doc/html/apidoc/lxml.html.clean.html

   1
   2
   3 <!DOCTYPE html>
   4 <html class="writer-html5" lang="en" >
   5 <head>
   6   <meta charset="utf-8">
   7
   8   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   9
  10   <title>lxml.html.clean module &mdash; lxml  documentation</title>
  11
  12
  13
  14   <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
  15   <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
  16
  17
  18
  19
  20
  21
  22
  23   <!--[if lt IE 9]>
  24     <script src="_static/js/html5shiv.min.js"></script>
  25   <![endif]-->
  26
  27
  28       <script type="text/javascript" id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script>
  29         <script src="_static/jquery.js"></script>
  30         <script src="_static/underscore.js"></script>
  31         <script src="_static/doctools.js"></script>
  32         <script src="_static/language_data.js"></script>
  33
  34     <script type="text/javascript" src="_static/js/theme.js"></script>
  35
  36
  37     <link rel="index" title="Index" href="genindex.html" />
  38     <link rel="search" title="Search" href="search.html" />
  39     <link rel="next" title="lxml.html.defs module" href="lxml.html.defs.html" />
  40     <link rel="prev" title="lxml.html.builder module" href="lxml.html.builder.html" />
  41 </head>
  42
  43 <body class="wy-body-for-nav">
  44
  45
  46   <div class="wy-grid-for-nav">
  47
  48     <nav data-toggle="wy-nav-shift" class="wy-nav-side">
  49       <div class="wy-side-scroll">
  50         <div class="wy-side-nav-search" >
  51
  52
  53
  54             <a href="index.html" class="icon icon-home" alt="Documentation Home"> lxml
  55
  56
  57
  58
  59             <img src="_static/python-xml.png" class="logo" alt="Logo"/>
  60
  61           </a>
  62
  63
  64
  65
  66               <div class="version">
  67                 4.6.0
  68               </div>
  69
  70
  71
  72
  73 <div role="search">
  74   <form id="rtd-search-form" class="wy-form" action="search.html" method="get">
  75     <input type="text" name="q" placeholder="Search docs" />
  76     <input type="hidden" name="check_keywords" value="yes" />
  77     <input type="hidden" name="area" value="default" />
  78   </form>
  79 </div>
  80
  81
  82         </div>
  83
  84
  85         <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
  86
  87
  88
  89
  90
  91
  92               <ul class="current">
  93 <li class="toctree-l1 current"><a class="reference internal" href="lxml.html">lxml package</a><ul class="current">
  94 <li class="toctree-l2 current"><a class="reference internal" href="lxml.html.html">lxml.html package</a><ul class="current">
  95 <li class="toctree-l3"><a class="reference internal" href="lxml.html.ElementSoup.html">lxml.html.ElementSoup module</a></li>
  96 <li class="toctree-l3"><a class="reference internal" href="lxml.html._diffcommand.html">lxml.html._diffcommand module</a></li>
  97 <li class="toctree-l3"><a class="reference internal" href="lxml.html._setmixin.html">lxml.html._setmixin module</a></li>
  98 <li class="toctree-l3"><a class="reference internal" href="lxml.html.builder.html">lxml.html.builder module</a></li>
  99 <li class="toctree-l3 current"><a class="current reference internal" href="#">lxml.html.clean module</a></li>
 100 <li class="toctree-l3"><a class="reference internal" href="lxml.html.defs.html">lxml.html.defs module</a></li>
 101 <li class="toctree-l3"><a class="reference internal" href="lxml.html.diff.html">lxml.html.diff module</a></li>
 102 <li class="toctree-l3"><a class="reference internal" href="lxml.html.formfill.html">lxml.html.formfill module</a></li>
 103 <li class="toctree-l3"><a class="reference internal" href="lxml.html.html5parser.html">lxml.html.html5parser module</a></li>
 104 <li class="toctree-l3"><a class="reference internal" href="lxml.html.soupparser.html">lxml.html.soupparser module</a></li>
 105 </ul>
 106 </li>
 107 <li class="toctree-l2"><a class="reference internal" href="lxml.isoschematron.html">lxml.isoschematron package</a></li>
 108 <li class="toctree-l2"><a class="reference internal" href="lxml.ElementInclude.html">lxml.ElementInclude module</a></li>
 109 <li class="toctree-l2"><a class="reference internal" href="lxml._elementpath.html">lxml._elementpath module</a></li>
 110 <li class="toctree-l2"><a class="reference internal" href="lxml.builder.html">lxml.builder module</a></li>
 111 <li class="toctree-l2"><a class="reference internal" href="lxml.cssselect.html">lxml.cssselect module</a></li>
 112 <li class="toctree-l2"><a class="reference internal" href="lxml.doctestcompare.html">lxml.doctestcompare module</a></li>
 113 <li class="toctree-l2"><a class="reference internal" href="lxml.etree.html">lxml.etree module</a></li>
 114 <li class="toctree-l2"><a class="reference internal" href="lxml.objectify.html">lxml.objectify module</a></li>
 115 <li class="toctree-l2"><a class="reference internal" href="lxml.sax.html">lxml.sax module</a></li>
 116 </ul>
 117 </li>
 118 </ul>
 119
 120
 121
 122         </div>
 123
 124       </div>
 125     </nav>
 126
 127     <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
 128
 129
 130       <nav class="wy-nav-top" aria-label="top navigation">
 131
 132           <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
 133           <a href="index.html">lxml</a>
 134
 135       </nav>
 136
 137
 138       <div class="wy-nav-content">
 139
 140         <div class="rst-content">
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158 <div role="navigation" aria-label="breadcrumbs navigation">
 159
 160   <ul class="wy-breadcrumbs">
 161
 162       <li><a href="index.html" class="icon icon-home"></a> &raquo;</li>
 163
 164           <li><a href="lxml.html">lxml package</a> &raquo;</li>
 165
 166           <li><a href="lxml.html.html">lxml.html package</a> &raquo;</li>
 167
 168       <li>lxml.html.clean module</li>
 169
 170
 171       <li class="wy-breadcrumbs-aside">
 172
 173
 174             <a href="_sources/lxml.html.clean.rst.txt" rel="nofollow"> View page source</a>
 175
 176
 177       </li>
 178
 179   </ul>
 180
 181
 182   <hr/>
 183 </div>
 184           <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
 185            <div itemprop="articleBody">
 186
 187   <div class="section" id="module-lxml.html.clean">
 188 <span id="lxml-html-clean-module"></span><h1>lxml.html.clean module<a class="headerlink" href="#module-lxml.html.clean" title="Permalink to this headline">¶</a></h1>
 189 <p>A cleanup tool for HTML.</p>
 190 <p>Removes unwanted tags and content.  See the <cite>Cleaner</cite> class for
 191 details.</p>
 192 <dl class="py class">
 193 <dt id="lxml.html.clean.Cleaner">
 194 <em class="property">class </em><code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">Cleaner</code><span class="sig-paren">(</span><em class="sig-param"><span class="o">**</span><span class="n">kw</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner" title="Permalink to this definition">¶</a></dt>
 195 <dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
 196 <p>Instances cleans the document of each of the possible offending
 197 elements.  The cleaning is controlled by attributes; you can
 198 override attributes in a subclass, or set them in the constructor.</p>
 199 <dl>
 200 <dt><code class="docutils literal notranslate"><span class="pre">scripts</span></code>:</dt><dd><p>Removes any <code class="docutils literal notranslate"><span class="pre">&lt;script&gt;</span></code> tags.</p>
 201 </dd>
 202 <dt><code class="docutils literal notranslate"><span class="pre">javascript</span></code>:</dt><dd><p>Removes any Javascript, like an <code class="docutils literal notranslate"><span class="pre">onclick</span></code> attribute. Also removes stylesheets
 203 as they could contain Javascript.</p>
 204 </dd>
 205 <dt><code class="docutils literal notranslate"><span class="pre">comments</span></code>:</dt><dd><p>Removes any comments.</p>
 206 </dd>
 207 <dt><code class="docutils literal notranslate"><span class="pre">style</span></code>:</dt><dd><p>Removes any style tags.</p>
 208 </dd>
 209 <dt><code class="docutils literal notranslate"><span class="pre">inline_style</span></code></dt><dd><p>Removes any style attributes.  Defaults to the value of the <code class="docutils literal notranslate"><span class="pre">style</span></code> option.</p>
 210 </dd>
 211 <dt><code class="docutils literal notranslate"><span class="pre">links</span></code>:</dt><dd><p>Removes any <code class="docutils literal notranslate"><span class="pre">&lt;link&gt;</span></code> tags</p>
 212 </dd>
 213 <dt><code class="docutils literal notranslate"><span class="pre">meta</span></code>:</dt><dd><p>Removes any <code class="docutils literal notranslate"><span class="pre">&lt;meta&gt;</span></code> tags</p>
 214 </dd>
 215 <dt><code class="docutils literal notranslate"><span class="pre">page_structure</span></code>:</dt><dd><p>Structural parts of a page: <code class="docutils literal notranslate"><span class="pre">&lt;head&gt;</span></code>, <code class="docutils literal notranslate"><span class="pre">&lt;html&gt;</span></code>, <code class="docutils literal notranslate"><span class="pre">&lt;title&gt;</span></code>.</p>
 216 </dd>
 217 <dt><code class="docutils literal notranslate"><span class="pre">processing_instructions</span></code>:</dt><dd><p>Removes any processing instructions.</p>
 218 </dd>
 219 <dt><code class="docutils literal notranslate"><span class="pre">embedded</span></code>:</dt><dd><p>Removes any embedded objects (flash, iframes)</p>
 220 </dd>
 221 <dt><code class="docutils literal notranslate"><span class="pre">frames</span></code>:</dt><dd><p>Removes any frame-related tags</p>
 222 </dd>
 223 <dt><code class="docutils literal notranslate"><span class="pre">forms</span></code>:</dt><dd><p>Removes any form tags</p>
 224 </dd>
 225 <dt><code class="docutils literal notranslate"><span class="pre">annoying_tags</span></code>:</dt><dd><p>Tags that aren’t <em>wrong</em>, but are annoying.  <code class="docutils literal notranslate"><span class="pre">&lt;blink&gt;</span></code> and <code class="docutils literal notranslate"><span class="pre">&lt;marquee&gt;</span></code></p>
 226 </dd>
 227 <dt><code class="docutils literal notranslate"><span class="pre">remove_tags</span></code>:</dt><dd><p>A list of tags to remove.  Only the tags will be removed,
 228 their content will get pulled up into the parent tag.</p>
 229 </dd>
 230 <dt><code class="docutils literal notranslate"><span class="pre">kill_tags</span></code>:</dt><dd><p>A list of tags to kill.  Killing also removes the tag’s content,
 231 i.e. the whole subtree, not just the tag itself.</p>
 232 </dd>
 233 <dt><code class="docutils literal notranslate"><span class="pre">allow_tags</span></code>:</dt><dd><p>A list of tags to include (default include all).</p>
 234 </dd>
 235 <dt><code class="docutils literal notranslate"><span class="pre">remove_unknown_tags</span></code>:</dt><dd><p>Remove any tags that aren’t standard parts of HTML.</p>
 236 </dd>
 237 <dt><code class="docutils literal notranslate"><span class="pre">safe_attrs_only</span></code>:</dt><dd><p>If true, only include ‘safe’ attributes (specifically the list
 238 from the feedparser HTML sanitisation web site).</p>
 239 </dd>
 240 <dt><code class="docutils literal notranslate"><span class="pre">safe_attrs</span></code>:</dt><dd><p>A set of attribute names to override the default list of attributes
 241 considered ‘safe’ (when safe_attrs_only=True).</p>
 242 </dd>
 243 <dt><code class="docutils literal notranslate"><span class="pre">add_nofollow</span></code>:</dt><dd><p>If true, then any &lt;a&gt; tags will have <code class="docutils literal notranslate"><span class="pre">rel=&quot;nofollow&quot;</span></code> added to them.</p>
 244 </dd>
 245 <dt><code class="docutils literal notranslate"><span class="pre">host_whitelist</span></code>:</dt><dd><p>A list or set of hosts that you can use for embedded content
 246 (for content like <code class="docutils literal notranslate"><span class="pre">&lt;object&gt;</span></code>, <code class="docutils literal notranslate"><span class="pre">&lt;link</span> <span class="pre">rel=&quot;stylesheet&quot;&gt;</span></code>, etc).
 247 You can also implement/override the method
 248 <code class="docutils literal notranslate"><span class="pre">allow_embedded_url(el,</span> <span class="pre">url)</span></code> or <code class="docutils literal notranslate"><span class="pre">allow_element(el)</span></code> to
 249 implement more complex rules for what can be embedded.
 250 Anything that passes this test will be shown, regardless of
 251 the value of (for instance) <code class="docutils literal notranslate"><span class="pre">embedded</span></code>.</p>
 252 <p>Note that this parameter might not work as intended if you do not
 253 make the links absolute before doing the cleaning.</p>
 254 <p>Note that you may also need to set <code class="docutils literal notranslate"><span class="pre">whitelist_tags</span></code>.</p>
 255 </dd>
 256 <dt><code class="docutils literal notranslate"><span class="pre">whitelist_tags</span></code>:</dt><dd><p>A set of tags that can be included with <code class="docutils literal notranslate"><span class="pre">host_whitelist</span></code>.
 257 The default is <code class="docutils literal notranslate"><span class="pre">iframe</span></code> and <code class="docutils literal notranslate"><span class="pre">embed</span></code>; you may wish to
 258 include other tags like <code class="docutils literal notranslate"><span class="pre">script</span></code>, or you may want to
 259 implement <code class="docutils literal notranslate"><span class="pre">allow_embedded_url</span></code> for more control.  Set to None to
 260 include all tags.</p>
 261 </dd>
 262 </dl>
 263 <p>This modifies the document <em>in place</em>.</p>
 264 <dl class="py method">
 265 <dt id="lxml.html.clean.Cleaner._has_sneaky_javascript">
 266 <code class="sig-name descname">_has_sneaky_javascript</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">style</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner._has_sneaky_javascript" title="Permalink to this definition">¶</a></dt>
 267 <dd><p>Depending on the browser, stuff like <code class="docutils literal notranslate"><span class="pre">e</span> <span class="pre">x</span> <span class="pre">p</span> <span class="pre">r</span> <span class="pre">e</span> <span class="pre">s</span> <span class="pre">s</span> <span class="pre">i</span> <span class="pre">o</span> <span class="pre">n(...)</span></code>
 268 can get interpreted, or <code class="docutils literal notranslate"><span class="pre">expre/*</span> <span class="pre">stuff</span> <span class="pre">*/ssion(...)</span></code>.  This
 269 checks for attempt to do stuff like this.</p>
 270 <p>Typically the response will be to kill the entire style; if you
 271 have just a bit of Javascript in the style another rule will catch
 272 that and remove only the Javascript from the style; this catches
 273 more sneaky attempts.</p>
 274 </dd></dl>
 275
 276 <dl class="py method">
 277 <dt id="lxml.html.clean.Cleaner._kill_elements">
 278 <code class="sig-name descname">_kill_elements</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">doc</span></em>, <em class="sig-param"><span class="n">condition</span></em>, <em class="sig-param"><span class="n">iterate</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner._kill_elements" title="Permalink to this definition">¶</a></dt>
 279 <dd></dd></dl>
 280
 281 <dl class="py method">
 282 <dt id="lxml.html.clean.Cleaner._remove_javascript_link">
 283 <code class="sig-name descname">_remove_javascript_link</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">link</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner._remove_javascript_link" title="Permalink to this definition">¶</a></dt>
 284 <dd></dd></dl>
 285
 286 <dl class="py method">
 287 <dt id="lxml.html.clean.Cleaner._substitute_comments">
 288 <code class="sig-name descname">_substitute_comments</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">string</span></em>, <em class="sig-param"><span class="n">count</span><span class="o">=</span><span class="default_value">0</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner._substitute_comments" title="Permalink to this definition">¶</a></dt>
 289 <dd><p>Return the string obtained by replacing the leftmost non-overlapping occurrences of pattern in string by the replacement repl.</p>
 290 </dd></dl>
 291
 292 <dl class="py method">
 293 <dt id="lxml.html.clean.Cleaner.allow_element">
 294 <code class="sig-name descname">allow_element</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">el</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner.allow_element" title="Permalink to this definition">¶</a></dt>
 295 <dd><p>Decide whether an element is configured to be accepted or rejected.</p>
 296 <dl class="field-list simple">
 297 <dt class="field-odd">Parameters</dt>
 298 <dd class="field-odd"><p><strong>el</strong> – an element.</p>
 299 </dd>
 300 <dt class="field-even">Returns</dt>
 301 <dd class="field-even"><p>true to accept the element or false to reject/discard it.</p>
 302 </dd>
 303 </dl>
 304 </dd></dl>
 305
 306 <dl class="py method">
 307 <dt id="lxml.html.clean.Cleaner.allow_embedded_url">
 308 <code class="sig-name descname">allow_embedded_url</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">el</span></em>, <em class="sig-param"><span class="n">url</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner.allow_embedded_url" title="Permalink to this definition">¶</a></dt>
 309 <dd><p>Decide whether a URL that was found in an element’s attributes or text
 310 if configured to be accepted or rejected.</p>
 311 <dl class="field-list simple">
 312 <dt class="field-odd">Parameters</dt>
 313 <dd class="field-odd"><ul class="simple">
 314 <li><p><strong>el</strong> – an element.</p></li>
 315 <li><p><strong>url</strong> – a URL found on the element.</p></li>
 316 </ul>
 317 </dd>
 318 <dt class="field-even">Returns</dt>
 319 <dd class="field-even"><p>true to accept the URL and false to reject it.</p>
 320 </dd>
 321 </dl>
 322 </dd></dl>
 323
 324 <dl class="py method">
 325 <dt id="lxml.html.clean.Cleaner.allow_follow">
 326 <code class="sig-name descname">allow_follow</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">anchor</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner.allow_follow" title="Permalink to this definition">¶</a></dt>
 327 <dd><p>Override to suppress rel=”nofollow” on some anchors.</p>
 328 </dd></dl>
 329
 330 <dl class="py method">
 331 <dt id="lxml.html.clean.Cleaner.clean_html">
 332 <code class="sig-name descname">clean_html</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">html</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner.clean_html" title="Permalink to this definition">¶</a></dt>
 333 <dd></dd></dl>
 334
 335 <dl class="py method">
 336 <dt id="lxml.html.clean.Cleaner.kill_conditional_comments">
 337 <code class="sig-name descname">kill_conditional_comments</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">doc</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.Cleaner.kill_conditional_comments" title="Permalink to this definition">¶</a></dt>
 338 <dd><p>IE conditional comments basically embed HTML that the parser
 339 doesn’t normally see.  We can’t allow anything like that, so
 340 we’ll kill any comments that could be conditional.</p>
 341 </dd></dl>
 342
 343 <dl class="py attribute">
 344 <dt id="lxml.html.clean.Cleaner._tag_link_attrs">
 345 <code class="sig-name descname">_tag_link_attrs</code><em class="property"> = {'a': 'href', 'applet': ['code', 'object'], 'embed': 'src', 'iframe': 'src', 'layer': 'src', 'link': 'href', 'script': 'src'}</em><a class="headerlink" href="#lxml.html.clean.Cleaner._tag_link_attrs" title="Permalink to this definition">¶</a></dt>
 346 <dd></dd></dl>
 347
 348 <dl class="py attribute">
 349 <dt id="lxml.html.clean.Cleaner.add_nofollow">
 350 <code class="sig-name descname">add_nofollow</code><em class="property"> = False</em><a class="headerlink" href="#lxml.html.clean.Cleaner.add_nofollow" title="Permalink to this definition">¶</a></dt>
 351 <dd></dd></dl>
 352
 353 <dl class="py attribute">
 354 <dt id="lxml.html.clean.Cleaner.allow_tags">
 355 <code class="sig-name descname">allow_tags</code><em class="property"> = None</em><a class="headerlink" href="#lxml.html.clean.Cleaner.allow_tags" title="Permalink to this definition">¶</a></dt>
 356 <dd></dd></dl>
 357
 358 <dl class="py attribute">
 359 <dt id="lxml.html.clean.Cleaner.annoying_tags">
 360 <code class="sig-name descname">annoying_tags</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.annoying_tags" title="Permalink to this definition">¶</a></dt>
 361 <dd></dd></dl>
 362
 363 <dl class="py attribute">
 364 <dt id="lxml.html.clean.Cleaner.comments">
 365 <code class="sig-name descname">comments</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.comments" title="Permalink to this definition">¶</a></dt>
 366 <dd></dd></dl>
 367
 368 <dl class="py attribute">
 369 <dt id="lxml.html.clean.Cleaner.embedded">
 370 <code class="sig-name descname">embedded</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.embedded" title="Permalink to this definition">¶</a></dt>
 371 <dd></dd></dl>
 372
 373 <dl class="py attribute">
 374 <dt id="lxml.html.clean.Cleaner.forms">
 375 <code class="sig-name descname">forms</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.forms" title="Permalink to this definition">¶</a></dt>
 376 <dd></dd></dl>
 377
 378 <dl class="py attribute">
 379 <dt id="lxml.html.clean.Cleaner.frames">
 380 <code class="sig-name descname">frames</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.frames" title="Permalink to this definition">¶</a></dt>
 381 <dd></dd></dl>
 382
 383 <dl class="py attribute">
 384 <dt id="lxml.html.clean.Cleaner.host_whitelist">
 385 <code class="sig-name descname">host_whitelist</code><em class="property"> = ()</em><a class="headerlink" href="#lxml.html.clean.Cleaner.host_whitelist" title="Permalink to this definition">¶</a></dt>
 386 <dd></dd></dl>
 387
 388 <dl class="py attribute">
 389 <dt id="lxml.html.clean.Cleaner.inline_style">
 390 <code class="sig-name descname">inline_style</code><em class="property"> = None</em><a class="headerlink" href="#lxml.html.clean.Cleaner.inline_style" title="Permalink to this definition">¶</a></dt>
 391 <dd></dd></dl>
 392
 393 <dl class="py attribute">
 394 <dt id="lxml.html.clean.Cleaner.javascript">
 395 <code class="sig-name descname">javascript</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.javascript" title="Permalink to this definition">¶</a></dt>
 396 <dd></dd></dl>
 397
 398 <dl class="py attribute">
 399 <dt id="lxml.html.clean.Cleaner.kill_tags">
 400 <code class="sig-name descname">kill_tags</code><em class="property"> = None</em><a class="headerlink" href="#lxml.html.clean.Cleaner.kill_tags" title="Permalink to this definition">¶</a></dt>
 401 <dd></dd></dl>
 402
 403 <dl class="py attribute">
 404 <dt id="lxml.html.clean.Cleaner.links">
 405 <code class="sig-name descname">links</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.links" title="Permalink to this definition">¶</a></dt>
 406 <dd></dd></dl>
 407
 408 <dl class="py attribute">
 409 <dt id="lxml.html.clean.Cleaner.meta">
 410 <code class="sig-name descname">meta</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.meta" title="Permalink to this definition">¶</a></dt>
 411 <dd></dd></dl>
 412
 413 <dl class="py attribute">
 414 <dt id="lxml.html.clean.Cleaner.page_structure">
 415 <code class="sig-name descname">page_structure</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.page_structure" title="Permalink to this definition">¶</a></dt>
 416 <dd></dd></dl>
 417
 418 <dl class="py attribute">
 419 <dt id="lxml.html.clean.Cleaner.processing_instructions">
 420 <code class="sig-name descname">processing_instructions</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.processing_instructions" title="Permalink to this definition">¶</a></dt>
 421 <dd></dd></dl>
 422
 423 <dl class="py attribute">
 424 <dt id="lxml.html.clean.Cleaner.remove_tags">
 425 <code class="sig-name descname">remove_tags</code><em class="property"> = None</em><a class="headerlink" href="#lxml.html.clean.Cleaner.remove_tags" title="Permalink to this definition">¶</a></dt>
 426 <dd></dd></dl>
 427
 428 <dl class="py attribute">
 429 <dt id="lxml.html.clean.Cleaner.remove_unknown_tags">
 430 <code class="sig-name descname">remove_unknown_tags</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.remove_unknown_tags" title="Permalink to this definition">¶</a></dt>
 431 <dd></dd></dl>
 432
 433 <dl class="py attribute">
 434 <dt id="lxml.html.clean.Cleaner.safe_attrs">
 435 <code class="sig-name descname">safe_attrs</code><em class="property"> = frozenset({'abbr', 'accept', 'accept-charset', 'accesskey', 'action', 'align', 'alt', 'axis', 'border', 'cellpadding', 'cellspacing', 'char', 'charoff', 'charset', 'checked', 'cite', 'class', 'clear', 'color', 'cols', 'colspan', 'compact', 'coords', 'datetime', 'dir', 'disabled', 'enctype', 'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', 'id', 'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method', 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly', 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title', 'type', 'usemap', 'valign', 'value', 'vspace', 'width'})</em><a class="headerlink" href="#lxml.html.clean.Cleaner.safe_attrs" title="Permalink to this definition">¶</a></dt>
 436 <dd></dd></dl>
 437
 438 <dl class="py attribute">
 439 <dt id="lxml.html.clean.Cleaner.safe_attrs_only">
 440 <code class="sig-name descname">safe_attrs_only</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.safe_attrs_only" title="Permalink to this definition">¶</a></dt>
 441 <dd></dd></dl>
 442
 443 <dl class="py attribute">
 444 <dt id="lxml.html.clean.Cleaner.scripts">
 445 <code class="sig-name descname">scripts</code><em class="property"> = True</em><a class="headerlink" href="#lxml.html.clean.Cleaner.scripts" title="Permalink to this definition">¶</a></dt>
 446 <dd></dd></dl>
 447
 448 <dl class="py attribute">
 449 <dt id="lxml.html.clean.Cleaner.style">
 450 <code class="sig-name descname">style</code><em class="property"> = False</em><a class="headerlink" href="#lxml.html.clean.Cleaner.style" title="Permalink to this definition">¶</a></dt>
 451 <dd></dd></dl>
 452
 453 <dl class="py attribute">
 454 <dt id="lxml.html.clean.Cleaner.whitelist_tags">
 455 <code class="sig-name descname">whitelist_tags</code><em class="property"> = {'embed', 'iframe'}</em><a class="headerlink" href="#lxml.html.clean.Cleaner.whitelist_tags" title="Permalink to this definition">¶</a></dt>
 456 <dd></dd></dl>
 457
 458 </dd></dl>
 459
 460 <dl class="py function">
 461 <dt id="lxml.html.clean._break_text">
 462 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">_break_text</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">text</span></em>, <em class="sig-param"><span class="n">max_width</span></em>, <em class="sig-param"><span class="n">break_character</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean._break_text" title="Permalink to this definition">¶</a></dt>
 463 <dd></dd></dl>
 464
 465 <dl class="py function">
 466 <dt id="lxml.html.clean._insert_break">
 467 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">_insert_break</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">word</span></em>, <em class="sig-param"><span class="n">width</span></em>, <em class="sig-param"><span class="n">break_character</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean._insert_break" title="Permalink to this definition">¶</a></dt>
 468 <dd></dd></dl>
 469
 470 <dl class="py function">
 471 <dt id="lxml.html.clean._is_image_dataurl">
 472 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">_is_image_dataurl</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">string</span></em>, <em class="sig-param"><span class="n">pos</span><span class="o">=</span><span class="default_value">0</span></em>, <em class="sig-param"><span class="n">endpos</span><span class="o">=</span><span class="default_value">9223372036854775807</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean._is_image_dataurl" title="Permalink to this definition">¶</a></dt>
 473 <dd><p>Scan through string looking for a match, and return a corresponding match object instance.</p>
 474 <p>Return None if no position in the string matches.</p>
 475 </dd></dl>
 476
 477 <dl class="py function">
 478 <dt id="lxml.html.clean._is_javascript_scheme">
 479 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">_is_javascript_scheme</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">s</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean._is_javascript_scheme" title="Permalink to this definition">¶</a></dt>
 480 <dd></dd></dl>
 481
 482 <dl class="py function">
 483 <dt id="lxml.html.clean._is_possibly_malicious_scheme">
 484 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">_is_possibly_malicious_scheme</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">string</span></em>, <em class="sig-param"><span class="n">pos</span><span class="o">=</span><span class="default_value">0</span></em>, <em class="sig-param"><span class="n">endpos</span><span class="o">=</span><span class="default_value">9223372036854775807</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean._is_possibly_malicious_scheme" title="Permalink to this definition">¶</a></dt>
 485 <dd><p>Scan through string looking for a match, and return a corresponding match object instance.</p>
 486 <p>Return None if no position in the string matches.</p>
 487 </dd></dl>
 488
 489 <dl class="py function">
 490 <dt id="lxml.html.clean._link_text">
 491 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">_link_text</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">text</span></em>, <em class="sig-param"><span class="n">link_regexes</span></em>, <em class="sig-param"><span class="n">avoid_hosts</span></em>, <em class="sig-param"><span class="n">factory</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean._link_text" title="Permalink to this definition">¶</a></dt>
 492 <dd></dd></dl>
 493
 494 <dl class="py function">
 495 <dt id="lxml.html.clean._substitute_whitespace">
 496 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">_substitute_whitespace</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">repl</span></em>, <em class="sig-param"><span class="n">string</span></em>, <em class="sig-param"><span class="n">count</span><span class="o">=</span><span class="default_value">0</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean._substitute_whitespace" title="Permalink to this definition">¶</a></dt>
 497 <dd><p>Return the string obtained by replacing the leftmost non-overlapping occurrences of pattern in string by the replacement repl.</p>
 498 </dd></dl>
 499
 500 <dl class="py function">
 501 <dt id="lxml.html.clean.autolink">
 502 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">autolink</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">el</span></em>, <em class="sig-param"><span class="n">link_regexes</span><span class="o">=</span><span class="default_value">[re.compile('(?P&lt;body&gt;https?://(?P&lt;host&gt;[a-z0-9._-]+)(?:/[/\\-_.,a-z0-9%&amp;?;=~]*)?(?:\\([/\\-_.,a-z0-9%&amp;?;=~]*\\))?)', re.IGNORECASE), re.compile('mailto:(?P&lt;body&gt;[a-z0-9._-]+&#64;(?P&lt;host&gt;[a-z0-9_.-]+[a-z]))', re.IGNORECASE)]</span></em>, <em class="sig-param"><span class="n">avoid_elements</span><span class="o">=</span><span class="default_value">['textarea', 'pre', 'code', 'head', 'select', 'a']</span></em>, <em class="sig-param"><span class="n">avoid_hosts</span><span class="o">=</span><span class="default_value">[re.compile('^localhost', re.IGNORECASE), re.compile('\\bexample\\.(?:com|org|net)$', re.IGNORECASE), re.compile('^127\\.0\\.0\\.1$')]</span></em>, <em class="sig-param"><span class="n">avoid_classes</span><span class="o">=</span><span class="default_value">['nolink']</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.autolink" title="Permalink to this definition">¶</a></dt>
 503 <dd><p>Turn any URLs into links.</p>
 504 <p>It will search for links identified by the given regular
 505 expressions (by default mailto and http(s) links).</p>
 506 <p>It won’t link text in an element in avoid_elements, or an element
 507 with a class in avoid_classes.  It won’t link to anything with a
 508 host that matches one of the regular expressions in avoid_hosts
 509 (default localhost and 127.0.0.1).</p>
 510 <p>If you pass in an element, the element’s tail will not be
 511 substituted, only the contents of the element.</p>
 512 </dd></dl>
 513
 514 <dl class="py function">
 515 <dt id="lxml.html.clean.autolink_html">
 516 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">autolink_html</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">html</span></em>, <em class="sig-param"><span class="o">*</span><span class="n">args</span></em>, <em class="sig-param"><span class="o">**</span><span class="n">kw</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.autolink_html" title="Permalink to this definition">¶</a></dt>
 517 <dd><p>Turn any URLs into links.</p>
 518 <p>It will search for links identified by the given regular
 519 expressions (by default mailto and http(s) links).</p>
 520 <p>It won’t link text in an element in avoid_elements, or an element
 521 with a class in avoid_classes.  It won’t link to anything with a
 522 host that matches one of the regular expressions in avoid_hosts
 523 (default localhost and 127.0.0.1).</p>
 524 <p>If you pass in an element, the element’s tail will not be
 525 substituted, only the contents of the element.</p>
 526 </dd></dl>
 527
 528 <dl class="py function">
 529 <dt id="lxml.html.clean.clean_html">
 530 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">clean_html</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">html</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.clean_html" title="Permalink to this definition">¶</a></dt>
 531 <dd></dd></dl>
 532
 533 <dl class="py function">
 534 <dt id="lxml.html.clean.word_break">
 535 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">word_break</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">el</span></em>, <em class="sig-param"><span class="n">max_width</span><span class="o">=</span><span class="default_value">40</span></em>, <em class="sig-param"><span class="n">avoid_elements</span><span class="o">=</span><span class="default_value">['pre', 'textarea', 'code']</span></em>, <em class="sig-param"><span class="n">avoid_classes</span><span class="o">=</span><span class="default_value">['nobreak']</span></em>, <em class="sig-param"><span class="n">break_character</span><span class="o">=</span><span class="default_value">'\u200b'</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.word_break" title="Permalink to this definition">¶</a></dt>
 536 <dd><p>Breaks any long words found in the body of the text (not attributes).</p>
 537 <p>Doesn’t effect any of the tags in avoid_elements, by default
 538 <code class="docutils literal notranslate"><span class="pre">&lt;textarea&gt;</span></code> and <code class="docutils literal notranslate"><span class="pre">&lt;pre&gt;</span></code></p>
 539 <p>Breaks words by inserting &amp;#8203;, which is a unicode character
 540 for Zero Width Space character.  This generally takes up no space
 541 in rendering, but does copy as a space, and in monospace contexts
 542 usually takes up space.</p>
 543 <p>See <a class="reference external" href="http://www.cs.tut.fi/~jkorpela/html/nobr.html">http://www.cs.tut.fi/~jkorpela/html/nobr.html</a> for a discussion</p>
 544 </dd></dl>
 545
 546 <dl class="py function">
 547 <dt id="lxml.html.clean.word_break_html">
 548 <code class="sig-prename descclassname">lxml.html.clean.</code><code class="sig-name descname">word_break_html</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">html</span></em>, <em class="sig-param"><span class="o">*</span><span class="n">args</span></em>, <em class="sig-param"><span class="o">**</span><span class="n">kw</span></em><span class="sig-paren">)</span><a class="headerlink" href="#lxml.html.clean.word_break_html" title="Permalink to this definition">¶</a></dt>
 549 <dd></dd></dl>
 550
 551 </div>
 552
 553
 554            </div>
 555
 556           </div>
 557           <footer>
 558
 559     <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
 560
 561         <a href="lxml.html.defs.html" class="btn btn-neutral float-right" title="lxml.html.defs module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
 562
 563
 564         <a href="lxml.html.builder.html" class="btn btn-neutral float-left" title="lxml.html.builder module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
 565
 566     </div>
 567
 568
 569   <hr/>
 570
 571   <div role="contentinfo">
 572     <p>
 573
 574         &copy; Copyright 2020, lxml dev team
 575
 576     </p>
 577   </div>
 578
 579
 580
 581     Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a
 582
 583     <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a>
 584
 585     provided by <a href="https://readthedocs.org">Read the Docs</a>.
 586
 587 </footer>
 588
 589         </div>
 590       </div>
 591
 592     </section>
 593
 594   </div>
 595
 596
 597   <script type="text/javascript">
 598       jQuery(function () {
 599           SphinxRtdTheme.Navigation.enable(true);
 600       });
 601   </script>
 602
 603
 604
 605
 606
 607
 608 </body>
 609 </html>