utils.html 114 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038
  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.utils &#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" accesskey="U">Module code</a> &#187;</li>
  28. <li class="nav-item nav-item-this"><a href="">searx.utils</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 searx.utils</h1><div class="highlight"><pre>
  36. <span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
  37. <span class="sd">&quot;&quot;&quot;Utility functions for the engines&quot;&quot;&quot;</span>
  38. <span class="kn">from</span><span class="w"> </span><span class="nn">__future__</span><span class="w"> </span><span class="kn">import</span> <span class="n">annotations</span>
  39. <span class="kn">import</span><span class="w"> </span><span class="nn">re</span>
  40. <span class="kn">import</span><span class="w"> </span><span class="nn">importlib</span>
  41. <span class="kn">import</span><span class="w"> </span><span class="nn">importlib.util</span>
  42. <span class="kn">import</span><span class="w"> </span><span class="nn">json</span>
  43. <span class="kn">import</span><span class="w"> </span><span class="nn">types</span>
  44. <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">Optional</span><span class="p">,</span> <span class="n">Union</span><span class="p">,</span> <span class="n">Any</span><span class="p">,</span> <span class="n">Set</span><span class="p">,</span> <span class="n">List</span><span class="p">,</span> <span class="n">Dict</span><span class="p">,</span> <span class="n">MutableMapping</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">,</span> <span class="n">Callable</span>
  45. <span class="kn">from</span><span class="w"> </span><span class="nn">numbers</span><span class="w"> </span><span class="kn">import</span> <span class="n">Number</span>
  46. <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">splitext</span><span class="p">,</span> <span class="n">join</span>
  47. <span class="kn">from</span><span class="w"> </span><span class="nn">random</span><span class="w"> </span><span class="kn">import</span> <span class="n">choice</span>
  48. <span class="kn">from</span><span class="w"> </span><span class="nn">html.parser</span><span class="w"> </span><span class="kn">import</span> <span class="n">HTMLParser</span>
  49. <span class="kn">from</span><span class="w"> </span><span class="nn">html</span><span class="w"> </span><span class="kn">import</span> <span class="n">escape</span>
  50. <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">urljoin</span><span class="p">,</span> <span class="n">urlparse</span><span class="p">,</span> <span class="n">parse_qs</span><span class="p">,</span> <span class="n">urlencode</span>
  51. <span class="kn">from</span><span class="w"> </span><span class="nn">datetime</span><span class="w"> </span><span class="kn">import</span> <span class="n">timedelta</span>
  52. <span class="kn">from</span><span class="w"> </span><span class="nn">markdown_it</span><span class="w"> </span><span class="kn">import</span> <span class="n">MarkdownIt</span>
  53. <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>
  54. <span class="kn">from</span><span class="w"> </span><span class="nn">lxml.etree</span><span class="w"> </span><span class="kn">import</span> <span class="n">ElementBase</span><span class="p">,</span> <span class="n">XPath</span><span class="p">,</span> <span class="n">XPathError</span><span class="p">,</span> <span class="n">XPathSyntaxError</span>
  55. <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">settings</span>
  56. <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">USER_AGENTS</span><span class="p">,</span> <span class="n">data_dir</span>
  57. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.version</span><span class="w"> </span><span class="kn">import</span> <span class="n">VERSION_TAG</span>
  58. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.sxng_locales</span><span class="w"> </span><span class="kn">import</span> <span class="n">sxng_locales</span>
  59. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.exceptions</span><span class="w"> </span><span class="kn">import</span> <span class="n">SearxXPathSyntaxException</span><span class="p">,</span> <span class="n">SearxEngineXPathException</span>
  60. <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">logger</span>
  61. <span class="n">logger</span> <span class="o">=</span> <span class="n">logger</span><span class="o">.</span><span class="n">getChild</span><span class="p">(</span><span class="s1">&#39;utils&#39;</span><span class="p">)</span>
  62. <span class="n">XPathSpecType</span> <span class="o">=</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">XPath</span><span class="p">]</span>
  63. <span class="n">_BLOCKED_TAGS</span> <span class="o">=</span> <span class="p">(</span><span class="s1">&#39;script&#39;</span><span class="p">,</span> <span class="s1">&#39;style&#39;</span><span class="p">)</span>
  64. <span class="n">_ECMA_UNESCAPE4_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;</span><span class="si">%u</span><span class="s1">([0-9a-fA-F]</span><span class="si">{4}</span><span class="s1">)&#39;</span><span class="p">,</span> <span class="n">re</span><span class="o">.</span><span class="n">UNICODE</span><span class="p">)</span>
  65. <span class="n">_ECMA_UNESCAPE2_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;%([0-9a-fA-F]</span><span class="si">{2}</span><span class="s1">)&#39;</span><span class="p">,</span> <span class="n">re</span><span class="o">.</span><span class="n">UNICODE</span><span class="p">)</span>
  66. <span class="n">_JS_QUOTE_KEYS_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;([\{\s,])(\w+)(:)&#39;</span><span class="p">)</span>
  67. <span class="n">_JS_VOID_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;void\s+[0-9]+|void\s*\([0-9]+\)&#39;</span><span class="p">)</span>
  68. <span class="n">_JS_DECIMAL_RE</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="sa">r</span><span class="s2">&quot;:\s*\.&quot;</span><span class="p">)</span>
  69. <span class="n">_XPATH_CACHE</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">XPath</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span>
  70. <span class="n">_LANG_TO_LC_CACHE</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="p">{}</span>
  71. <span class="n">_FASTTEXT_MODEL</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="s2">&quot;fasttext.FastText._FastText&quot;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span> <span class="c1"># type: ignore</span>
  72. <span class="sd">&quot;&quot;&quot;fasttext model to predict language of a search term&quot;&quot;&quot;</span>
  73. <span class="n">SEARCH_LANGUAGE_CODES</span> <span class="o">=</span> <span class="nb">frozenset</span><span class="p">([</span><span class="n">searxng_locale</span><span class="p">[</span><span class="mi">0</span><span class="p">]</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="k">for</span> <span class="n">searxng_locale</span> <span class="ow">in</span> <span class="n">sxng_locales</span><span class="p">])</span>
  74. <span class="sd">&quot;&quot;&quot;Languages supported by most searxng engines (:py:obj:`searx.sxng_locales.sxng_locales`).&quot;&quot;&quot;</span>
  75. <span class="k">class</span><span class="w"> </span><span class="nc">_NotSetClass</span><span class="p">:</span> <span class="c1"># pylint: disable=too-few-public-methods</span>
  76. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Internal class for this module, do not create instance of this class.</span>
  77. <span class="sd"> Replace the None value, allow explicitly pass None as a function argument&quot;&quot;&quot;</span>
  78. <span class="n">_NOTSET</span> <span class="o">=</span> <span class="n">_NotSetClass</span><span class="p">()</span>
  79. <div class="viewcode-block" id="searx_useragent">
  80. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.searx_useragent">[docs]</a>
  81. <span class="k">def</span><span class="w"> </span><span class="nf">searx_useragent</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  82. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Return the searx User Agent&quot;&quot;&quot;</span>
  83. <span class="k">return</span> <span class="s1">&#39;searx/</span><span class="si">{searx_version}</span><span class="s1"> </span><span class="si">{suffix}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
  84. <span class="n">searx_version</span><span class="o">=</span><span class="n">VERSION_TAG</span><span class="p">,</span> <span class="n">suffix</span><span class="o">=</span><span class="n">settings</span><span class="p">[</span><span class="s1">&#39;outgoing&#39;</span><span class="p">][</span><span class="s1">&#39;useragent_suffix&#39;</span><span class="p">]</span>
  85. <span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span></div>
  86. <div class="viewcode-block" id="gen_useragent">
  87. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.gen_useragent">[docs]</a>
  88. <span class="k">def</span><span class="w"> </span><span class="nf">gen_useragent</span><span class="p">(</span><span class="n">os_string</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  89. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Return a random browser User Agent</span>
  90. <span class="sd"> See searx/data/useragents.json</span>
  91. <span class="sd"> &quot;&quot;&quot;</span>
  92. <span class="k">return</span> <span class="n">USER_AGENTS</span><span class="p">[</span><span class="s1">&#39;ua&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">os</span><span class="o">=</span><span class="n">os_string</span> <span class="ow">or</span> <span class="n">choice</span><span class="p">(</span><span class="n">USER_AGENTS</span><span class="p">[</span><span class="s1">&#39;os&#39;</span><span class="p">]),</span> <span class="n">version</span><span class="o">=</span><span class="n">choice</span><span class="p">(</span><span class="n">USER_AGENTS</span><span class="p">[</span><span class="s1">&#39;versions&#39;</span><span class="p">]))</span></div>
  93. <span class="k">class</span><span class="w"> </span><span class="nc">_HTMLTextExtractorException</span><span class="p">(</span><span class="ne">Exception</span><span class="p">):</span>
  94. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Internal exception raised when the HTML is invalid&quot;&quot;&quot;</span>
  95. <span class="k">class</span><span class="w"> </span><span class="nc">_HTMLTextExtractor</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">):</span>
  96. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Internal class to extract text from HTML&quot;&quot;&quot;</span>
  97. <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  98. <span class="n">HTMLParser</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
  99. <span class="bp">self</span><span class="o">.</span><span class="n">result</span> <span class="o">=</span> <span class="p">[]</span>
  100. <span class="bp">self</span><span class="o">.</span><span class="n">tags</span> <span class="o">=</span> <span class="p">[]</span>
  101. <span class="k">def</span><span class="w"> </span><span class="nf">handle_starttag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag</span><span class="p">,</span> <span class="n">attrs</span><span class="p">):</span>
  102. <span class="bp">self</span><span class="o">.</span><span class="n">tags</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">tag</span><span class="p">)</span>
  103. <span class="k">if</span> <span class="n">tag</span> <span class="o">==</span> <span class="s1">&#39;br&#39;</span><span class="p">:</span>
  104. <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s1">&#39; &#39;</span><span class="p">)</span>
  105. <span class="k">def</span><span class="w"> </span><span class="nf">handle_endtag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag</span><span class="p">):</span>
  106. <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">tags</span><span class="p">:</span>
  107. <span class="k">return</span>
  108. <span class="k">if</span> <span class="n">tag</span> <span class="o">!=</span> <span class="bp">self</span><span class="o">.</span><span class="n">tags</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]:</span>
  109. <span class="k">raise</span> <span class="n">_HTMLTextExtractorException</span><span class="p">()</span>
  110. <span class="bp">self</span><span class="o">.</span><span class="n">tags</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
  111. <span class="k">def</span><span class="w"> </span><span class="nf">is_valid_tag</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  112. <span class="k">return</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">tags</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">tags</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">_BLOCKED_TAGS</span>
  113. <span class="k">def</span><span class="w"> </span><span class="nf">handle_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
  114. <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_valid_tag</span><span class="p">():</span>
  115. <span class="k">return</span>
  116. <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
  117. <span class="k">def</span><span class="w"> </span><span class="nf">handle_charref</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
  118. <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_valid_tag</span><span class="p">():</span>
  119. <span class="k">return</span>
  120. <span class="k">if</span> <span class="n">name</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">&#39;x&#39;</span><span class="p">,</span> <span class="s1">&#39;X&#39;</span><span class="p">):</span>
  121. <span class="n">codepoint</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">name</span><span class="p">[</span><span class="mi">1</span><span class="p">:],</span> <span class="mi">16</span><span class="p">)</span>
  122. <span class="k">else</span><span class="p">:</span>
  123. <span class="n">codepoint</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
  124. <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">chr</span><span class="p">(</span><span class="n">codepoint</span><span class="p">))</span>
  125. <span class="k">def</span><span class="w"> </span><span class="nf">handle_entityref</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span>
  126. <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_valid_tag</span><span class="p">():</span>
  127. <span class="k">return</span>
  128. <span class="c1"># codepoint = htmlentitydefs.name2codepoint[name]</span>
  129. <span class="c1"># self.result.append(chr(codepoint))</span>
  130. <span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">name</span><span class="p">)</span>
  131. <span class="k">def</span><span class="w"> </span><span class="nf">get_text</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
  132. <span class="k">return</span> <span class="s1">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">result</span><span class="p">)</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
  133. <span class="k">def</span><span class="w"> </span><span class="nf">error</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">message</span><span class="p">):</span>
  134. <span class="c1"># error handle is needed in &lt;py3.10</span>
  135. <span class="c1"># https://github.com/python/cpython/pull/8562/files</span>
  136. <span class="k">raise</span> <span class="ne">AssertionError</span><span class="p">(</span><span class="n">message</span><span class="p">)</span>
  137. <div class="viewcode-block" id="html_to_text">
  138. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.html_to_text">[docs]</a>
  139. <span class="k">def</span><span class="w"> </span><span class="nf">html_to_text</span><span class="p">(</span><span class="n">html_str</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  140. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Extract text from a HTML string</span>
  141. <span class="sd"> Args:</span>
  142. <span class="sd"> * html_str (str): string HTML</span>
  143. <span class="sd"> Returns:</span>
  144. <span class="sd"> * str: extracted text</span>
  145. <span class="sd"> Examples:</span>
  146. <span class="sd"> &gt;&gt;&gt; html_to_text(&#39;Example &lt;span id=&quot;42&quot;&gt;#2&lt;/span&gt;&#39;)</span>
  147. <span class="sd"> &#39;Example #2&#39;</span>
  148. <span class="sd"> &gt;&gt;&gt; html_to_text(&#39;&lt;style&gt;.span { color: red; }&lt;/style&gt;&lt;span&gt;Example&lt;/span&gt;&#39;)</span>
  149. <span class="sd"> &#39;Example&#39;</span>
  150. <span class="sd"> &gt;&gt;&gt; html_to_text(r&#39;regexp: (?&lt;![a-zA-Z]&#39;)</span>
  151. <span class="sd"> &#39;regexp: (?&lt;![a-zA-Z]&#39;</span>
  152. <span class="sd"> &quot;&quot;&quot;</span>
  153. <span class="k">if</span> <span class="ow">not</span> <span class="n">html_str</span><span class="p">:</span>
  154. <span class="k">return</span> <span class="s2">&quot;&quot;</span>
  155. <span class="n">html_str</span> <span class="o">=</span> <span class="n">html_str</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39; &#39;</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\r</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39; &#39;</span><span class="p">)</span>
  156. <span class="n">html_str</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">html_str</span><span class="o">.</span><span class="n">split</span><span class="p">())</span>
  157. <span class="n">s</span> <span class="o">=</span> <span class="n">_HTMLTextExtractor</span><span class="p">()</span>
  158. <span class="k">try</span><span class="p">:</span>
  159. <span class="n">s</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="n">html_str</span><span class="p">)</span>
  160. <span class="k">except</span> <span class="ne">AssertionError</span><span class="p">:</span>
  161. <span class="n">s</span> <span class="o">=</span> <span class="n">_HTMLTextExtractor</span><span class="p">()</span>
  162. <span class="n">s</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="n">escape</span><span class="p">(</span><span class="n">html_str</span><span class="p">,</span> <span class="n">quote</span><span class="o">=</span><span class="kc">True</span><span class="p">))</span>
  163. <span class="k">except</span> <span class="n">_HTMLTextExtractorException</span><span class="p">:</span>
  164. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;HTMLTextExtractor: invalid HTML</span><span class="se">\n</span><span class="si">%s</span><span class="s2">&quot;</span><span class="p">,</span> <span class="n">html_str</span><span class="p">)</span>
  165. <span class="k">return</span> <span class="n">s</span><span class="o">.</span><span class="n">get_text</span><span class="p">()</span></div>
  166. <div class="viewcode-block" id="markdown_to_text">
  167. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.markdown_to_text">[docs]</a>
  168. <span class="k">def</span><span class="w"> </span><span class="nf">markdown_to_text</span><span class="p">(</span><span class="n">markdown_str</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  169. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Extract text from a Markdown string</span>
  170. <span class="sd"> Args:</span>
  171. <span class="sd"> * markdown_str (str): string Markdown</span>
  172. <span class="sd"> Returns:</span>
  173. <span class="sd"> * str: extracted text</span>
  174. <span class="sd"> Examples:</span>
  175. <span class="sd"> &gt;&gt;&gt; markdown_to_text(&#39;[example](https://example.com)&#39;)</span>
  176. <span class="sd"> &#39;example&#39;</span>
  177. <span class="sd"> &gt;&gt;&gt; markdown_to_text(&#39;## Headline&#39;)</span>
  178. <span class="sd"> &#39;Headline&#39;</span>
  179. <span class="sd"> &quot;&quot;&quot;</span>
  180. <span class="n">html_str</span> <span class="o">=</span> <span class="p">(</span>
  181. <span class="n">MarkdownIt</span><span class="p">(</span><span class="s2">&quot;commonmark&quot;</span><span class="p">,</span> <span class="p">{</span><span class="s2">&quot;typographer&quot;</span><span class="p">:</span> <span class="kc">True</span><span class="p">})</span><span class="o">.</span><span class="n">enable</span><span class="p">([</span><span class="s2">&quot;replacements&quot;</span><span class="p">,</span> <span class="s2">&quot;smartquotes&quot;</span><span class="p">])</span><span class="o">.</span><span class="n">render</span><span class="p">(</span><span class="n">markdown_str</span><span class="p">)</span>
  182. <span class="p">)</span>
  183. <span class="k">return</span> <span class="n">html_to_text</span><span class="p">(</span><span class="n">html_str</span><span class="p">)</span></div>
  184. <div class="viewcode-block" id="extract_text">
  185. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.extract_text">[docs]</a>
  186. <span class="k">def</span><span class="w"> </span><span class="nf">extract_text</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">,</span> <span class="n">allow_none</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span>
  187. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Extract text from a lxml result</span>
  188. <span class="sd"> * if xpath_results is list, extract the text from each result and concat the list</span>
  189. <span class="sd"> * if xpath_results is a xml element, extract all the text node from it</span>
  190. <span class="sd"> ( text_content() method from lxml )</span>
  191. <span class="sd"> * if xpath_results is a string element, then it&#39;s already done</span>
  192. <span class="sd"> &quot;&quot;&quot;</span>
  193. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
  194. <span class="c1"># it&#39;s list of result : concat everything using recursive call</span>
  195. <span class="n">result</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  196. <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">xpath_results</span><span class="p">:</span>
  197. <span class="n">result</span> <span class="o">=</span> <span class="n">result</span> <span class="o">+</span> <span class="p">(</span><span class="n">extract_text</span><span class="p">(</span><span class="n">e</span><span class="p">)</span> <span class="ow">or</span> <span class="s1">&#39;&#39;</span><span class="p">)</span>
  198. <span class="k">return</span> <span class="n">result</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
  199. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">,</span> <span class="n">ElementBase</span><span class="p">):</span>
  200. <span class="c1"># it&#39;s a element</span>
  201. <span class="n">text</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">tostring</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;unicode&#39;</span><span class="p">,</span> <span class="n">method</span><span class="o">=</span><span class="s1">&#39;text&#39;</span><span class="p">,</span> <span class="n">with_tail</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
  202. <span class="n">text</span> <span class="o">=</span> <span class="n">text</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39; &#39;</span><span class="p">)</span>
  203. <span class="k">return</span> <span class="s1">&#39; &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">text</span><span class="o">.</span><span class="n">split</span><span class="p">())</span>
  204. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">,</span> <span class="p">(</span><span class="nb">str</span><span class="p">,</span> <span class="n">Number</span><span class="p">,</span> <span class="nb">bool</span><span class="p">)):</span>
  205. <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">)</span>
  206. <span class="k">if</span> <span class="n">xpath_results</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">allow_none</span><span class="p">:</span>
  207. <span class="k">return</span> <span class="kc">None</span>
  208. <span class="k">if</span> <span class="n">xpath_results</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">allow_none</span><span class="p">:</span>
  209. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;extract_text(None, allow_none=False)&#39;</span><span class="p">)</span>
  210. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;unsupported type&#39;</span><span class="p">)</span></div>
  211. <div class="viewcode-block" id="normalize_url">
  212. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.normalize_url">[docs]</a>
  213. <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> <span class="nb">str</span><span class="p">,</span> <span class="n">base_url</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  214. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Normalize URL: add protocol, join URL with base_url, add trailing slash if there is no path</span>
  215. <span class="sd"> Args:</span>
  216. <span class="sd"> * url (str): Relative URL</span>
  217. <span class="sd"> * base_url (str): Base URL, it must be an absolute URL.</span>
  218. <span class="sd"> Example:</span>
  219. <span class="sd"> &gt;&gt;&gt; normalize_url(&#39;https://example.com&#39;, &#39;http://example.com/&#39;)</span>
  220. <span class="sd"> &#39;https://example.com/&#39;</span>
  221. <span class="sd"> &gt;&gt;&gt; normalize_url(&#39;//example.com&#39;, &#39;http://example.com/&#39;)</span>
  222. <span class="sd"> &#39;http://example.com/&#39;</span>
  223. <span class="sd"> &gt;&gt;&gt; normalize_url(&#39;//example.com&#39;, &#39;https://example.com/&#39;)</span>
  224. <span class="sd"> &#39;https://example.com/&#39;</span>
  225. <span class="sd"> &gt;&gt;&gt; normalize_url(&#39;/path?a=1&#39;, &#39;https://example.com&#39;)</span>
  226. <span class="sd"> &#39;https://example.com/path?a=1&#39;</span>
  227. <span class="sd"> &gt;&gt;&gt; normalize_url(&#39;&#39;, &#39;https://example.com&#39;)</span>
  228. <span class="sd"> &#39;https://example.com/&#39;</span>
  229. <span class="sd"> &gt;&gt;&gt; normalize_url(&#39;/test&#39;, &#39;/path&#39;)</span>
  230. <span class="sd"> raise ValueError</span>
  231. <span class="sd"> Raises:</span>
  232. <span class="sd"> * lxml.etree.ParserError</span>
  233. <span class="sd"> Returns:</span>
  234. <span class="sd"> * str: normalized URL</span>
  235. <span class="sd"> &quot;&quot;&quot;</span>
  236. <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;//&#39;</span><span class="p">):</span>
  237. <span class="c1"># add http or https to this kind of url //example.com/</span>
  238. <span class="n">parsed_search_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">base_url</span><span class="p">)</span>
  239. <span class="n">url</span> <span class="o">=</span> <span class="s1">&#39;</span><span class="si">{0}</span><span class="s1">:</span><span class="si">{1}</span><span class="s1">&#39;</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">parsed_search_url</span><span class="o">.</span><span class="n">scheme</span> <span class="ow">or</span> <span class="s1">&#39;http&#39;</span><span class="p">,</span> <span class="n">url</span><span class="p">)</span>
  240. <span class="k">elif</span> <span class="n">url</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">):</span>
  241. <span class="c1"># fix relative url to the search engine</span>
  242. <span class="n">url</span> <span class="o">=</span> <span class="n">urljoin</span><span class="p">(</span><span class="n">base_url</span><span class="p">,</span> <span class="n">url</span><span class="p">)</span>
  243. <span class="c1"># fix relative urls that fall through the crack</span>
  244. <span class="k">if</span> <span class="s1">&#39;://&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">url</span><span class="p">:</span>
  245. <span class="n">url</span> <span class="o">=</span> <span class="n">urljoin</span><span class="p">(</span><span class="n">base_url</span><span class="p">,</span> <span class="n">url</span><span class="p">)</span>
  246. <span class="n">parsed_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
  247. <span class="c1"># add a / at this end of the url if there is no path</span>
  248. <span class="k">if</span> <span class="ow">not</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span><span class="p">:</span>
  249. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Cannot parse url&#39;</span><span class="p">)</span>
  250. <span class="k">if</span> <span class="ow">not</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="p">:</span>
  251. <span class="n">url</span> <span class="o">+=</span> <span class="s1">&#39;/&#39;</span>
  252. <span class="k">return</span> <span class="n">url</span></div>
  253. <div class="viewcode-block" id="extract_url">
  254. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.extract_url">[docs]</a>
  255. <span class="k">def</span><span class="w"> </span><span class="nf">extract_url</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">,</span> <span class="n">base_url</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  256. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Extract and normalize URL from lxml Element</span>
  257. <span class="sd"> Args:</span>
  258. <span class="sd"> * xpath_results (Union[List[html.HtmlElement], html.HtmlElement]): lxml Element(s)</span>
  259. <span class="sd"> * base_url (str): Base URL</span>
  260. <span class="sd"> Example:</span>
  261. <span class="sd"> &gt;&gt;&gt; def f(s, search_url):</span>
  262. <span class="sd"> &gt;&gt;&gt; return searx.utils.extract_url(html.fromstring(s), search_url)</span>
  263. <span class="sd"> &gt;&gt;&gt; f(&#39;&lt;span id=&quot;42&quot;&gt;https://example.com&lt;/span&gt;&#39;, &#39;http://example.com/&#39;)</span>
  264. <span class="sd"> &#39;https://example.com/&#39;</span>
  265. <span class="sd"> &gt;&gt;&gt; f(&#39;https://example.com&#39;, &#39;http://example.com/&#39;)</span>
  266. <span class="sd"> &#39;https://example.com/&#39;</span>
  267. <span class="sd"> &gt;&gt;&gt; f(&#39;//example.com&#39;, &#39;http://example.com/&#39;)</span>
  268. <span class="sd"> &#39;http://example.com/&#39;</span>
  269. <span class="sd"> &gt;&gt;&gt; f(&#39;//example.com&#39;, &#39;https://example.com/&#39;)</span>
  270. <span class="sd"> &#39;https://example.com/&#39;</span>
  271. <span class="sd"> &gt;&gt;&gt; f(&#39;/path?a=1&#39;, &#39;https://example.com&#39;)</span>
  272. <span class="sd"> &#39;https://example.com/path?a=1&#39;</span>
  273. <span class="sd"> &gt;&gt;&gt; f(&#39;&#39;, &#39;https://example.com&#39;)</span>
  274. <span class="sd"> raise lxml.etree.ParserError</span>
  275. <span class="sd"> &gt;&gt;&gt; searx.utils.extract_url([], &#39;https://example.com&#39;)</span>
  276. <span class="sd"> raise ValueError</span>
  277. <span class="sd"> Raises:</span>
  278. <span class="sd"> * ValueError</span>
  279. <span class="sd"> * lxml.etree.ParserError</span>
  280. <span class="sd"> Returns:</span>
  281. <span class="sd"> * str: normalized URL</span>
  282. <span class="sd"> &quot;&quot;&quot;</span>
  283. <span class="k">if</span> <span class="n">xpath_results</span> <span class="o">==</span> <span class="p">[]:</span>
  284. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Empty url resultset&#39;</span><span class="p">)</span>
  285. <span class="n">url</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">xpath_results</span><span class="p">)</span>
  286. <span class="k">if</span> <span class="n">url</span><span class="p">:</span>
  287. <span class="k">return</span> <span class="n">normalize_url</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">base_url</span><span class="p">)</span>
  288. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;URL not found&#39;</span><span class="p">)</span></div>
  289. <div class="viewcode-block" id="dict_subset">
  290. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.dict_subset">[docs]</a>
  291. <span class="k">def</span><span class="w"> </span><span class="nf">dict_subset</span><span class="p">(</span><span class="n">dictionary</span><span class="p">:</span> <span class="n">MutableMapping</span><span class="p">,</span> <span class="n">properties</span><span class="p">:</span> <span class="n">Set</span><span class="p">[</span><span class="nb">str</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">Dict</span><span class="p">:</span>
  292. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Extract a subset of a dict</span>
  293. <span class="sd"> Examples:</span>
  294. <span class="sd"> &gt;&gt;&gt; dict_subset({&#39;A&#39;: &#39;a&#39;, &#39;B&#39;: &#39;b&#39;, &#39;C&#39;: &#39;c&#39;}, [&#39;A&#39;, &#39;C&#39;])</span>
  295. <span class="sd"> {&#39;A&#39;: &#39;a&#39;, &#39;C&#39;: &#39;c&#39;}</span>
  296. <span class="sd"> &gt;&gt;&gt; &gt;&gt; dict_subset({&#39;A&#39;: &#39;a&#39;, &#39;B&#39;: &#39;b&#39;, &#39;C&#39;: &#39;c&#39;}, [&#39;A&#39;, &#39;D&#39;])</span>
  297. <span class="sd"> {&#39;A&#39;: &#39;a&#39;}</span>
  298. <span class="sd"> &quot;&quot;&quot;</span>
  299. <span class="k">return</span> <span class="p">{</span><span class="n">k</span><span class="p">:</span> <span class="n">dictionary</span><span class="p">[</span><span class="n">k</span><span class="p">]</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">properties</span> <span class="k">if</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">dictionary</span><span class="p">}</span></div>
  300. <div class="viewcode-block" id="humanize_bytes">
  301. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.humanize_bytes">[docs]</a>
  302. <span class="k">def</span><span class="w"> </span><span class="nf">humanize_bytes</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">precision</span><span class="o">=</span><span class="mi">2</span><span class="p">):</span>
  303. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Determine the *human readable* value of bytes on 1024 base (1KB=1024B).&quot;&quot;&quot;</span>
  304. <span class="n">s</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;B &#39;</span><span class="p">,</span> <span class="s1">&#39;KB&#39;</span><span class="p">,</span> <span class="s1">&#39;MB&#39;</span><span class="p">,</span> <span class="s1">&#39;GB&#39;</span><span class="p">,</span> <span class="s1">&#39;TB&#39;</span><span class="p">]</span>
  305. <span class="n">x</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="p">)</span>
  306. <span class="n">p</span> <span class="o">=</span> <span class="mi">0</span>
  307. <span class="k">while</span> <span class="n">size</span> <span class="o">&gt;</span> <span class="mi">1024</span> <span class="ow">and</span> <span class="n">p</span> <span class="o">&lt;</span> <span class="n">x</span><span class="p">:</span>
  308. <span class="n">p</span> <span class="o">+=</span> <span class="mi">1</span>
  309. <span class="n">size</span> <span class="o">=</span> <span class="n">size</span> <span class="o">/</span> <span class="mf">1024.0</span>
  310. <span class="k">return</span> <span class="s2">&quot;</span><span class="si">%.*f</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">precision</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">s</span><span class="p">[</span><span class="n">p</span><span class="p">])</span></div>
  311. <div class="viewcode-block" id="humanize_number">
  312. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.humanize_number">[docs]</a>
  313. <span class="k">def</span><span class="w"> </span><span class="nf">humanize_number</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="n">precision</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
  314. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Determine the *human readable* value of a decimal number.&quot;&quot;&quot;</span>
  315. <span class="n">s</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;&#39;</span><span class="p">,</span> <span class="s1">&#39;K&#39;</span><span class="p">,</span> <span class="s1">&#39;M&#39;</span><span class="p">,</span> <span class="s1">&#39;B&#39;</span><span class="p">,</span> <span class="s1">&#39;T&#39;</span><span class="p">]</span>
  316. <span class="n">x</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">s</span><span class="p">)</span>
  317. <span class="n">p</span> <span class="o">=</span> <span class="mi">0</span>
  318. <span class="k">while</span> <span class="n">size</span> <span class="o">&gt;</span> <span class="mi">1000</span> <span class="ow">and</span> <span class="n">p</span> <span class="o">&lt;</span> <span class="n">x</span><span class="p">:</span>
  319. <span class="n">p</span> <span class="o">+=</span> <span class="mi">1</span>
  320. <span class="n">size</span> <span class="o">=</span> <span class="n">size</span> <span class="o">/</span> <span class="mf">1000.0</span>
  321. <span class="k">return</span> <span class="s2">&quot;</span><span class="si">%.*f%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">precision</span><span class="p">,</span> <span class="n">size</span><span class="p">,</span> <span class="n">s</span><span class="p">[</span><span class="n">p</span><span class="p">])</span></div>
  322. <div class="viewcode-block" id="convert_str_to_int">
  323. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.convert_str_to_int">[docs]</a>
  324. <span class="k">def</span><span class="w"> </span><span class="nf">convert_str_to_int</span><span class="p">(</span><span class="n">number_str</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
  325. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Convert number_str to int or 0 if number_str is not a number.&quot;&quot;&quot;</span>
  326. <span class="k">if</span> <span class="n">number_str</span><span class="o">.</span><span class="n">isdigit</span><span class="p">():</span>
  327. <span class="k">return</span> <span class="nb">int</span><span class="p">(</span><span class="n">number_str</span><span class="p">)</span>
  328. <span class="k">return</span> <span class="mi">0</span></div>
  329. <div class="viewcode-block" id="extr">
  330. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.extr">[docs]</a>
  331. <span class="k">def</span><span class="w"> </span><span class="nf">extr</span><span class="p">(</span><span class="n">txt</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">begin</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">end</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">default</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span><span class="p">):</span>
  332. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Extract the string between ``begin`` and ``end`` from ``txt``</span>
  333. <span class="sd"> :param txt: String to search in</span>
  334. <span class="sd"> :param begin: First string to be searched for</span>
  335. <span class="sd"> :param end: Second string to be searched for after ``begin``</span>
  336. <span class="sd"> :param default: Default value if one of ``begin`` or ``end`` is not</span>
  337. <span class="sd"> found. Defaults to an empty string.</span>
  338. <span class="sd"> :return: The string between the two search-strings ``begin`` and ``end``.</span>
  339. <span class="sd"> If at least one of ``begin`` or ``end`` is not found, the value of</span>
  340. <span class="sd"> ``default`` is returned.</span>
  341. <span class="sd"> Examples:</span>
  342. <span class="sd"> &gt;&gt;&gt; extr(&quot;abcde&quot;, &quot;a&quot;, &quot;e&quot;)</span>
  343. <span class="sd"> &quot;bcd&quot;</span>
  344. <span class="sd"> &gt;&gt;&gt; extr(&quot;abcde&quot;, &quot;a&quot;, &quot;z&quot;, deafult=&quot;nothing&quot;)</span>
  345. <span class="sd"> &quot;nothing&quot;</span>
  346. <span class="sd"> &quot;&quot;&quot;</span>
  347. <span class="c1"># From https://github.com/mikf/gallery-dl/blob/master/gallery_dl/text.py#L129</span>
  348. <span class="k">try</span><span class="p">:</span>
  349. <span class="n">first</span> <span class="o">=</span> <span class="n">txt</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="n">begin</span><span class="p">)</span> <span class="o">+</span> <span class="nb">len</span><span class="p">(</span><span class="n">begin</span><span class="p">)</span>
  350. <span class="k">return</span> <span class="n">txt</span><span class="p">[</span><span class="n">first</span> <span class="p">:</span> <span class="n">txt</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="n">end</span><span class="p">,</span> <span class="n">first</span><span class="p">)]</span>
  351. <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span>
  352. <span class="k">return</span> <span class="n">default</span></div>
  353. <div class="viewcode-block" id="int_or_zero">
  354. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.int_or_zero">[docs]</a>
  355. <span class="k">def</span><span class="w"> </span><span class="nf">int_or_zero</span><span class="p">(</span><span class="n">num</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">],</span> <span class="nb">str</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
  356. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Convert num to int or 0. num can be either a str or a list.</span>
  357. <span class="sd"> If num is a list, the first element is converted to int (or return 0 if the list is empty).</span>
  358. <span class="sd"> If num is a str, see convert_str_to_int</span>
  359. <span class="sd"> &quot;&quot;&quot;</span>
  360. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">num</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
  361. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">num</span><span class="p">)</span> <span class="o">&lt;</span> <span class="mi">1</span><span class="p">:</span>
  362. <span class="k">return</span> <span class="mi">0</span>
  363. <span class="n">num</span> <span class="o">=</span> <span class="n">num</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
  364. <span class="k">return</span> <span class="n">convert_str_to_int</span><span class="p">(</span><span class="n">num</span><span class="p">)</span></div>
  365. <div class="viewcode-block" id="is_valid_lang">
  366. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.is_valid_lang">[docs]</a>
  367. <span class="k">def</span><span class="w"> </span><span class="nf">is_valid_lang</span><span class="p">(</span><span class="n">lang</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="nb">bool</span><span class="p">,</span> <span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">]]:</span>
  368. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Return language code and name if lang describe a language.</span>
  369. <span class="sd"> Examples:</span>
  370. <span class="sd"> &gt;&gt;&gt; is_valid_lang(&#39;zz&#39;)</span>
  371. <span class="sd"> None</span>
  372. <span class="sd"> &gt;&gt;&gt; is_valid_lang(&#39;uk&#39;)</span>
  373. <span class="sd"> (True, &#39;uk&#39;, &#39;ukrainian&#39;)</span>
  374. <span class="sd"> &gt;&gt;&gt; is_valid_lang(b&#39;uk&#39;)</span>
  375. <span class="sd"> (True, &#39;uk&#39;, &#39;ukrainian&#39;)</span>
  376. <span class="sd"> &gt;&gt;&gt; is_valid_lang(&#39;en&#39;)</span>
  377. <span class="sd"> (True, &#39;en&#39;, &#39;english&#39;)</span>
  378. <span class="sd"> &gt;&gt;&gt; searx.utils.is_valid_lang(&#39;Español&#39;)</span>
  379. <span class="sd"> (True, &#39;es&#39;, &#39;spanish&#39;)</span>
  380. <span class="sd"> &gt;&gt;&gt; searx.utils.is_valid_lang(&#39;Spanish&#39;)</span>
  381. <span class="sd"> (True, &#39;es&#39;, &#39;spanish&#39;)</span>
  382. <span class="sd"> &quot;&quot;&quot;</span>
  383. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">lang</span><span class="p">,</span> <span class="nb">bytes</span><span class="p">):</span>
  384. <span class="n">lang</span> <span class="o">=</span> <span class="n">lang</span><span class="o">.</span><span class="n">decode</span><span class="p">()</span>
  385. <span class="n">is_abbr</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">lang</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span>
  386. <span class="n">lang</span> <span class="o">=</span> <span class="n">lang</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
  387. <span class="k">if</span> <span class="n">is_abbr</span><span class="p">:</span>
  388. <span class="k">for</span> <span class="n">l</span> <span class="ow">in</span> <span class="n">sxng_locales</span><span class="p">:</span>
  389. <span class="k">if</span> <span class="n">l</span><span class="p">[</span><span class="mi">0</span><span class="p">][:</span><span class="mi">2</span><span class="p">]</span> <span class="o">==</span> <span class="n">lang</span><span class="p">:</span>
  390. <span class="k">return</span> <span class="p">(</span><span class="kc">True</span><span class="p">,</span> <span class="n">l</span><span class="p">[</span><span class="mi">0</span><span class="p">][:</span><span class="mi">2</span><span class="p">],</span> <span class="n">l</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">())</span>
  391. <span class="k">return</span> <span class="kc">None</span>
  392. <span class="k">for</span> <span class="n">l</span> <span class="ow">in</span> <span class="n">sxng_locales</span><span class="p">:</span>
  393. <span class="k">if</span> <span class="n">l</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="n">lang</span> <span class="ow">or</span> <span class="n">l</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span> <span class="o">==</span> <span class="n">lang</span><span class="p">:</span>
  394. <span class="k">return</span> <span class="p">(</span><span class="kc">True</span><span class="p">,</span> <span class="n">l</span><span class="p">[</span><span class="mi">0</span><span class="p">][:</span><span class="mi">2</span><span class="p">],</span> <span class="n">l</span><span class="p">[</span><span class="mi">3</span><span class="p">]</span><span class="o">.</span><span class="n">lower</span><span class="p">())</span>
  395. <span class="k">return</span> <span class="kc">None</span></div>
  396. <span class="k">def</span><span class="w"> </span><span class="nf">load_module</span><span class="p">(</span><span class="n">filename</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">module_dir</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">types</span><span class="o">.</span><span class="n">ModuleType</span><span class="p">:</span>
  397. <span class="n">modname</span> <span class="o">=</span> <span class="n">splitext</span><span class="p">(</span><span class="n">filename</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
  398. <span class="n">modpath</span> <span class="o">=</span> <span class="n">join</span><span class="p">(</span><span class="n">module_dir</span><span class="p">,</span> <span class="n">filename</span><span class="p">)</span>
  399. <span class="c1"># and https://docs.python.org/3/library/importlib.html#importing-a-source-file-directly</span>
  400. <span class="n">spec</span> <span class="o">=</span> <span class="n">importlib</span><span class="o">.</span><span class="n">util</span><span class="o">.</span><span class="n">spec_from_file_location</span><span class="p">(</span><span class="n">modname</span><span class="p">,</span> <span class="n">modpath</span><span class="p">)</span>
  401. <span class="k">if</span> <span class="ow">not</span> <span class="n">spec</span><span class="p">:</span>
  402. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Error loading &#39;</span><span class="si">{</span><span class="n">modpath</span><span class="si">}</span><span class="s2">&#39; module&quot;</span><span class="p">)</span>
  403. <span class="n">module</span> <span class="o">=</span> <span class="n">importlib</span><span class="o">.</span><span class="n">util</span><span class="o">.</span><span class="n">module_from_spec</span><span class="p">(</span><span class="n">spec</span><span class="p">)</span>
  404. <span class="k">if</span> <span class="ow">not</span> <span class="n">spec</span><span class="o">.</span><span class="n">loader</span><span class="p">:</span>
  405. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="sa">f</span><span class="s2">&quot;Error loading &#39;</span><span class="si">{</span><span class="n">modpath</span><span class="si">}</span><span class="s2">&#39; module&quot;</span><span class="p">)</span>
  406. <span class="n">spec</span><span class="o">.</span><span class="n">loader</span><span class="o">.</span><span class="n">exec_module</span><span class="p">(</span><span class="n">module</span><span class="p">)</span>
  407. <span class="k">return</span> <span class="n">module</span>
  408. <div class="viewcode-block" id="to_string">
  409. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.to_string">[docs]</a>
  410. <span class="k">def</span><span class="w"> </span><span class="nf">to_string</span><span class="p">(</span><span class="n">obj</span><span class="p">:</span> <span class="n">Any</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  411. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Convert obj to its string representation.&quot;&quot;&quot;</span>
  412. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
  413. <span class="k">return</span> <span class="n">obj</span>
  414. <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="s1">&#39;__str__&#39;</span><span class="p">):</span>
  415. <span class="k">return</span> <span class="nb">str</span><span class="p">(</span><span class="n">obj</span><span class="p">)</span>
  416. <span class="k">return</span> <span class="nb">repr</span><span class="p">(</span><span class="n">obj</span><span class="p">)</span></div>
  417. <div class="viewcode-block" id="ecma_unescape">
  418. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.ecma_unescape">[docs]</a>
  419. <span class="k">def</span><span class="w"> </span><span class="nf">ecma_unescape</span><span class="p">(</span><span class="n">string</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
  420. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Python implementation of the unescape javascript function</span>
  421. <span class="sd"> https://www.ecma-international.org/ecma-262/6.0/#sec-unescape-string</span>
  422. <span class="sd"> https://developer.mozilla.org/fr/docs/Web/JavaScript/Reference/Objets_globaux/unescape</span>
  423. <span class="sd"> Examples:</span>
  424. <span class="sd"> &gt;&gt;&gt; ecma_unescape(&#39;%u5409&#39;)</span>
  425. <span class="sd"> &#39;吉&#39;</span>
  426. <span class="sd"> &gt;&gt;&gt; ecma_unescape(&#39;%20&#39;)</span>
  427. <span class="sd"> &#39; &#39;</span>
  428. <span class="sd"> &gt;&gt;&gt; ecma_unescape(&#39;%F3&#39;)</span>
  429. <span class="sd"> &#39;ó&#39;</span>
  430. <span class="sd"> &quot;&quot;&quot;</span>
  431. <span class="c1"># &quot;%u5409&quot; becomes &quot;吉&quot;</span>
  432. <span class="n">string</span> <span class="o">=</span> <span class="n">_ECMA_UNESCAPE4_RE</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="k">lambda</span> <span class="n">e</span><span class="p">:</span> <span class="nb">chr</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span> <span class="mi">16</span><span class="p">)),</span> <span class="n">string</span><span class="p">)</span>
  433. <span class="c1"># &quot;%20&quot; becomes &quot; &quot;, &quot;%F3&quot; becomes &quot;ó&quot;</span>
  434. <span class="n">string</span> <span class="o">=</span> <span class="n">_ECMA_UNESCAPE2_RE</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="k">lambda</span> <span class="n">e</span><span class="p">:</span> <span class="nb">chr</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span> <span class="mi">16</span><span class="p">)),</span> <span class="n">string</span><span class="p">)</span>
  435. <span class="k">return</span> <span class="n">string</span></div>
  436. <div class="viewcode-block" id="remove_pua_from_str">
  437. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.remove_pua_from_str">[docs]</a>
  438. <span class="k">def</span><span class="w"> </span><span class="nf">remove_pua_from_str</span><span class="p">(</span><span class="n">string</span><span class="p">):</span>
  439. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Removes unicode&#39;s &quot;PRIVATE USE CHARACTER&quot;s (PUA_) from a string.</span>
  440. <span class="sd"> .. _PUA: https://en.wikipedia.org/wiki/Private_Use_Areas</span>
  441. <span class="sd"> &quot;&quot;&quot;</span>
  442. <span class="n">pua_ranges</span> <span class="o">=</span> <span class="p">((</span><span class="mh">0xE000</span><span class="p">,</span> <span class="mh">0xF8FF</span><span class="p">),</span> <span class="p">(</span><span class="mh">0xF0000</span><span class="p">,</span> <span class="mh">0xFFFFD</span><span class="p">),</span> <span class="p">(</span><span class="mh">0x100000</span><span class="p">,</span> <span class="mh">0x10FFFD</span><span class="p">))</span>
  443. <span class="n">s</span> <span class="o">=</span> <span class="p">[]</span>
  444. <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">string</span><span class="p">:</span>
  445. <span class="n">i</span> <span class="o">=</span> <span class="nb">ord</span><span class="p">(</span><span class="n">c</span><span class="p">)</span>
  446. <span class="k">if</span> <span class="nb">any</span><span class="p">(</span><span class="n">a</span> <span class="o">&lt;=</span> <span class="n">i</span> <span class="o">&lt;=</span> <span class="n">b</span> <span class="k">for</span> <span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">)</span> <span class="ow">in</span> <span class="n">pua_ranges</span><span class="p">):</span>
  447. <span class="k">continue</span>
  448. <span class="n">s</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">c</span><span class="p">)</span>
  449. <span class="k">return</span> <span class="s2">&quot;&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">s</span><span class="p">)</span></div>
  450. <span class="k">def</span><span class="w"> </span><span class="nf">get_string_replaces_function</span><span class="p">(</span><span class="n">replaces</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">str</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">Callable</span><span class="p">[[</span><span class="nb">str</span><span class="p">],</span> <span class="nb">str</span><span class="p">]:</span>
  451. <span class="n">rep</span> <span class="o">=</span> <span class="p">{</span><span class="n">re</span><span class="o">.</span><span class="n">escape</span><span class="p">(</span><span class="n">k</span><span class="p">):</span> <span class="n">v</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="n">replaces</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span>
  452. <span class="n">pattern</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span><span class="s2">&quot;|&quot;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">rep</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span>
  453. <span class="k">def</span><span class="w"> </span><span class="nf">func</span><span class="p">(</span><span class="n">text</span><span class="p">):</span>
  454. <span class="k">return</span> <span class="n">pattern</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="k">lambda</span> <span class="n">m</span><span class="p">:</span> <span class="n">rep</span><span class="p">[</span><span class="n">re</span><span class="o">.</span><span class="n">escape</span><span class="p">(</span><span class="n">m</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">0</span><span class="p">))],</span> <span class="n">text</span><span class="p">)</span>
  455. <span class="k">return</span> <span class="n">func</span>
  456. <div class="viewcode-block" id="get_engine_from_settings">
  457. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.get_engine_from_settings">[docs]</a>
  458. <span class="k">def</span><span class="w"> </span><span class="nf">get_engine_from_settings</span><span class="p">(</span><span class="n">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Dict</span><span class="p">:</span>
  459. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Return engine configuration from settings.yml of a given engine name&quot;&quot;&quot;</span>
  460. <span class="k">if</span> <span class="s1">&#39;engines&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">settings</span><span class="p">:</span>
  461. <span class="k">return</span> <span class="p">{}</span>
  462. <span class="k">for</span> <span class="n">engine</span> <span class="ow">in</span> <span class="n">settings</span><span class="p">[</span><span class="s1">&#39;engines&#39;</span><span class="p">]:</span>
  463. <span class="k">if</span> <span class="s1">&#39;name&#39;</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">engine</span><span class="p">:</span>
  464. <span class="k">continue</span>
  465. <span class="k">if</span> <span class="n">name</span> <span class="o">==</span> <span class="n">engine</span><span class="p">[</span><span class="s1">&#39;name&#39;</span><span class="p">]:</span>
  466. <span class="k">return</span> <span class="n">engine</span>
  467. <span class="k">return</span> <span class="p">{}</span></div>
  468. <div class="viewcode-block" id="get_xpath">
  469. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.get_xpath">[docs]</a>
  470. <span class="k">def</span><span class="w"> </span><span class="nf">get_xpath</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">:</span> <span class="n">XPathSpecType</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">XPath</span><span class="p">:</span>
  471. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Return cached compiled XPath</span>
  472. <span class="sd"> There is no thread lock.</span>
  473. <span class="sd"> Worst case scenario, xpath_str is compiled more than one time.</span>
  474. <span class="sd"> Args:</span>
  475. <span class="sd"> * xpath_spec (str|lxml.etree.XPath): XPath as a str or lxml.etree.XPath</span>
  476. <span class="sd"> Returns:</span>
  477. <span class="sd"> * result (bool, float, list, str): Results.</span>
  478. <span class="sd"> Raises:</span>
  479. <span class="sd"> * TypeError: Raise when xpath_spec is neither a str nor a lxml.etree.XPath</span>
  480. <span class="sd"> * SearxXPathSyntaxException: Raise when there is a syntax error in the XPath</span>
  481. <span class="sd"> &quot;&quot;&quot;</span>
  482. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
  483. <span class="n">result</span> <span class="o">=</span> <span class="n">_XPATH_CACHE</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
  484. <span class="k">if</span> <span class="n">result</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  485. <span class="k">try</span><span class="p">:</span>
  486. <span class="n">result</span> <span class="o">=</span> <span class="n">XPath</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">)</span>
  487. <span class="k">except</span> <span class="n">XPathSyntaxError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  488. <span class="k">raise</span> <span class="n">SearxXPathSyntaxException</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">e</span><span class="o">.</span><span class="n">msg</span><span class="p">))</span> <span class="kn">from</span><span class="w"> </span><span class="nn">e</span>
  489. <span class="n">_XPATH_CACHE</span><span class="p">[</span><span class="n">xpath_spec</span><span class="p">]</span> <span class="o">=</span> <span class="n">result</span>
  490. <span class="k">return</span> <span class="n">result</span>
  491. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="n">XPath</span><span class="p">):</span>
  492. <span class="k">return</span> <span class="n">xpath_spec</span>
  493. <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="s1">&#39;xpath_spec must be either a str or a lxml.etree.XPath&#39;</span><span class="p">)</span></div>
  494. <div class="viewcode-block" id="eval_xpath">
  495. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.eval_xpath">[docs]</a>
  496. <span class="k">def</span><span class="w"> </span><span class="nf">eval_xpath</span><span class="p">(</span><span class="n">element</span><span class="p">:</span> <span class="n">ElementBase</span><span class="p">,</span> <span class="n">xpath_spec</span><span class="p">:</span> <span class="n">XPathSpecType</span><span class="p">):</span>
  497. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Equivalent of element.xpath(xpath_str) but compile xpath_str once for all.</span>
  498. <span class="sd"> See https://lxml.de/xpathxslt.html#xpath-return-values</span>
  499. <span class="sd"> Args:</span>
  500. <span class="sd"> * element (ElementBase): [description]</span>
  501. <span class="sd"> * xpath_spec (str|lxml.etree.XPath): XPath as a str or lxml.etree.XPath</span>
  502. <span class="sd"> Returns:</span>
  503. <span class="sd"> * result (bool, float, list, str): Results.</span>
  504. <span class="sd"> Raises:</span>
  505. <span class="sd"> * TypeError: Raise when xpath_spec is neither a str nor a lxml.etree.XPath</span>
  506. <span class="sd"> * SearxXPathSyntaxException: Raise when there is a syntax error in the XPath</span>
  507. <span class="sd"> * SearxEngineXPathException: Raise when the XPath can&#39;t be evaluated.</span>
  508. <span class="sd"> &quot;&quot;&quot;</span>
  509. <span class="n">xpath</span> <span class="o">=</span> <span class="n">get_xpath</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">)</span>
  510. <span class="k">try</span><span class="p">:</span>
  511. <span class="k">return</span> <span class="n">xpath</span><span class="p">(</span><span class="n">element</span><span class="p">)</span>
  512. <span class="k">except</span> <span class="n">XPathError</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
  513. <span class="n">arg</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">str</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">e</span><span class="o">.</span><span class="n">args</span><span class="p">])</span>
  514. <span class="k">raise</span> <span class="n">SearxEngineXPathException</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="n">arg</span><span class="p">)</span> <span class="kn">from</span><span class="w"> </span><span class="nn">e</span></div>
  515. <div class="viewcode-block" id="eval_xpath_list">
  516. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.eval_xpath_list">[docs]</a>
  517. <span class="k">def</span><span class="w"> </span><span class="nf">eval_xpath_list</span><span class="p">(</span><span class="n">element</span><span class="p">:</span> <span class="n">ElementBase</span><span class="p">,</span> <span class="n">xpath_spec</span><span class="p">:</span> <span class="n">XPathSpecType</span><span class="p">,</span> <span class="n">min_len</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
  518. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Same as eval_xpath, check if the result is a list</span>
  519. <span class="sd"> Args:</span>
  520. <span class="sd"> * element (ElementBase): [description]</span>
  521. <span class="sd"> * xpath_spec (str|lxml.etree.XPath): XPath as a str or lxml.etree.XPath</span>
  522. <span class="sd"> * min_len (int, optional): [description]. Defaults to None.</span>
  523. <span class="sd"> Raises:</span>
  524. <span class="sd"> * TypeError: Raise when xpath_spec is neither a str nor a lxml.etree.XPath</span>
  525. <span class="sd"> * SearxXPathSyntaxException: Raise when there is a syntax error in the XPath</span>
  526. <span class="sd"> * SearxEngineXPathException: raise if the result is not a list</span>
  527. <span class="sd"> Returns:</span>
  528. <span class="sd"> * result (bool, float, list, str): Results.</span>
  529. <span class="sd"> &quot;&quot;&quot;</span>
  530. <span class="n">result</span> <span class="o">=</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">element</span><span class="p">,</span> <span class="n">xpath_spec</span><span class="p">)</span>
  531. <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
  532. <span class="k">raise</span> <span class="n">SearxEngineXPathException</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="s1">&#39;the result is not a list&#39;</span><span class="p">)</span>
  533. <span class="k">if</span> <span class="n">min_len</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">min_len</span> <span class="o">&gt;</span> <span class="nb">len</span><span class="p">(</span><span class="n">result</span><span class="p">):</span>
  534. <span class="k">raise</span> <span class="n">SearxEngineXPathException</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="s1">&#39;len(xpath_str) &lt; &#39;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">min_len</span><span class="p">))</span>
  535. <span class="k">return</span> <span class="n">result</span></div>
  536. <div class="viewcode-block" id="eval_xpath_getindex">
  537. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.eval_xpath_getindex">[docs]</a>
  538. <span class="k">def</span><span class="w"> </span><span class="nf">eval_xpath_getindex</span><span class="p">(</span><span class="n">elements</span><span class="p">:</span> <span class="n">ElementBase</span><span class="p">,</span> <span class="n">xpath_spec</span><span class="p">:</span> <span class="n">XPathSpecType</span><span class="p">,</span> <span class="n">index</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="n">_NOTSET</span><span class="p">):</span>
  539. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Call eval_xpath_list then get one element using the index parameter.</span>
  540. <span class="sd"> If the index does not exist, either raise an exception is default is not set,</span>
  541. <span class="sd"> other return the default value (can be None).</span>
  542. <span class="sd"> Args:</span>
  543. <span class="sd"> * elements (ElementBase): lxml element to apply the xpath.</span>
  544. <span class="sd"> * xpath_spec (str|lxml.etree.XPath): XPath as a str or lxml.etree.XPath.</span>
  545. <span class="sd"> * index (int): index to get</span>
  546. <span class="sd"> * default (Object, optional): Defaults if index doesn&#39;t exist.</span>
  547. <span class="sd"> Raises:</span>
  548. <span class="sd"> * TypeError: Raise when xpath_spec is neither a str nor a lxml.etree.XPath</span>
  549. <span class="sd"> * SearxXPathSyntaxException: Raise when there is a syntax error in the XPath</span>
  550. <span class="sd"> * SearxEngineXPathException: if the index is not found. Also see eval_xpath.</span>
  551. <span class="sd"> Returns:</span>
  552. <span class="sd"> * result (bool, float, list, str): Results.</span>
  553. <span class="sd"> &quot;&quot;&quot;</span>
  554. <span class="n">result</span> <span class="o">=</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">elements</span><span class="p">,</span> <span class="n">xpath_spec</span><span class="p">)</span>
  555. <span class="k">if</span> <span class="o">-</span><span class="nb">len</span><span class="p">(</span><span class="n">result</span><span class="p">)</span> <span class="o">&lt;=</span> <span class="n">index</span> <span class="o">&lt;</span> <span class="nb">len</span><span class="p">(</span><span class="n">result</span><span class="p">):</span>
  556. <span class="k">return</span> <span class="n">result</span><span class="p">[</span><span class="n">index</span><span class="p">]</span>
  557. <span class="k">if</span> <span class="n">default</span> <span class="o">==</span> <span class="n">_NOTSET</span><span class="p">:</span>
  558. <span class="c1"># raise an SearxEngineXPathException instead of IndexError</span>
  559. <span class="c1"># to record xpath_spec</span>
  560. <span class="k">raise</span> <span class="n">SearxEngineXPathException</span><span class="p">(</span><span class="n">xpath_spec</span><span class="p">,</span> <span class="s1">&#39;index &#39;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">index</span><span class="p">)</span> <span class="o">+</span> <span class="s1">&#39; not found&#39;</span><span class="p">)</span>
  561. <span class="k">return</span> <span class="n">default</span></div>
  562. <span class="k">def</span><span class="w"> </span><span class="nf">_get_fasttext_model</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="s2">&quot;fasttext.FastText._FastText&quot;</span><span class="p">:</span> <span class="c1"># type: ignore</span>
  563. <span class="k">global</span> <span class="n">_FASTTEXT_MODEL</span> <span class="c1"># pylint: disable=global-statement</span>
  564. <span class="k">if</span> <span class="n">_FASTTEXT_MODEL</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
  565. <span class="kn">import</span><span class="w"> </span><span class="nn">fasttext</span> <span class="c1"># pylint: disable=import-outside-toplevel</span>
  566. <span class="c1"># Monkey patch: prevent fasttext from showing a (useless) warning when loading a model.</span>
  567. <span class="n">fasttext</span><span class="o">.</span><span class="n">FastText</span><span class="o">.</span><span class="n">eprint</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="kc">None</span>
  568. <span class="n">_FASTTEXT_MODEL</span> <span class="o">=</span> <span class="n">fasttext</span><span class="o">.</span><span class="n">load_model</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">data_dir</span> <span class="o">/</span> <span class="s1">&#39;lid.176.ftz&#39;</span><span class="p">))</span>
  569. <span class="k">return</span> <span class="n">_FASTTEXT_MODEL</span>
  570. <div class="viewcode-block" id="get_embeded_stream_url">
  571. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.get_embeded_stream_url">[docs]</a>
  572. <span class="k">def</span><span class="w"> </span><span class="nf">get_embeded_stream_url</span><span class="p">(</span><span class="n">url</span><span class="p">):</span>
  573. <span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
  574. <span class="sd"> Converts a standard video URL into its embed format. Supported services include Youtube,</span>
  575. <span class="sd"> Facebook, Instagram, TikTok, Dailymotion, and Bilibili.</span>
  576. <span class="sd"> &quot;&quot;&quot;</span>
  577. <span class="n">parsed_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
  578. <span class="n">iframe_src</span> <span class="o">=</span> <span class="kc">None</span>
  579. <span class="c1"># YouTube</span>
  580. <span class="k">if</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;www.youtube.com&#39;</span><span class="p">,</span> <span class="s1">&#39;youtube.com&#39;</span><span class="p">]</span> <span class="ow">and</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span> <span class="o">==</span> <span class="s1">&#39;/watch&#39;</span> <span class="ow">and</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">query</span><span class="p">:</span>
  581. <span class="n">video_id</span> <span class="o">=</span> <span class="n">parse_qs</span><span class="p">(</span><span class="n">parsed_url</span><span class="o">.</span><span class="n">query</span><span class="p">)</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;v&#39;</span><span class="p">,</span> <span class="p">[])</span>
  582. <span class="k">if</span> <span class="n">video_id</span><span class="p">:</span>
  583. <span class="n">iframe_src</span> <span class="o">=</span> <span class="s1">&#39;https://www.youtube-nocookie.com/embed/&#39;</span> <span class="o">+</span> <span class="n">video_id</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
  584. <span class="c1"># Facebook</span>
  585. <span class="k">elif</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;www.facebook.com&#39;</span><span class="p">,</span> <span class="s1">&#39;facebook.com&#39;</span><span class="p">]:</span>
  586. <span class="n">encoded_href</span> <span class="o">=</span> <span class="n">urlencode</span><span class="p">({</span><span class="s1">&#39;href&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">})</span>
  587. <span class="n">iframe_src</span> <span class="o">=</span> <span class="s1">&#39;https://www.facebook.com/plugins/video.php?allowfullscreen=true&amp;&#39;</span> <span class="o">+</span> <span class="n">encoded_href</span>
  588. <span class="c1"># Instagram</span>
  589. <span class="k">elif</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;www.instagram.com&#39;</span><span class="p">,</span> <span class="s1">&#39;instagram.com&#39;</span><span class="p">]</span> <span class="ow">and</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;/p/&#39;</span><span class="p">):</span>
  590. <span class="k">if</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">&#39;/&#39;</span><span class="p">):</span>
  591. <span class="n">iframe_src</span> <span class="o">=</span> <span class="n">url</span> <span class="o">+</span> <span class="s1">&#39;embed&#39;</span>
  592. <span class="k">else</span><span class="p">:</span>
  593. <span class="n">iframe_src</span> <span class="o">=</span> <span class="n">url</span> <span class="o">+</span> <span class="s1">&#39;/embed&#39;</span>
  594. <span class="c1"># TikTok</span>
  595. <span class="k">elif</span> <span class="p">(</span>
  596. <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;www.tiktok.com&#39;</span><span class="p">,</span> <span class="s1">&#39;tiktok.com&#39;</span><span class="p">]</span>
  597. <span class="ow">and</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;/@&#39;</span><span class="p">)</span>
  598. <span class="ow">and</span> <span class="s1">&#39;/video/&#39;</span> <span class="ow">in</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span>
  599. <span class="p">):</span>
  600. <span class="n">path_parts</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;/video/&#39;</span><span class="p">)</span>
  601. <span class="n">video_id</span> <span class="o">=</span> <span class="n">path_parts</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span>
  602. <span class="n">iframe_src</span> <span class="o">=</span> <span class="s1">&#39;https://www.tiktok.com/embed/&#39;</span> <span class="o">+</span> <span class="n">video_id</span>
  603. <span class="c1"># Dailymotion</span>
  604. <span class="k">elif</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;www.dailymotion.com&#39;</span><span class="p">,</span> <span class="s1">&#39;dailymotion.com&#39;</span><span class="p">]</span> <span class="ow">and</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;/video/&#39;</span><span class="p">):</span>
  605. <span class="n">path_parts</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;/&#39;</span><span class="p">)</span>
  606. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">path_parts</span><span class="p">)</span> <span class="o">==</span> <span class="mi">3</span><span class="p">:</span>
  607. <span class="n">video_id</span> <span class="o">=</span> <span class="n">path_parts</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
  608. <span class="n">iframe_src</span> <span class="o">=</span> <span class="s1">&#39;https://www.dailymotion.com/embed/video/&#39;</span> <span class="o">+</span> <span class="n">video_id</span>
  609. <span class="c1"># Bilibili</span>
  610. <span class="k">elif</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">&#39;www.bilibili.com&#39;</span><span class="p">,</span> <span class="s1">&#39;bilibili.com&#39;</span><span class="p">]</span> <span class="ow">and</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;/video/&#39;</span><span class="p">):</span>
  611. <span class="n">path_parts</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;/&#39;</span><span class="p">)</span>
  612. <span class="n">video_id</span> <span class="o">=</span> <span class="n">path_parts</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span>
  613. <span class="n">param_key</span> <span class="o">=</span> <span class="kc">None</span>
  614. <span class="k">if</span> <span class="n">video_id</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;av&#39;</span><span class="p">):</span>
  615. <span class="n">video_id</span> <span class="o">=</span> <span class="n">video_id</span><span class="p">[</span><span class="mi">2</span><span class="p">:]</span>
  616. <span class="n">param_key</span> <span class="o">=</span> <span class="s1">&#39;aid&#39;</span>
  617. <span class="k">elif</span> <span class="n">video_id</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">&#39;BV&#39;</span><span class="p">):</span>
  618. <span class="n">param_key</span> <span class="o">=</span> <span class="s1">&#39;bvid&#39;</span>
  619. <span class="n">iframe_src</span> <span class="o">=</span> <span class="p">(</span>
  620. <span class="sa">f</span><span class="s1">&#39;https://player.bilibili.com/player.html?</span><span class="si">{</span><span class="n">param_key</span><span class="si">}</span><span class="s1">=</span><span class="si">{</span><span class="n">video_id</span><span class="si">}</span><span class="s1">&amp;high_quality=1&amp;autoplay=false&amp;danmaku=0&#39;</span>
  621. <span class="p">)</span>
  622. <span class="k">return</span> <span class="n">iframe_src</span></div>
  623. <div class="viewcode-block" id="detect_language">
  624. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.detect_language">[docs]</a>
  625. <span class="k">def</span><span class="w"> </span><span class="nf">detect_language</span><span class="p">(</span><span class="n">text</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">threshold</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.3</span><span class="p">,</span> <span class="n">only_search_languages</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span>
  626. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Detect the language of the ``text`` parameter.</span>
  627. <span class="sd"> :param str text: The string whose language is to be detected.</span>
  628. <span class="sd"> :param float threshold: Threshold filters the returned labels by a threshold</span>
  629. <span class="sd"> on probability. A choice of 0.3 will return labels with at least 0.3</span>
  630. <span class="sd"> probability.</span>
  631. <span class="sd"> :param bool only_search_languages: If ``True``, returns only supported</span>
  632. <span class="sd"> SearXNG search languages. see :py:obj:`searx.languages`</span>
  633. <span class="sd"> :rtype: str, None</span>
  634. <span class="sd"> :returns:</span>
  635. <span class="sd"> The detected language code or ``None``. See below.</span>
  636. <span class="sd"> :raises ValueError: If ``text`` is not a string.</span>
  637. <span class="sd"> The language detection is done by using `a fork`_ of the fastText_ library</span>
  638. <span class="sd"> (`python fasttext`_). fastText_ distributes the `language identification</span>
  639. <span class="sd"> model`_, for reference:</span>
  640. <span class="sd"> - `FastText.zip: Compressing text classification models`_</span>
  641. <span class="sd"> - `Bag of Tricks for Efficient Text Classification`_</span>
  642. <span class="sd"> The `language identification model`_ support the language codes</span>
  643. <span class="sd"> (ISO-639-3)::</span>
  644. <span class="sd"> af als am an ar arz as ast av az azb ba bar bcl be bg bh bn bo bpy br bs</span>
  645. <span class="sd"> bxr ca cbk ce ceb ckb co cs cv cy da de diq dsb dty dv el eml en eo es</span>
  646. <span class="sd"> et eu fa fi fr frr fy ga gd gl gn gom gu gv he hi hif hr hsb ht hu hy ia</span>
  647. <span class="sd"> id ie ilo io is it ja jbo jv ka kk km kn ko krc ku kv kw ky la lb lez li</span>
  648. <span class="sd"> lmo lo lrc lt lv mai mg mhr min mk ml mn mr mrj ms mt mwl my myv mzn nah</span>
  649. <span class="sd"> nap nds ne new nl nn no oc or os pa pam pfl pl pms pnb ps pt qu rm ro ru</span>
  650. <span class="sd"> rue sa sah sc scn sco sd sh si sk sl so sq sr su sv sw ta te tg th tk tl</span>
  651. <span class="sd"> tr tt tyv ug uk ur uz vec vep vi vls vo wa war wuu xal xmf yi yo yue zh</span>
  652. <span class="sd"> By using ``only_search_languages=True`` the `language identification model`_</span>
  653. <span class="sd"> is harmonized with the SearXNG&#39;s language (locale) model. General</span>
  654. <span class="sd"> conditions of SearXNG&#39;s locale model are:</span>
  655. <span class="sd"> a. SearXNG&#39;s locale of a query is passed to the</span>
  656. <span class="sd"> :py:obj:`searx.locales.get_engine_locale` to get a language and/or region</span>
  657. <span class="sd"> code that is used by an engine.</span>
  658. <span class="sd"> b. Most of SearXNG&#39;s engines do not support all the languages from `language</span>
  659. <span class="sd"> identification model`_ and there is also a discrepancy in the ISO-639-3</span>
  660. <span class="sd"> (fasttext) and ISO-639-2 (SearXNG)handling. Further more, in SearXNG the</span>
  661. <span class="sd"> locales like ``zh-TH`` (``zh-CN``) are mapped to ``zh_Hant``</span>
  662. <span class="sd"> (``zh_Hans``) while the `language identification model`_ reduce both to</span>
  663. <span class="sd"> ``zh``.</span>
  664. <span class="sd"> .. _a fork: https://github.com/searxng/fasttext-predict</span>
  665. <span class="sd"> .. _fastText: https://fasttext.cc/</span>
  666. <span class="sd"> .. _python fasttext: https://pypi.org/project/fasttext/</span>
  667. <span class="sd"> .. _language identification model: https://fasttext.cc/docs/en/language-identification.html</span>
  668. <span class="sd"> .. _Bag of Tricks for Efficient Text Classification: https://arxiv.org/abs/1607.01759</span>
  669. <span class="sd"> .. _`FastText.zip: Compressing text classification models`: https://arxiv.org/abs/1612.03651</span>
  670. <span class="sd"> &quot;&quot;&quot;</span>
  671. <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">text</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
  672. <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;text must a str&#39;</span><span class="p">)</span>
  673. <span class="n">r</span> <span class="o">=</span> <span class="n">_get_fasttext_model</span><span class="p">()</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">text</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;</span><span class="se">\n</span><span class="s1">&#39;</span><span class="p">,</span> <span class="s1">&#39; &#39;</span><span class="p">),</span> <span class="n">k</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">threshold</span><span class="o">=</span><span class="n">threshold</span><span class="p">)</span>
  674. <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">r</span><span class="p">,</span> <span class="nb">tuple</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">r</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">r</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
  675. <span class="n">language</span> <span class="o">=</span> <span class="n">r</span><span class="p">[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">&#39;__label__&#39;</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
  676. <span class="k">if</span> <span class="n">only_search_languages</span> <span class="ow">and</span> <span class="n">language</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">SEARCH_LANGUAGE_CODES</span><span class="p">:</span>
  677. <span class="k">return</span> <span class="kc">None</span>
  678. <span class="k">return</span> <span class="n">language</span>
  679. <span class="k">return</span> <span class="kc">None</span></div>
  680. <div class="viewcode-block" id="js_variable_to_python">
  681. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.js_variable_to_python">[docs]</a>
  682. <span class="k">def</span><span class="w"> </span><span class="nf">js_variable_to_python</span><span class="p">(</span><span class="n">js_variable</span><span class="p">):</span>
  683. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Convert a javascript variable into JSON and then load the value</span>
  684. <span class="sd"> It does not deal with all cases, but it is good enough for now.</span>
  685. <span class="sd"> chompjs has a better implementation.</span>
  686. <span class="sd"> &quot;&quot;&quot;</span>
  687. <span class="c1"># when in_string is not None, it contains the character that has opened the string</span>
  688. <span class="c1"># either simple quote or double quote</span>
  689. <span class="n">in_string</span> <span class="o">=</span> <span class="kc">None</span>
  690. <span class="c1"># cut the string:</span>
  691. <span class="c1"># r&quot;&quot;&quot;{ a:&quot;f\&quot;irst&quot;, c:&#39;sec&quot;ond&#39;}&quot;&quot;&quot;</span>
  692. <span class="c1"># becomes</span>
  693. <span class="c1"># [&#39;{ a:&#39;, &#39;&quot;&#39;, &#39;f\\&#39;, &#39;&quot;&#39;, &#39;irst&#39;, &#39;&quot;&#39;, &#39;, c:&#39;, &quot;&#39;&quot;, &#39;sec&#39;, &#39;&quot;&#39;, &#39;ond&#39;, &quot;&#39;&quot;, &#39;}&#39;]</span>
  694. <span class="n">parts</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;([&quot;</span><span class="se">\&#39;</span><span class="s1">])&#39;</span><span class="p">,</span> <span class="n">js_variable</span><span class="p">)</span>
  695. <span class="c1"># previous part (to check the escape character antislash)</span>
  696. <span class="n">previous_p</span> <span class="o">=</span> <span class="s2">&quot;&quot;</span>
  697. <span class="k">for</span> <span class="n">i</span><span class="p">,</span> <span class="n">p</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">parts</span><span class="p">):</span>
  698. <span class="c1"># parse characters inside a ECMA string</span>
  699. <span class="k">if</span> <span class="n">in_string</span><span class="p">:</span>
  700. <span class="c1"># we are in a JS string: replace the colon by a temporary character</span>
  701. <span class="c1"># so quote_keys_regex doesn&#39;t have to deal with colon inside the JS strings</span>
  702. <span class="n">parts</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">parts</span><span class="p">[</span><span class="n">i</span><span class="p">]</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="nb">chr</span><span class="p">(</span><span class="mi">1</span><span class="p">))</span>
  703. <span class="k">if</span> <span class="n">in_string</span> <span class="o">==</span> <span class="s2">&quot;&#39;&quot;</span><span class="p">:</span>
  704. <span class="c1"># the JS string is delimited by simple quote.</span>
  705. <span class="c1"># This is not supported by JSON.</span>
  706. <span class="c1"># simple quote delimited string are converted to double quote delimited string</span>
  707. <span class="c1"># here, inside a JS string, we escape the double quote</span>
  708. <span class="n">parts</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">parts</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">&#39;&quot;&#39;</span><span class="p">,</span> <span class="sa">r</span><span class="s1">&#39;\&quot;&#39;</span><span class="p">)</span>
  709. <span class="c1"># deal with delimiters and escape character</span>
  710. <span class="k">if</span> <span class="ow">not</span> <span class="n">in_string</span> <span class="ow">and</span> <span class="n">p</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">&#39;&quot;&#39;</span><span class="p">,</span> <span class="s2">&quot;&#39;&quot;</span><span class="p">):</span>
  711. <span class="c1"># we are not in string</span>
  712. <span class="c1"># but p is double or simple quote</span>
  713. <span class="c1"># that&#39;s the start of a new string</span>
  714. <span class="c1"># replace simple quote by double quote</span>
  715. <span class="c1"># (JSON doesn&#39;t support simple quote)</span>
  716. <span class="n">parts</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;&quot;&#39;</span>
  717. <span class="n">in_string</span> <span class="o">=</span> <span class="n">p</span>
  718. <span class="k">continue</span>
  719. <span class="k">if</span> <span class="n">p</span> <span class="o">==</span> <span class="n">in_string</span><span class="p">:</span>
  720. <span class="c1"># we are in a string and the current part MAY close the string</span>
  721. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">previous_p</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">previous_p</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;</span><span class="se">\\</span><span class="s1">&#39;</span><span class="p">:</span>
  722. <span class="c1"># there is an antislash just before: the ECMA string continue</span>
  723. <span class="k">continue</span>
  724. <span class="c1"># the current p close the string</span>
  725. <span class="c1"># replace simple quote by double quote</span>
  726. <span class="n">parts</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="s1">&#39;&quot;&#39;</span>
  727. <span class="n">in_string</span> <span class="o">=</span> <span class="kc">None</span>
  728. <span class="k">if</span> <span class="ow">not</span> <span class="n">in_string</span><span class="p">:</span>
  729. <span class="c1"># replace void 0 by null</span>
  730. <span class="c1"># https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/void</span>
  731. <span class="c1"># we are sure there is no string in p</span>
  732. <span class="n">parts</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="n">_JS_VOID_RE</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="s2">&quot;null&quot;</span><span class="p">,</span> <span class="n">p</span><span class="p">)</span>
  733. <span class="c1"># update previous_p</span>
  734. <span class="n">previous_p</span> <span class="o">=</span> <span class="n">p</span>
  735. <span class="c1"># join the string</span>
  736. <span class="n">s</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">parts</span><span class="p">)</span>
  737. <span class="c1"># add quote around the key</span>
  738. <span class="c1"># { a: 12 }</span>
  739. <span class="c1"># becomes</span>
  740. <span class="c1"># { &quot;a&quot;: 12 }</span>
  741. <span class="n">s</span> <span class="o">=</span> <span class="n">_JS_QUOTE_KEYS_RE</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s1">&#39;\1&quot;\2&quot;\3&#39;</span><span class="p">,</span> <span class="n">s</span><span class="p">)</span>
  742. <span class="n">s</span> <span class="o">=</span> <span class="n">_JS_DECIMAL_RE</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="s2">&quot;:0.&quot;</span><span class="p">,</span> <span class="n">s</span><span class="p">)</span>
  743. <span class="c1"># replace the surogate character by colon</span>
  744. <span class="n">s</span> <span class="o">=</span> <span class="n">s</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="nb">chr</span><span class="p">(</span><span class="mi">1</span><span class="p">),</span> <span class="s1">&#39;:&#39;</span><span class="p">)</span>
  745. <span class="c1"># load the JSON and return the result</span>
  746. <span class="k">return</span> <span class="n">json</span><span class="o">.</span><span class="n">loads</span><span class="p">(</span><span class="n">s</span><span class="p">)</span></div>
  747. <div class="viewcode-block" id="parse_duration_string">
  748. <a class="viewcode-back" href="../../src/searx.utils.html#searx.utils.parse_duration_string">[docs]</a>
  749. <span class="k">def</span><span class="w"> </span><span class="nf">parse_duration_string</span><span class="p">(</span><span class="n">duration_str</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">timedelta</span> <span class="o">|</span> <span class="kc">None</span><span class="p">:</span>
  750. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Parse a time string in format MM:SS or HH:MM:SS and convert it to a `timedelta` object.</span>
  751. <span class="sd"> Returns None if the provided string doesn&#39;t match any of the formats.</span>
  752. <span class="sd"> &quot;&quot;&quot;</span>
  753. <span class="n">duration_str</span> <span class="o">=</span> <span class="n">duration_str</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
  754. <span class="k">if</span> <span class="ow">not</span> <span class="n">duration_str</span><span class="p">:</span>
  755. <span class="k">return</span> <span class="kc">None</span>
  756. <span class="k">try</span><span class="p">:</span>
  757. <span class="c1"># prepending [&quot;00&quot;] here inits hours to 0 if they are not provided</span>
  758. <span class="n">time_parts</span> <span class="o">=</span> <span class="p">([</span><span class="s2">&quot;00&quot;</span><span class="p">]</span> <span class="o">+</span> <span class="n">duration_str</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;:&quot;</span><span class="p">))[:</span><span class="mi">3</span><span class="p">]</span>
  759. <span class="n">hours</span><span class="p">,</span> <span class="n">minutes</span><span class="p">,</span> <span class="n">seconds</span> <span class="o">=</span> <span class="nb">map</span><span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="n">time_parts</span><span class="p">)</span>
  760. <span class="k">return</span> <span class="n">timedelta</span><span class="p">(</span><span class="n">hours</span><span class="o">=</span><span class="n">hours</span><span class="p">,</span> <span class="n">minutes</span><span class="o">=</span><span class="n">minutes</span><span class="p">,</span> <span class="n">seconds</span><span class="o">=</span><span class="n">seconds</span><span class="p">)</span>
  761. <span class="k">except</span> <span class="p">(</span><span class="ne">ValueError</span><span class="p">,</span> <span class="ne">TypeError</span><span class="p">):</span>
  762. <span class="k">pass</span>
  763. <span class="k">return</span> <span class="kc">None</span></div>
  764. </pre></div>
  765. <div class="clearer"></div>
  766. </div>
  767. </div>
  768. </div>
  769. <span id="sidebar-top"></span>
  770. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  771. <div class="sphinxsidebarwrapper">
  772. <p class="logo"><a href="../../index.html">
  773. <img class="logo" src="../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  774. </a></p>
  775. <h3><a href="../../index.html">Table of Contents</a></h3>
  776. <ul>
  777. <li class="toctree-l1"><a class="reference internal" href="../../user/index.html">User information</a></li>
  778. <li class="toctree-l1"><a class="reference internal" href="../../own-instance.html">Why use a private instance?</a></li>
  779. <li class="toctree-l1"><a class="reference internal" href="../../admin/index.html">Administrator documentation</a></li>
  780. <li class="toctree-l1"><a class="reference internal" href="../../dev/index.html">Developer documentation</a></li>
  781. <li class="toctree-l1"><a class="reference internal" href="../../utils/index.html">DevOps tooling box</a></li>
  782. <li class="toctree-l1"><a class="reference internal" href="../../src/index.html">Source-Code</a></li>
  783. </ul>
  784. <h3>Project Links</h3>
  785. <ul>
  786. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  787. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  788. <li><a href="https://searx.space">Public instances</a>
  789. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  790. </ul><h3>Navigation</h3>
  791. <ul>
  792. <li><a href="../../index.html">Overview</a>
  793. <ul>
  794. <li><a href="../index.html">Module code</a>
  795. </ul>
  796. </li>
  797. </ul>
  798. </li>
  799. </ul>
  800. <search id="searchbox" style="display: none" role="search">
  801. <h3 id="searchlabel">Quick search</h3>
  802. <div class="searchformwrapper">
  803. <form class="search" action="../../search.html" method="get">
  804. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  805. <input type="submit" value="Go" />
  806. </form>
  807. </div>
  808. </search>
  809. <script>document.getElementById('searchbox').style.display = "block"</script>
  810. </div>
  811. </div>
  812. <div class="clearer"></div>
  813. </div>
  814. <div class="footer" role="contentinfo">
  815. &#169; Copyright SearXNG team.
  816. </div>
  817. </body>
  818. </html>