">normalize_url</span><span class="p">(</span><span class="n">url</span><span class="p">):</span>
  249. <span class="n">url</span> <span class="o">=</span> <span class="n">url</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;</span><span class="si">{language}</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39;en&#39;</span><span class="p">)</span>
  250. <span class="n">url</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">_replace</span><span class="p">(</span><span class="n">path</span><span class="o">=</span><span class="s1">&#39;/&#39;</span><span class="p">,</span> <span class="n">params</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="n">query</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="n">fragment</span><span class="o">=</span><span class="s1">&#39;&#39;</span><span class="p">)</span><span class="o">.</span><span class="n">geturl</span><span class="p">()</span>
  251. <span class="n">url</span> <span class="o">=</span> <span class="n">url</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;https://api.&#39;</span><span class="p">,</span> <span class="s1">&#39;https://&#39;</span><span class="p">)</span>
  252. <span class="k">return</span> <span class="n">url</span>
  253. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_website_description</span><span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">website</span><span class="p">):</span>
  254. <span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;- fetch website descr: </span><span class="si">{</span><span class="n">engine_name</span><span class="si">}</span><span class="s2"> / </span><span class="si">{</span><span class="n">website</span><span class="si">}</span><span class="s2">&quot;</span><span class="p">)</span>
  255. <span class="n">default_lang</span><span class="p">,</span> <span class="n">default_description</span> <span class="o">=</span> <span class="n">get_website_description</span><span class="p">(</span><span class="n">website</span><span class="p">,</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
  256. <span class="k">if</span> <span class="n">default_lang</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">default_description</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  257. <span class="c1"># the front page can&#39;t be fetched: skip this engine</span>
  258. <span class="k">return</span>
  259. <span class="c1"># to specify an order in where the most common languages are in front of the</span>
  260. <span class="c1"># language list ..</span>
  261. <span class="n">languages</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;en&#39;</span><span class="p">,</span> <span class="s1">&#39;es&#39;</span><span class="p">,</span> <span class="s1">&#39;pt&#39;</span><span class="p">,</span> <span class="s1">&#39;ru&#39;</span><span class="p">,</span> <span class="s1">&#39;tr&#39;</span><span class="p">,</span> <span class="s1">&#39;fr&#39;</span><span class="p">]</span>
  262. <span class="n">languages</span> <span class="o">=</span> <span class="n">languages</span> <span class="o">+</span> <span class="p">[</span><span class="n">l</span> <span class="k">for</span> <span class="n">l</span> <span class="ow">in</span> <span class="n">LOCALE_NAMES</span> <span class="k">if</span> <span class="n">l</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">languages</span><span class="p">]</span>
  263. <span class="n">previous_matched_lang</span> <span class="o">=</span> <span class="kc">None</span>
  264. <span class="n">previous_count</span> <span class="o">=</span> <span class="mi">0</span>
  265. <span class="k">for</span> <span class="n">lang</span> <span class="ow">in</span> <span class="n">languages</span><span class="p">:</span>
  266. <span class="k">if</span> <span class="n">lang</span> <span class="ow">in</span> <span class="n">descriptions</span><span class="p">[</span><span class="n">engine_name</span><span class="p">]:</span>
  267. <span class="k">continue</span>
  268. <span class="n">fetched_lang</span><span class="p">,</span> <span class="n">desc</span> <span class="o">=</span> <span class="n">get_website_description</span><span class="p">(</span><span class="n">website</span><span class="p">,</span> <span class="n">lang</span><span class="p">,</span> <span class="n">WIKIPEDIA_LANGUAGES</span><span class="p">[</span><span class="n">lang</span><span class="p">])</span>
  269. <span class="k">if</span> <span class="n">fetched_lang</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="n">desc</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  270. <span class="k">continue</span>
  271. <span class="c1"># check if desc changed with the different lang values</span>
  272. <span class="k">if</span> <span class="n">fetched_lang</span> <span class="o">==</span> <span class="n">previous_matched_lang</span><span class="p">:</span>
  273. <span class="n">previous_count</span> <span class="o">+=</span> <span class="mi">1</span>
  274. <span class="k">if</span> <span class="n">previous_count</span> <span class="o">==</span> <span class="mi">6</span><span class="p">:</span>
  275. <span class="c1"># the website has returned the same description for 6 different languages in Accept-Language header</span>
  276. <span class="c1"># stop now</span>
  277. <span class="k">break</span>
  278. <span class="k">else</span><span class="p">:</span>
  279. <span class="n">previous_matched_lang</span> <span class="o">=</span> <span class="n">fetched_lang</span>
  280. <span class="n">previous_count</span> <span class="o">=</span> <span class="mi">0</span>
  281. <span class="c1"># Don&#39;t trust in the value of fetched_lang, some websites return</span>
  282. <span class="c1"># for some inappropriate values, by example bing-images::</span>
  283. <span class="c1">#</span>
  284. <span class="c1"># requested lang: zh-Hans-CN / fetched lang: ceb / desc: 查看根据您的兴趣量身定制的提要</span>
  285. <span class="c1">#</span>
  286. <span class="c1"># The lang ceb is &quot;Cebuano&quot; but the description is given in zh-Hans-CN</span>
  287. <span class="nb">print</span><span class="p">(</span>
  288. <span class="sa">f</span><span class="s2">&quot; engine: </span><span class="si">{</span><span class="n">engine_name</span><span class="si">:</span><span class="s2">20</span><span class="si">}</span><span class="s2"> / requested lang:</span><span class="si">{</span><span class="n">lang</span><span class="si">:</span><span class="s2">7</span><span class="si">}</span><span class="s2">&quot;</span>
  289. <span class="sa">f</span><span class="s2">&quot; / fetched lang: </span><span class="si">{</span><span class="n">fetched_lang</span><span class="si">:</span><span class="s2">7</span><span class="si">}</span><span class="s2"> / len(desc): </span><span class="si">{</span><span class="nb">len</span><span class="p">(</span><span class="n">desc</span><span class="p">)</span><span class="si">}</span><span class="s2">&quot;</span>
  290. <span class="p">)</span>
  291. <span class="n">matched_lang</span> <span class="o">=</span> <span class="n">match_locale</span><span class="p">(</span><span class="n">fetched_lang</span><span class="p">,</span> <span class="n">LOCALE_NAMES</span><span class="o">.</span><span class="n">keys</span><span class="p">(),</span> <span class="n">fallback</span><span class="o">=</span><span class="n">lang</span><span class="p">)</span>
  292. <span class="n">update_description</span><span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">matched_lang</span><span class="p">,</span> <span class="n">desc</span><span class="p">,</span> <span class="n">website</span><span class="p">,</span> <span class="n">replace</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
  293. <span class="k">def</span><span class="w"> </span><span class="nf">fetch_website_descriptions</span><span class="p">():</span>
  294. <span class="nb">print</span><span class="p">(</span><span class="s1">&#39;Fetching website descriptions&#39;</span><span class="p">)</span>
  295. <span class="k">for</span> <span class="n">engine_name</span><span class="p">,</span> <span class="n">engine</span> <span class="ow">in</span> <span class="n">searx</span><span class="o">.</span><span class="n">engines</span><span class="o">.</span><span class="n">engines</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
  296. <span class="n">website</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">engine</span><span class="p">,</span> <span class="s2">&quot;about&quot;</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;website&#39;</span><span class="p">)</span>
  297. <span class="k">if</span> <span class="n">website</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">engine</span><span class="p">,</span> <span class="s2">&quot;search_url&quot;</span><span class="p">):</span>
  298. <span class="n">website</span> <span class="o">=</span> <span class="n">normalize_url</span><span class="p">(</span><span class="nb">getattr</span><span class="p">(</span><span class="n">engine</span><span class="p">,</span> <span class="s2">&quot;search_url&quot;</span><span class="p">))</span>
  299. <span class="k">if</span> <span class="n">website</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">engine</span><span class="p">,</span> <span class="s2">&quot;base_url&quot;</span><span class="p">):</span>
  300. <span class="n">website</span> <span class="o">=</span> <span class="n">normalize_url</span><span class="p">(</span><span class="nb">getattr</span><span class="p">(</span><span class="n">engine</span><span class="p">,</span> <span class="s2">&quot;base_url&quot;</span><span class="p">))</span>
  301. <span class="k">if</span> <span class="n">website</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
  302. <span class="n">fetch_website_description</span><span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">website</span><span class="p">)</span>
  303. <span class="k">def</span><span class="w"> </span><span class="nf">get_engine_descriptions_filename</span><span class="p">():</span>
  304. <span class="k">return</span> <span class="n">join</span><span class="p">(</span><span class="n">join</span><span class="p">(</span><span class="n">searx_dir</span><span class="p">,</span> <span class="s2">&quot;data&quot;</span><span class="p">),</span> <span class="s2">&quot;engine_descriptions.json&quot;</span><span class="p">)</span>
  305. <div class="viewcode-block" id="get_output">
  306. <a class="viewcode-back" href="../../../dev/searxng_extra/update.html#searxng_extra.update.update_engine_descriptions.get_output">[docs]</a>
  307. <span class="k">def</span><span class="w"> </span><span class="nf">get_output</span><span class="p">():</span>
  308. <span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
  309. <span class="sd"> From descriptions[engine][language] = [description, source]</span>
  310. <span class="sd"> To</span>
  311. <span class="sd"> * output[language][engine] = description_and_source</span>
  312. <span class="sd"> * description_and_source can be:</span>
  313. <span class="sd"> * [description, source]</span>
  314. <span class="sd"> * description (if source = &quot;wikipedia&quot;)</span>
  315. <span class="sd"> * [f&quot;engine:lang&quot;, &quot;ref&quot;] (reference to another existing description)</span>
  316. <span class="sd"> &quot;&quot;&quot;</span>
  317. <span class="n">output</span> <span class="o">=</span> <span class="p">{</span><span class="n">locale</span><span class="p">:</span> <span class="p">{}</span> <span class="k">for</span> <span class="n">locale</span> <span class="ow">in</span> <span class="n">LOCALE_NAMES</span><span class="p">}</span>
  318. <span class="n">seen_descriptions</span> <span class="o">=</span> <span class="p">{}</span>
  319. <span class="k">for</span> <span class="n">engine_name</span><span class="p">,</span> <span class="n">lang_descriptions</span> <span class="ow">in</span> <span class="n">descriptions</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
  320. <span class="k">for</span> <span class="n">language</span><span class="p">,</span> <span class="n">description</span> <span class="ow">in</span> <span class="n">lang_descriptions</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
  321. <span class="k">if</span> <span class="n">description</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">in</span> <span class="n">seen_descriptions</span><span class="p">:</span>
  322. <span class="n">ref</span> <span class="o">=</span> <span class="n">seen_descriptions</span><span class="p">[</span><span class="n">description</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span>
  323. <span class="n">description</span> <span class="o">=</span> <span class="p">[</span><span class="sa">f</span><span class="s1">&#39;</span><span class="si">{</span><span class="n">ref</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="si">}</span><span class="s1">:</span><span class="si">{</span><span class="n">ref</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="si">}</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39;ref&#39;</span><span class="p">]</span>
  324. <span class="k">else</span><span class="p">:</span>
  325. <span class="n">seen_descriptions</span><span class="p">[</span><span class="n">description</span><span class="p">[</span><span class="mi">0</span><span class="p">]]</span> <span class="o">=</span> <span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">language</span><span class="p">)</span>
  326. <span class="k">if</span> <span class="n">description</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;wikipedia&#39;</span><span class="p">:</span>
  327. <span class="n">description</span> <span class="o">=</span> <span class="n">description</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
  328. <span class="n">output</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="n">language</span><span class="p">,</span> <span class="p">{})</span><span class="o">.</span><span class="n">setdefault</span><span class="p">(</span><span class="n">engine_name</span><span class="p">,</span> <span class="n">description</span><span class="p">)</span>
  329. <span class="k">return</span> <span class="n">output</span></div>
  330. <span class="k">def</span><span class="w"> </span><span class="nf">main</span><span class="p">():</span>
  331. <span class="n">initialize</span><span class="p">()</span>
  332. <span class="n">fetch_wikidata_descriptions</span><span class="p">()</span>
  333. <span class="n">fetch_wikipedia_descriptions</span><span class="p">()</span>
  334. <span class="n">fetch_website_descriptions</span><span class="p">()</span>
  335. <span class="n">output</span> <span class="o">=</span> <span class="n">get_output</span><span class="p">()</span>
  336. <span class="k">with</span> <span class="n">DATA_FILE</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="s1">&#39;w&#39;</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;utf8&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
  337. <span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">json</span><span class="o">.</span><span class="n">dumps</span><span class="p">(</span><span class="n">output</span><span class="p">,</span> <span class="n">indent</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">separators</span><span class="o">=</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> <span class="n">sort_keys</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">ensure_ascii</span><span class="o">=</span><span class="kc">False</span><span class="p">))</span>
  338. <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">&quot;__main__&quot;</span><span class="p">:</span>
  339. <span class="n">main</span><span class="p">()</span>
  340. </pre></div>
  341. <div class="clearer"></div>
  342. </div>
  343. </div>
  344. </div>
  345. <span id="sidebar-top"></span>
  346. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  347. <div class="sphinxsidebarwrapper">
  348. <p class="logo"><a href="../../../index.html">
  349. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  350. </a></p>
  351. <h3><a href="../../../index.html">Table of Contents</a></h3>
  352. <ul>
  353. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  354. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  355. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  356. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  357. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  358. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  359. </ul>
  360. <h3>Project Links</h3>
  361. <ul>
  362. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  363. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  364. <li><a href="https://searx.space">Public instances</a>
  365. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  366. </ul><h3>Navigation</h3>
  367. <ul>
  368. <li><a href="../../../index.html">Overview</a>
  369. <ul>
  370. <li><a href="../../index.html">Module code</a>
  371. </ul>
  372. </li>
  373. </ul>
  374. </li>
  375. </ul>
  376. <search id="searchbox" style="display: none" role="search">
  377. <h3 id="searchlabel">Quick search</h3>
  378. <div class="searchformwrapper">
  379. <form class="search" action="../../../search.html" method="get">
  380. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  381. <input type="submit" value="Go" />
  382. </form>
  383. </div>
  384. </search>
  385. <script>document.getElementById('searchbox').style.display = "block"</script>
  386. </div>
  387. </div>
  388. <div class="clearer"></div>
  389. </div>
  390. <div class="footer" role="contentinfo">
  391. &#169; Copyright SearXNG team.
  392. </div>
  393. </body>
  394. </html>