xpath.html 34 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447
  1. <!DOCTYPE html>
  2. <html lang="en" data-content_root="../../../">
  3. <head>
  4. <meta charset="utf-8" />
  5. <meta name="viewport" content="width=device-width, initial-scale=1.0" />
  6. <meta name="viewport" content="width=device-width, initial-scale=1">
  7. <title>searx.engines.xpath &#8212; SearXNG Documentation (2025.4.30+fd33559cf)</title>
  8. <link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=6625fa76" />
  9. <link rel="stylesheet" type="text/css" href="../../../_static/searxng.css?v=52e4ff28" />
  10. <script src="../../../_static/documentation_options.js?v=b12b0e12"></script>
  11. <script src="../../../_static/doctools.js?v=9a2dae69"></script>
  12. <script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
  13. <script data-project="searxng" data-version="2025.4.30+fd33559cf" src="../../../_static/describe_version.js?v=fa7f30d0"></script>
  14. <link rel="index" title="Index" href="../../../genindex.html" />
  15. <link rel="search" title="Search" href="../../../search.html" />
  16. </head><body>
  17. <div class="related" role="navigation" aria-label="Related">
  18. <h3>Navigation</h3>
  19. <ul>
  20. <li class="right" style="margin-right: 10px">
  21. <a href="../../../genindex.html" title="General Index"
  22. accesskey="I">index</a></li>
  23. <li class="right" >
  24. <a href="../../../py-modindex.html" title="Python Module Index"
  25. >modules</a> |</li>
  26. <li class="nav-item nav-item-0"><a href="../../../index.html">SearXNG Documentation (2025.4.30+fd33559cf)</a> &#187;</li>
  27. <li class="nav-item nav-item-1"><a href="../../index.html" >Module code</a> &#187;</li>
  28. <li class="nav-item nav-item-2"><a href="../engines.html" accesskey="U">searx.engines</a> &#187;</li>
  29. <li class="nav-item nav-item-this"><a href="">searx.engines.xpath</a></li>
  30. </ul>
  31. </div>
  32. <div class="document">
  33. <div class="documentwrapper">
  34. <div class="bodywrapper">
  35. <div class="body" role="main">
  36. <h1>Source code for searx.engines.xpath</h1><div class="highlight"><pre>
  37. <span></span><span class="c1"># SPDX-License-Identifier: AGPL-3.0-or-later</span>
  38. <span class="sd">&quot;&quot;&quot;The XPath engine is a *generic* engine with which it is possible to configure</span>
  39. <span class="sd">engines in the settings.</span>
  40. <span class="sd">.. _XPath selector: https://quickref.me/xpath.html#xpath-selectors</span>
  41. <span class="sd">Configuration</span>
  42. <span class="sd">=============</span>
  43. <span class="sd">Request:</span>
  44. <span class="sd">- :py:obj:`search_url`</span>
  45. <span class="sd">- :py:obj:`lang_all`</span>
  46. <span class="sd">- :py:obj:`soft_max_redirects`</span>
  47. <span class="sd">- :py:obj:`method`</span>
  48. <span class="sd">- :py:obj:`request_body`</span>
  49. <span class="sd">- :py:obj:`cookies`</span>
  50. <span class="sd">- :py:obj:`headers`</span>
  51. <span class="sd">Paging:</span>
  52. <span class="sd">- :py:obj:`paging`</span>
  53. <span class="sd">- :py:obj:`page_size`</span>
  54. <span class="sd">- :py:obj:`first_page_num`</span>
  55. <span class="sd">Time Range:</span>
  56. <span class="sd">- :py:obj:`time_range_support`</span>
  57. <span class="sd">- :py:obj:`time_range_url`</span>
  58. <span class="sd">- :py:obj:`time_range_map`</span>
  59. <span class="sd">Safe-Search:</span>
  60. <span class="sd">- :py:obj:`safe_search_support`</span>
  61. <span class="sd">- :py:obj:`safe_search_map`</span>
  62. <span class="sd">Response:</span>
  63. <span class="sd">- :py:obj:`no_result_for_http_status`</span>
  64. <span class="sd">`XPath selector`_:</span>
  65. <span class="sd">- :py:obj:`results_xpath`</span>
  66. <span class="sd">- :py:obj:`url_xpath`</span>
  67. <span class="sd">- :py:obj:`title_xpath`</span>
  68. <span class="sd">- :py:obj:`content_xpath`</span>
  69. <span class="sd">- :py:obj:`thumbnail_xpath`</span>
  70. <span class="sd">- :py:obj:`suggestion_xpath`</span>
  71. <span class="sd">Example</span>
  72. <span class="sd">=======</span>
  73. <span class="sd">Here is a simple example of a XPath engine configured in the :ref:`settings</span>
  74. <span class="sd">engines` section, further read :ref:`engines-dev`.</span>
  75. <span class="sd">.. code:: yaml</span>
  76. <span class="sd"> - name : bitbucket</span>
  77. <span class="sd"> engine : xpath</span>
  78. <span class="sd"> paging : True</span>
  79. <span class="sd"> search_url : https://bitbucket.org/repo/all/{pageno}?name={query}</span>
  80. <span class="sd"> url_xpath : //article[@class=&quot;repo-summary&quot;]//a[@class=&quot;repo-link&quot;]/@href</span>
  81. <span class="sd"> title_xpath : //article[@class=&quot;repo-summary&quot;]//a[@class=&quot;repo-link&quot;]</span>
  82. <span class="sd"> content_xpath : //article[@class=&quot;repo-summary&quot;]/p</span>
  83. <span class="sd">Implementations</span>
  84. <span class="sd">===============</span>
  85. <span class="sd">&quot;&quot;&quot;</span>
  86. <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">urlencode</span>
  87. <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>
  88. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.utils</span><span class="w"> </span><span class="kn">import</span> <span class="n">extract_text</span><span class="p">,</span> <span class="n">extract_url</span><span class="p">,</span> <span class="n">eval_xpath</span><span class="p">,</span> <span class="n">eval_xpath_list</span>
  89. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.network</span><span class="w"> </span><span class="kn">import</span> <span class="n">raise_for_httperror</span>
  90. <span class="kn">from</span><span class="w"> </span><span class="nn">searx.result_types</span><span class="w"> </span><span class="kn">import</span> <span class="n">EngineResults</span>
  91. <span class="n">search_url</span> <span class="o">=</span> <span class="kc">None</span>
  92. <span class="sd">&quot;&quot;&quot;</span>
  93. <span class="sd">Search URL of the engine. Example::</span>
  94. <span class="sd"> https://example.org/?search={query}&amp;page={pageno}{time_range}{safe_search}</span>
  95. <span class="sd">Replacements are:</span>
  96. <span class="sd">``{query}``:</span>
  97. <span class="sd"> Search terms from user.</span>
  98. <span class="sd">``{pageno}``:</span>
  99. <span class="sd"> Page number if engine supports paging :py:obj:`paging`</span>
  100. <span class="sd">``{lang}``:</span>
  101. <span class="sd"> ISO 639-1 language code (en, de, fr ..)</span>
  102. <span class="sd">``{time_range}``:</span>
  103. <span class="sd"> :py:obj:`URL parameter &lt;time_range_url&gt;` if engine :py:obj:`supports time</span>
  104. <span class="sd"> range &lt;time_range_support&gt;`. The value for the parameter is taken from</span>
  105. <span class="sd"> :py:obj:`time_range_map`.</span>
  106. <span class="sd">``{safe_search}``:</span>
  107. <span class="sd"> Safe-search :py:obj:`URL parameter &lt;safe_search_map&gt;` if engine</span>
  108. <span class="sd"> :py:obj:`supports safe-search &lt;safe_search_support&gt;`. The ``{safe_search}``</span>
  109. <span class="sd"> replacement is taken from the :py:obj:`safes_search_map`. Filter results::</span>
  110. <span class="sd"> 0: none, 1: moderate, 2:strict</span>
  111. <span class="sd"> If not supported, the URL parameter is an empty string.</span>
  112. <span class="sd">&quot;&quot;&quot;</span>
  113. <span class="n">lang_all</span> <span class="o">=</span> <span class="s1">&#39;en&#39;</span>
  114. <span class="sd">&#39;&#39;&#39;Replacement ``{lang}`` in :py:obj:`search_url` if language ``all`` is</span>
  115. <span class="sd">selected.</span>
  116. <span class="sd">&#39;&#39;&#39;</span>
  117. <span class="n">no_result_for_http_status</span> <span class="o">=</span> <span class="p">[]</span>
  118. <span class="sd">&#39;&#39;&#39;Return empty result for these HTTP status codes instead of throwing an error.</span>
  119. <span class="sd">.. code:: yaml</span>
  120. <span class="sd"> no_result_for_http_status: []</span>
  121. <span class="sd">&#39;&#39;&#39;</span>
  122. <span class="n">soft_max_redirects</span> <span class="o">=</span> <span class="mi">0</span>
  123. <span class="sd">&#39;&#39;&#39;Maximum redirects, soft limit. Record an error but don&#39;t stop the engine&#39;&#39;&#39;</span>
  124. <span class="n">results_xpath</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  125. <span class="sd">&#39;&#39;&#39;`XPath selector`_ for the list of result items&#39;&#39;&#39;</span>
  126. <span class="n">url_xpath</span> <span class="o">=</span> <span class="kc">None</span>
  127. <span class="sd">&#39;&#39;&#39;`XPath selector`_ of result&#39;s ``url``.&#39;&#39;&#39;</span>
  128. <span class="n">content_xpath</span> <span class="o">=</span> <span class="kc">None</span>
  129. <span class="sd">&#39;&#39;&#39;`XPath selector`_ of result&#39;s ``content``.&#39;&#39;&#39;</span>
  130. <span class="n">title_xpath</span> <span class="o">=</span> <span class="kc">None</span>
  131. <span class="sd">&#39;&#39;&#39;`XPath selector`_ of result&#39;s ``title``.&#39;&#39;&#39;</span>
  132. <span class="n">thumbnail_xpath</span> <span class="o">=</span> <span class="kc">False</span>
  133. <span class="sd">&#39;&#39;&#39;`XPath selector`_ of result&#39;s ``thumbnail``.&#39;&#39;&#39;</span>
  134. <span class="n">suggestion_xpath</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  135. <span class="sd">&#39;&#39;&#39;`XPath selector`_ of result&#39;s ``suggestion``.&#39;&#39;&#39;</span>
  136. <span class="n">cached_xpath</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  137. <span class="n">cached_url</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  138. <span class="n">cookies</span> <span class="o">=</span> <span class="p">{}</span>
  139. <span class="sd">&#39;&#39;&#39;Some engines might offer different result based on cookies.</span>
  140. <span class="sd">Possible use-case: To set safesearch cookie.&#39;&#39;&#39;</span>
  141. <span class="n">headers</span> <span class="o">=</span> <span class="p">{}</span>
  142. <span class="sd">&#39;&#39;&#39;Some engines might offer different result based headers. Possible use-case:</span>
  143. <span class="sd">To set header to moderate.&#39;&#39;&#39;</span>
  144. <span class="n">method</span> <span class="o">=</span> <span class="s1">&#39;GET&#39;</span>
  145. <span class="sd">&#39;&#39;&#39;Some engines might require to do POST requests for search.&#39;&#39;&#39;</span>
  146. <span class="n">request_body</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  147. <span class="sd">&#39;&#39;&#39;The body of the request. This can only be used if different :py:obj:`method`</span>
  148. <span class="sd">is set, e.g. ``POST``. For formatting see the documentation of :py:obj:`search_url`::</span>
  149. <span class="sd"> search={query}&amp;page={pageno}{time_range}{safe_search}</span>
  150. <span class="sd">&#39;&#39;&#39;</span>
  151. <span class="n">paging</span> <span class="o">=</span> <span class="kc">False</span>
  152. <span class="sd">&#39;&#39;&#39;Engine supports paging [True or False].&#39;&#39;&#39;</span>
  153. <span class="n">page_size</span> <span class="o">=</span> <span class="mi">1</span>
  154. <span class="sd">&#39;&#39;&#39;Number of results on each page. Only needed if the site requires not a page</span>
  155. <span class="sd">number, but an offset.&#39;&#39;&#39;</span>
  156. <span class="n">first_page_num</span> <span class="o">=</span> <span class="mi">1</span>
  157. <span class="sd">&#39;&#39;&#39;Number of the first page (usually 0 or 1).&#39;&#39;&#39;</span>
  158. <span class="n">time_range_support</span> <span class="o">=</span> <span class="kc">False</span>
  159. <span class="sd">&#39;&#39;&#39;Engine supports search time range.&#39;&#39;&#39;</span>
  160. <span class="n">time_range_url</span> <span class="o">=</span> <span class="s1">&#39;&amp;hours=</span><span class="si">{time_range_val}</span><span class="s1">&#39;</span>
  161. <span class="sd">&#39;&#39;&#39;Time range URL parameter in the in :py:obj:`search_url`. If no time range is</span>
  162. <span class="sd">requested by the user, the URL parameter is an empty string. The</span>
  163. <span class="sd">``{time_range_val}`` replacement is taken from the :py:obj:`time_range_map`.</span>
  164. <span class="sd">.. code:: yaml</span>
  165. <span class="sd"> time_range_url : &#39;&amp;days={time_range_val}&#39;</span>
  166. <span class="sd">&#39;&#39;&#39;</span>
  167. <span class="n">time_range_map</span> <span class="o">=</span> <span class="p">{</span>
  168. <span class="s1">&#39;day&#39;</span><span class="p">:</span> <span class="mi">24</span><span class="p">,</span>
  169. <span class="s1">&#39;week&#39;</span><span class="p">:</span> <span class="mi">24</span> <span class="o">*</span> <span class="mi">7</span><span class="p">,</span>
  170. <span class="s1">&#39;month&#39;</span><span class="p">:</span> <span class="mi">24</span> <span class="o">*</span> <span class="mi">30</span><span class="p">,</span>
  171. <span class="s1">&#39;year&#39;</span><span class="p">:</span> <span class="mi">24</span> <span class="o">*</span> <span class="mi">365</span><span class="p">,</span>
  172. <span class="p">}</span>
  173. <span class="sd">&#39;&#39;&#39;Maps time range value from user to ``{time_range_val}`` in</span>
  174. <span class="sd">:py:obj:`time_range_url`.</span>
  175. <span class="sd">.. code:: yaml</span>
  176. <span class="sd"> time_range_map:</span>
  177. <span class="sd"> day: 1</span>
  178. <span class="sd"> week: 7</span>
  179. <span class="sd"> month: 30</span>
  180. <span class="sd"> year: 365</span>
  181. <span class="sd">&#39;&#39;&#39;</span>
  182. <span class="n">safe_search_support</span> <span class="o">=</span> <span class="kc">False</span>
  183. <span class="sd">&#39;&#39;&#39;Engine supports safe-search.&#39;&#39;&#39;</span>
  184. <span class="n">safe_search_map</span> <span class="o">=</span> <span class="p">{</span><span class="mi">0</span><span class="p">:</span> <span class="s1">&#39;&amp;filter=none&#39;</span><span class="p">,</span> <span class="mi">1</span><span class="p">:</span> <span class="s1">&#39;&amp;filter=moderate&#39;</span><span class="p">,</span> <span class="mi">2</span><span class="p">:</span> <span class="s1">&#39;&amp;filter=strict&#39;</span><span class="p">}</span>
  185. <span class="sd">&#39;&#39;&#39;Maps safe-search value to ``{safe_search}`` in :py:obj:`search_url`.</span>
  186. <span class="sd">.. code:: yaml</span>
  187. <span class="sd"> safesearch: true</span>
  188. <span class="sd"> safes_search_map:</span>
  189. <span class="sd"> 0: &#39;&amp;filter=none&#39;</span>
  190. <span class="sd"> 1: &#39;&amp;filter=moderate&#39;</span>
  191. <span class="sd"> 2: &#39;&amp;filter=strict&#39;</span>
  192. <span class="sd">&#39;&#39;&#39;</span>
  193. <div class="viewcode-block" id="request">
  194. <a class="viewcode-back" href="../../../dev/engines/xpath.html#searx.engines.xpath.request">[docs]</a>
  195. <span class="k">def</span><span class="w"> </span><span class="nf">request</span><span class="p">(</span><span class="n">query</span><span class="p">,</span> <span class="n">params</span><span class="p">):</span>
  196. <span class="w"> </span><span class="sd">&#39;&#39;&#39;Build request parameters (see :ref:`engine request`).&#39;&#39;&#39;</span>
  197. <span class="n">lang</span> <span class="o">=</span> <span class="n">lang_all</span>
  198. <span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;language&#39;</span><span class="p">]</span> <span class="o">!=</span> <span class="s1">&#39;all&#39;</span><span class="p">:</span>
  199. <span class="n">lang</span> <span class="o">=</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;language&#39;</span><span class="p">][:</span><span class="mi">2</span><span class="p">]</span>
  200. <span class="n">time_range</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  201. <span class="k">if</span> <span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;time_range&#39;</span><span class="p">):</span>
  202. <span class="n">time_range_val</span> <span class="o">=</span> <span class="n">time_range_map</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">params</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">&#39;time_range&#39;</span><span class="p">))</span>
  203. <span class="n">time_range</span> <span class="o">=</span> <span class="n">time_range_url</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">time_range_val</span><span class="o">=</span><span class="n">time_range_val</span><span class="p">)</span>
  204. <span class="n">safe_search</span> <span class="o">=</span> <span class="s1">&#39;&#39;</span>
  205. <span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;safesearch&#39;</span><span class="p">]:</span>
  206. <span class="n">safe_search</span> <span class="o">=</span> <span class="n">safe_search_map</span><span class="p">[</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;safesearch&#39;</span><span class="p">]]</span>
  207. <span class="n">fargs</span> <span class="o">=</span> <span class="p">{</span>
  208. <span class="s1">&#39;query&#39;</span><span class="p">:</span> <span class="n">urlencode</span><span class="p">({</span><span class="s1">&#39;q&#39;</span><span class="p">:</span> <span class="n">query</span><span class="p">})[</span><span class="mi">2</span><span class="p">:],</span>
  209. <span class="s1">&#39;lang&#39;</span><span class="p">:</span> <span class="n">lang</span><span class="p">,</span>
  210. <span class="s1">&#39;pageno&#39;</span><span class="p">:</span> <span class="p">(</span><span class="n">params</span><span class="p">[</span><span class="s1">&#39;pageno&#39;</span><span class="p">]</span> <span class="o">-</span> <span class="mi">1</span><span class="p">)</span> <span class="o">*</span> <span class="n">page_size</span> <span class="o">+</span> <span class="n">first_page_num</span><span class="p">,</span>
  211. <span class="s1">&#39;time_range&#39;</span><span class="p">:</span> <span class="n">time_range</span><span class="p">,</span>
  212. <span class="s1">&#39;safe_search&#39;</span><span class="p">:</span> <span class="n">safe_search</span><span class="p">,</span>
  213. <span class="p">}</span>
  214. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;cookies&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">cookies</span><span class="p">)</span>
  215. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;headers&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">headers</span><span class="p">)</span>
  216. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;url&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">search_url</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="n">fargs</span><span class="p">)</span>
  217. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;method&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">method</span>
  218. <span class="k">if</span> <span class="n">request_body</span><span class="p">:</span>
  219. <span class="c1"># don&#39;t url-encode the query if it&#39;s in the request body</span>
  220. <span class="n">fargs</span><span class="p">[</span><span class="s1">&#39;query&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">query</span>
  221. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;data&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">request_body</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="o">**</span><span class="n">fargs</span><span class="p">)</span>
  222. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;soft_max_redirects&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">soft_max_redirects</span>
  223. <span class="n">params</span><span class="p">[</span><span class="s1">&#39;raise_for_httperror&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">False</span>
  224. <span class="k">return</span> <span class="n">params</span></div>
  225. <div class="viewcode-block" id="response">
  226. <a class="viewcode-back" href="../../../dev/engines/xpath.html#searx.engines.xpath.response">[docs]</a>
  227. <span class="k">def</span><span class="w"> </span><span class="nf">response</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">EngineResults</span><span class="p">:</span> <span class="c1"># pylint: disable=too-many-branches</span>
  228. <span class="w"> </span><span class="sd">&quot;&quot;&quot;Scrap *results* from the response (see :ref:`result types`).&quot;&quot;&quot;</span>
  229. <span class="n">results</span> <span class="o">=</span> <span class="n">EngineResults</span><span class="p">()</span>
  230. <span class="k">if</span> <span class="n">no_result_for_http_status</span> <span class="ow">and</span> <span class="n">resp</span><span class="o">.</span><span class="n">status_code</span> <span class="ow">in</span> <span class="n">no_result_for_http_status</span><span class="p">:</span>
  231. <span class="k">return</span> <span class="n">results</span>
  232. <span class="n">raise_for_httperror</span><span class="p">(</span><span class="n">resp</span><span class="p">)</span>
  233. <span class="k">if</span> <span class="ow">not</span> <span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">:</span>
  234. <span class="k">return</span> <span class="n">results</span>
  235. <span class="n">dom</span> <span class="o">=</span> <span class="n">html</span><span class="o">.</span><span class="n">fromstring</span><span class="p">(</span><span class="n">resp</span><span class="o">.</span><span class="n">text</span><span class="p">)</span>
  236. <span class="n">is_onion</span> <span class="o">=</span> <span class="s1">&#39;onions&#39;</span> <span class="ow">in</span> <span class="n">categories</span>
  237. <span class="k">if</span> <span class="n">results_xpath</span><span class="p">:</span>
  238. <span class="k">for</span> <span class="n">result</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">results_xpath</span><span class="p">):</span>
  239. <span class="n">url</span> <span class="o">=</span> <span class="n">extract_url</span><span class="p">(</span><span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">url_xpath</span><span class="p">,</span> <span class="n">min_len</span><span class="o">=</span><span class="mi">1</span><span class="p">),</span> <span class="n">search_url</span><span class="p">)</span>
  240. <span class="n">title</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">title_xpath</span><span class="p">,</span> <span class="n">min_len</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
  241. <span class="n">content</span> <span class="o">=</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">content_xpath</span><span class="p">))</span>
  242. <span class="n">tmp_result</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;url&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span> <span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span> <span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">content</span><span class="p">}</span>
  243. <span class="c1"># add thumbnail if available</span>
  244. <span class="k">if</span> <span class="n">thumbnail_xpath</span><span class="p">:</span>
  245. <span class="n">thumbnail_xpath_result</span> <span class="o">=</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">thumbnail_xpath</span><span class="p">)</span>
  246. <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">thumbnail_xpath_result</span><span class="p">)</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">:</span>
  247. <span class="n">tmp_result</span><span class="p">[</span><span class="s1">&#39;thumbnail&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">extract_url</span><span class="p">(</span><span class="n">thumbnail_xpath_result</span><span class="p">,</span> <span class="n">search_url</span><span class="p">)</span>
  248. <span class="c1"># add alternative cached url if available</span>
  249. <span class="k">if</span> <span class="n">cached_xpath</span><span class="p">:</span>
  250. <span class="n">tmp_result</span><span class="p">[</span><span class="s1">&#39;cached_url&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">cached_url</span> <span class="o">+</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">result</span><span class="p">,</span> <span class="n">cached_xpath</span><span class="p">,</span> <span class="n">min_len</span><span class="o">=</span><span class="mi">1</span><span class="p">))</span>
  251. <span class="k">if</span> <span class="n">is_onion</span><span class="p">:</span>
  252. <span class="n">tmp_result</span><span class="p">[</span><span class="s1">&#39;is_onion&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="kc">True</span>
  253. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">tmp_result</span><span class="p">)</span>
  254. <span class="k">else</span><span class="p">:</span>
  255. <span class="k">if</span> <span class="n">cached_xpath</span><span class="p">:</span>
  256. <span class="k">for</span> <span class="n">url</span><span class="p">,</span> <span class="n">title</span><span class="p">,</span> <span class="n">content</span><span class="p">,</span> <span class="n">cached</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span>
  257. <span class="p">(</span><span class="n">extract_url</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">search_url</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">url_xpath</span><span class="p">)),</span>
  258. <span class="nb">map</span><span class="p">(</span><span class="n">extract_text</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">title_xpath</span><span class="p">)),</span>
  259. <span class="nb">map</span><span class="p">(</span><span class="n">extract_text</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">content_xpath</span><span class="p">)),</span>
  260. <span class="nb">map</span><span class="p">(</span><span class="n">extract_text</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">cached_xpath</span><span class="p">)),</span>
  261. <span class="p">):</span>
  262. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
  263. <span class="p">{</span>
  264. <span class="s1">&#39;url&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span>
  265. <span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span>
  266. <span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span>
  267. <span class="s1">&#39;cached_url&#39;</span><span class="p">:</span> <span class="n">cached_url</span> <span class="o">+</span> <span class="n">cached</span><span class="p">,</span>
  268. <span class="s1">&#39;is_onion&#39;</span><span class="p">:</span> <span class="n">is_onion</span><span class="p">,</span>
  269. <span class="p">}</span>
  270. <span class="p">)</span>
  271. <span class="k">else</span><span class="p">:</span>
  272. <span class="k">for</span> <span class="n">url</span><span class="p">,</span> <span class="n">title</span><span class="p">,</span> <span class="n">content</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span>
  273. <span class="p">(</span><span class="n">extract_url</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">search_url</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">url_xpath</span><span class="p">)),</span>
  274. <span class="nb">map</span><span class="p">(</span><span class="n">extract_text</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">title_xpath</span><span class="p">)),</span>
  275. <span class="nb">map</span><span class="p">(</span><span class="n">extract_text</span><span class="p">,</span> <span class="n">eval_xpath_list</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">content_xpath</span><span class="p">)),</span>
  276. <span class="p">):</span>
  277. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">&#39;url&#39;</span><span class="p">:</span> <span class="n">url</span><span class="p">,</span> <span class="s1">&#39;title&#39;</span><span class="p">:</span> <span class="n">title</span><span class="p">,</span> <span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">content</span><span class="p">,</span> <span class="s1">&#39;is_onion&#39;</span><span class="p">:</span> <span class="n">is_onion</span><span class="p">})</span>
  278. <span class="k">if</span> <span class="n">suggestion_xpath</span><span class="p">:</span>
  279. <span class="k">for</span> <span class="n">suggestion</span> <span class="ow">in</span> <span class="n">eval_xpath</span><span class="p">(</span><span class="n">dom</span><span class="p">,</span> <span class="n">suggestion_xpath</span><span class="p">):</span>
  280. <span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">({</span><span class="s1">&#39;suggestion&#39;</span><span class="p">:</span> <span class="n">extract_text</span><span class="p">(</span><span class="n">suggestion</span><span class="p">)})</span>
  281. <span class="n">logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">&quot;found </span><span class="si">%s</span><span class="s2"> results&quot;</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">results</span><span class="p">))</span>
  282. <span class="k">return</span> <span class="n">results</span></div>
  283. </pre></div>
  284. <div class="clearer"></div>
  285. </div>
  286. </div>
  287. </div>
  288. <span id="sidebar-top"></span>
  289. <div class="sphinxsidebar" role="navigation" aria-label="Main">
  290. <div class="sphinxsidebarwrapper">
  291. <p class="logo"><a href="../../../index.html">
  292. <img class="logo" src="../../../_static/searxng-wordmark.svg" alt="Logo of SearXNG"/>
  293. </a></p>
  294. <h3><a href="../../../index.html">Table of Contents</a></h3>
  295. <ul>
  296. <li class="toctree-l1"><a class="reference internal" href="../../../user/index.html">User information</a></li>
  297. <li class="toctree-l1"><a class="reference internal" href="../../../own-instance.html">Why use a private instance?</a></li>
  298. <li class="toctree-l1"><a class="reference internal" href="../../../admin/index.html">Administrator documentation</a></li>
  299. <li class="toctree-l1"><a class="reference internal" href="../../../dev/index.html">Developer documentation</a></li>
  300. <li class="toctree-l1"><a class="reference internal" href="../../../utils/index.html">DevOps tooling box</a></li>
  301. <li class="toctree-l1"><a class="reference internal" href="../../../src/index.html">Source-Code</a></li>
  302. </ul>
  303. <h3>Project Links</h3>
  304. <ul>
  305. <li><a href="https://github.com/searxng/searxng/tree/master">Source</a>
  306. <li><a href="https://github.com/searxng/searxng/wiki">Wiki</a>
  307. <li><a href="https://searx.space">Public instances</a>
  308. <li><a href="https://github.com/searxng/searxng/issues">Issue Tracker</a>
  309. </ul><h3>Navigation</h3>
  310. <ul>
  311. <li><a href="../../../index.html">Overview</a>
  312. <ul>
  313. <li><a href="../../index.html">Module code</a>
  314. <ul>
  315. <li><a href="../engines.html">searx.engines</a>
  316. </ul>
  317. </li></ul>
  318. </li>
  319. </ul>
  320. </li>
  321. </ul>
  322. <search id="searchbox" style="display: none" role="search">
  323. <h3 id="searchlabel">Quick search</h3>
  324. <div class="searchformwrapper">
  325. <form class="search" action="../../../search.html" method="get">
  326. <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/>
  327. <input type="submit" value="Go" />
  328. </form>
  329. </div>
  330. </search>
  331. <script>document.getElementById('searchbox').style.display = "block"</script>
  332. </div>
  333. </div>
  334. <div class="clearer"></div>
  335. </div>
  336. <div class="footer" role="contentinfo">
  337. &#169; Copyright SearXNG team.
  338. </div>
  339. </body>
  340. </html>