661 lines
51 KiB
HTML
661 lines
51 KiB
HTML
<!DOCTYPE html>
|
||
|
||
<html lang="en" data-content_root="../">
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
|
||
<meta property="og:title" content="html.parser — Simple HTML and XHTML parser" />
|
||
<meta property="og:type" content="website" />
|
||
<meta property="og:url" content="https://docs.python.org/3/library/html.parser.html" />
|
||
<meta property="og:site_name" content="Python documentation" />
|
||
<meta property="og:description" content="Source code: Lib/html/parser.py This module defines a class HTMLParser which serves as the basis for parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML. Example HTML Parser..." />
|
||
<meta property="og:image" content="https://docs.python.org/3/_static/og-image.png" />
|
||
<meta property="og:image:alt" content="Python documentation" />
|
||
<meta name="description" content="Source code: Lib/html/parser.py This module defines a class HTMLParser which serves as the basis for parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML. Example HTML Parser..." />
|
||
<meta property="og:image:width" content="200">
|
||
<meta property="og:image:height" content="200">
|
||
<meta name="theme-color" content="#3776ab">
|
||
|
||
<title>html.parser — Simple HTML and XHTML parser — Python 3.13.3 documentation</title><meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
|
||
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=b86133f3" />
|
||
<link rel="stylesheet" type="text/css" href="../_static/pydoctheme.css?v=23252803" />
|
||
<link id="pygments_dark_css" media="(prefers-color-scheme: dark)" rel="stylesheet" type="text/css" href="../_static/pygments_dark.css?v=5349f25f" />
|
||
|
||
<script src="../_static/documentation_options.js?v=5d57ca2d"></script>
|
||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
|
||
<script src="../_static/sidebar.js"></script>
|
||
|
||
<link rel="search" type="application/opensearchdescription+xml"
|
||
title="Search within Python 3.13.3 documentation"
|
||
href="../_static/opensearch.xml"/>
|
||
<link rel="author" title="About these documents" href="../about.html" />
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="copyright" title="Copyright" href="../copyright.html" />
|
||
<link rel="next" title="html.entities — Definitions of HTML general entities" href="html.entities.html" />
|
||
<link rel="prev" title="html — HyperText Markup Language support" href="html.html" />
|
||
|
||
<link rel="canonical" href="https://docs.python.org/3/library/html.parser.html">
|
||
|
||
|
||
|
||
|
||
|
||
<style>
|
||
@media only screen {
|
||
table.full-width-table {
|
||
width: 100%;
|
||
}
|
||
}
|
||
</style>
|
||
<link rel="stylesheet" href="../_static/pydoctheme_dark.css" media="(prefers-color-scheme: dark)" id="pydoctheme_dark_css">
|
||
<link rel="shortcut icon" type="image/png" href="../_static/py.svg" />
|
||
<script type="text/javascript" src="../_static/copybutton.js"></script>
|
||
<script type="text/javascript" src="../_static/menu.js"></script>
|
||
<script type="text/javascript" src="../_static/search-focus.js"></script>
|
||
<script type="text/javascript" src="../_static/themetoggle.js"></script>
|
||
<script type="text/javascript" src="../_static/rtd_switcher.js"></script>
|
||
<meta name="readthedocs-addons-api-version" content="1">
|
||
|
||
</head>
|
||
<body>
|
||
<div class="mobile-nav">
|
||
<input type="checkbox" id="menuToggler" class="toggler__input" aria-controls="navigation"
|
||
aria-pressed="false" aria-expanded="false" role="button" aria-label="Menu" />
|
||
<nav class="nav-content" role="navigation">
|
||
<label for="menuToggler" class="toggler__label">
|
||
<span></span>
|
||
</label>
|
||
<span class="nav-items-wrapper">
|
||
<a href="https://www.python.org/" class="nav-logo">
|
||
<img src="../_static/py.svg" alt="Python logo"/>
|
||
</a>
|
||
<span class="version_switcher_placeholder"></span>
|
||
<form role="search" class="search" action="../search.html" method="get">
|
||
<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" class="search-icon">
|
||
<path fill-rule="nonzero" fill="currentColor" d="M15.5 14h-.79l-.28-.27a6.5 6.5 0 001.48-5.34c-.47-2.78-2.79-5-5.59-5.34a6.505 6.505 0 00-7.27 7.27c.34 2.8 2.56 5.12 5.34 5.59a6.5 6.5 0 005.34-1.48l.27.28v.79l4.25 4.25c.41.41 1.08.41 1.49 0 .41-.41.41-1.08 0-1.49L15.5 14zm-6 0C7.01 14 5 11.99 5 9.5S7.01 5 9.5 5 14 7.01 14 9.5 11.99 14 9.5 14z"></path>
|
||
</svg>
|
||
<input placeholder="Quick search" aria-label="Quick search" type="search" name="q" />
|
||
<input type="submit" value="Go"/>
|
||
</form>
|
||
</span>
|
||
</nav>
|
||
<div class="menu-wrapper">
|
||
<nav class="menu" role="navigation" aria-label="main navigation">
|
||
<div class="language_switcher_placeholder"></div>
|
||
|
||
<label class="theme-selector-label">
|
||
Theme
|
||
<select class="theme-selector" oninput="activateTheme(this.value)">
|
||
<option value="auto" selected>Auto</option>
|
||
<option value="light">Light</option>
|
||
<option value="dark">Dark</option>
|
||
</select>
|
||
</label>
|
||
<div>
|
||
<h3><a href="../contents.html">Table of Contents</a></h3>
|
||
<ul>
|
||
<li><a class="reference internal" href="#"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.parser</span></code> — Simple HTML and XHTML parser</a><ul>
|
||
<li><a class="reference internal" href="#example-html-parser-application">Example HTML Parser Application</a></li>
|
||
<li><a class="reference internal" href="#htmlparser-methods"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code> Methods</a></li>
|
||
<li><a class="reference internal" href="#examples">Examples</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
|
||
</div>
|
||
<div>
|
||
<h4>Previous topic</h4>
|
||
<p class="topless"><a href="html.html"
|
||
title="previous chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html</span></code> — HyperText Markup Language support</a></p>
|
||
</div>
|
||
<div>
|
||
<h4>Next topic</h4>
|
||
<p class="topless"><a href="html.entities.html"
|
||
title="next chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.entities</span></code> — Definitions of HTML general entities</a></p>
|
||
</div>
|
||
<div role="note" aria-label="source link">
|
||
<h3>This Page</h3>
|
||
<ul class="this-page-menu">
|
||
<li><a href="../bugs.html">Report a Bug</a></li>
|
||
<li>
|
||
<a href="https://github.com/python/cpython/blob/main/Doc/library/html.parser.rst"
|
||
rel="nofollow">Show Source
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
<div class="related" role="navigation" aria-label="Related">
|
||
<h3>Navigation</h3>
|
||
<ul>
|
||
<li class="right" style="margin-right: 10px">
|
||
<a href="../genindex.html" title="General Index"
|
||
accesskey="I">index</a></li>
|
||
<li class="right" >
|
||
<a href="../py-modindex.html" title="Python Module Index"
|
||
>modules</a> |</li>
|
||
<li class="right" >
|
||
<a href="html.entities.html" title="html.entities — Definitions of HTML general entities"
|
||
accesskey="N">next</a> |</li>
|
||
<li class="right" >
|
||
<a href="html.html" title="html — HyperText Markup Language support"
|
||
accesskey="P">previous</a> |</li>
|
||
|
||
<li><img src="../_static/py.svg" alt="Python logo" style="vertical-align: middle; margin-top: -1px"/></li>
|
||
<li><a href="https://www.python.org/">Python</a> »</li>
|
||
<li class="switchers">
|
||
<div class="language_switcher_placeholder"></div>
|
||
<div class="version_switcher_placeholder"></div>
|
||
</li>
|
||
<li>
|
||
|
||
</li>
|
||
<li id="cpython-language-and-version">
|
||
<a href="../index.html">3.13.3 Documentation</a> »
|
||
</li>
|
||
|
||
<li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> »</li>
|
||
<li class="nav-item nav-item-2"><a href="markup.html" accesskey="U">Structured Markup Processing Tools</a> »</li>
|
||
<li class="nav-item nav-item-this"><a href=""><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.parser</span></code> — Simple HTML and XHTML parser</a></li>
|
||
<li class="right">
|
||
|
||
|
||
<div class="inline-search" role="search">
|
||
<form class="inline-search" action="../search.html" method="get">
|
||
<input placeholder="Quick search" aria-label="Quick search" type="search" name="q" id="search-box" />
|
||
<input type="submit" value="Go" />
|
||
</form>
|
||
</div>
|
||
|
|
||
</li>
|
||
<li class="right">
|
||
<label class="theme-selector-label">
|
||
Theme
|
||
<select class="theme-selector" oninput="activateTheme(this.value)">
|
||
<option value="auto" selected>Auto</option>
|
||
<option value="light">Light</option>
|
||
<option value="dark">Dark</option>
|
||
</select>
|
||
</label> |</li>
|
||
|
||
</ul>
|
||
</div>
|
||
|
||
<div class="document">
|
||
<div class="documentwrapper">
|
||
<div class="bodywrapper">
|
||
<div class="body" role="main">
|
||
|
||
<section id="module-html.parser">
|
||
<span id="html-parser-simple-html-and-xhtml-parser"></span><h1><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.parser</span></code> — Simple HTML and XHTML parser<a class="headerlink" href="#module-html.parser" title="Link to this heading">¶</a></h1>
|
||
<p><strong>Source code:</strong> <a class="extlink-source reference external" href="https://github.com/python/cpython/tree/3.13/Lib/html/parser.py">Lib/html/parser.py</a></p>
|
||
<hr class="docutils" id="index-0" />
|
||
<p>This module defines a class <a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> which serves as the basis for
|
||
parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML.</p>
|
||
<dl class="py class">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser">
|
||
<em class="property"><span class="k"><span class="pre">class</span></span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">html.parser.</span></span><span class="sig-name descname"><span class="pre">HTMLParser</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="keyword-only-separator o"><abbr title="Keyword-only parameters separator (PEP 3102)"><span class="pre">*</span></abbr></span></em>, <em class="sig-param"><span class="n"><span class="pre">convert_charrefs</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Create a parser instance able to parse invalid markup.</p>
|
||
<p>If <em>convert_charrefs</em> is <code class="docutils literal notranslate"><span class="pre">True</span></code> (the default), all character
|
||
references (except the ones in <code class="docutils literal notranslate"><span class="pre">script</span></code>/<code class="docutils literal notranslate"><span class="pre">style</span></code> elements) are
|
||
automatically converted to the corresponding Unicode characters.</p>
|
||
<p>An <a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> instance is fed HTML data and calls handler methods
|
||
when start tags, end tags, text, comments, and other markup elements are
|
||
encountered. The user should subclass <a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> and override its
|
||
methods to implement the desired behavior.</p>
|
||
<p>This parser does not check that end tags match start tags or call the end-tag
|
||
handler for elements which are closed implicitly by closing an outer element.</p>
|
||
<div class="versionchanged">
|
||
<p><span class="versionmodified changed">Changed in version 3.4: </span><em>convert_charrefs</em> keyword argument added.</p>
|
||
</div>
|
||
<div class="versionchanged">
|
||
<p><span class="versionmodified changed">Changed in version 3.5: </span>The default value for argument <em>convert_charrefs</em> is now <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<section id="example-html-parser-application">
|
||
<h2>Example HTML Parser Application<a class="headerlink" href="#example-html-parser-application" title="Link to this heading">¶</a></h2>
|
||
<p>As a basic example, below is a simple HTML parser that uses the
|
||
<a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> class to print out start tags, end tags, and data
|
||
as they are encountered:</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><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>
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyHTMLParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">):</span>
|
||
<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>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Encountered a start tag:"</span><span class="p">,</span> <span class="n">tag</span><span class="p">)</span>
|
||
|
||
<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>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Encountered an end tag :"</span><span class="p">,</span> <span class="n">tag</span><span class="p">)</span>
|
||
|
||
<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>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Encountered some data :"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
|
||
|
||
<span class="n">parser</span> <span class="o">=</span> <span class="n">MyHTMLParser</span><span class="p">()</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<html><head><title>Test</title></head>'</span>
|
||
<span class="s1">'<body><h1>Parse me!</h1></body></html>'</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>The output will then be:</p>
|
||
<div class="highlight-none notranslate"><div class="highlight"><pre><span></span>Encountered a start tag: html
|
||
Encountered a start tag: head
|
||
Encountered a start tag: title
|
||
Encountered some data : Test
|
||
Encountered an end tag : title
|
||
Encountered an end tag : head
|
||
Encountered a start tag: body
|
||
Encountered a start tag: h1
|
||
Encountered some data : Parse me!
|
||
Encountered an end tag : h1
|
||
Encountered an end tag : body
|
||
Encountered an end tag : html
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
<section id="htmlparser-methods">
|
||
<h2><a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> Methods<a class="headerlink" href="#htmlparser-methods" title="Link to this heading">¶</a></h2>
|
||
<p><a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> instances have the following methods:</p>
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.feed">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">feed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.feed" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Feed some text to the parser. It is processed insofar as it consists of
|
||
complete elements; incomplete data is buffered until more data is fed or
|
||
<a class="reference internal" href="#html.parser.HTMLParser.close" title="html.parser.HTMLParser.close"><code class="xref py py-meth docutils literal notranslate"><span class="pre">close()</span></code></a> is called. <em>data</em> must be <a class="reference internal" href="stdtypes.html#str" title="str"><code class="xref py py-class docutils literal notranslate"><span class="pre">str</span></code></a>.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.close">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.close" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Force processing of all buffered data as if it were followed by an end-of-file
|
||
mark. This method may be redefined by a derived class to define additional
|
||
processing at the end of the input, but the redefined version should always call
|
||
the <a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> base class method <a class="reference internal" href="#html.parser.HTMLParser.close" title="html.parser.HTMLParser.close"><code class="xref py py-meth docutils literal notranslate"><span class="pre">close()</span></code></a>.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.reset">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.reset" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Reset the instance. Loses all unprocessed data. This is called implicitly at
|
||
instantiation time.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.getpos">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">getpos</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.getpos" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Return current line number and offset.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.get_starttag_text">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">get_starttag_text</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.get_starttag_text" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Return the text of the most recently opened start tag. This should not normally
|
||
be needed for structured processing, but may be useful in dealing with HTML “as
|
||
deployed” or for re-generating input with minimal changes (whitespace between
|
||
attributes can be preserved, etc.).</p>
|
||
</dd></dl>
|
||
|
||
<p>The following methods are called when data or markup elements are encountered
|
||
and they are meant to be overridden in a subclass. The base class
|
||
implementations do nothing (except for <a class="reference internal" href="#html.parser.HTMLParser.handle_startendtag" title="html.parser.HTMLParser.handle_startendtag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_startendtag()</span></code></a>):</p>
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_starttag">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_starttag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_starttag" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called to handle the start tag of an element (e.g. <code class="docutils literal notranslate"><span class="pre"><div</span> <span class="pre">id="main"></span></code>).</p>
|
||
<p>The <em>tag</em> argument is the name of the tag converted to lower case. The <em>attrs</em>
|
||
argument is a list of <code class="docutils literal notranslate"><span class="pre">(name,</span> <span class="pre">value)</span></code> pairs containing the attributes found
|
||
inside the tag’s <code class="docutils literal notranslate"><span class="pre"><></span></code> brackets. The <em>name</em> will be translated to lower case,
|
||
and quotes in the <em>value</em> have been removed, and character and entity references
|
||
have been replaced.</p>
|
||
<p>For instance, for the tag <code class="docutils literal notranslate"><span class="pre"><A</span> <span class="pre">HREF="https://www.cwi.nl/"></span></code>, this method
|
||
would be called as <code class="docutils literal notranslate"><span class="pre">handle_starttag('a',</span> <span class="pre">[('href',</span> <span class="pre">'https://www.cwi.nl/')])</span></code>.</p>
|
||
<p>All entity references from <a class="reference internal" href="html.entities.html#module-html.entities" title="html.entities: Definitions of HTML general entities."><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.entities</span></code></a> are replaced in the attribute
|
||
values.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_endtag">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_endtag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_endtag" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called to handle the end tag of an element (e.g. <code class="docutils literal notranslate"><span class="pre"></div></span></code>).</p>
|
||
<p>The <em>tag</em> argument is the name of the tag converted to lower case.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_startendtag">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_startendtag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_startendtag" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Similar to <a class="reference internal" href="#html.parser.HTMLParser.handle_starttag" title="html.parser.HTMLParser.handle_starttag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_starttag()</span></code></a>, but called when the parser encounters an
|
||
XHTML-style empty tag (<code class="docutils literal notranslate"><span class="pre"><img</span> <span class="pre">...</span> <span class="pre">/></span></code>). This method may be overridden by
|
||
subclasses which require this particular lexical information; the default
|
||
implementation simply calls <a class="reference internal" href="#html.parser.HTMLParser.handle_starttag" title="html.parser.HTMLParser.handle_starttag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_starttag()</span></code></a> and <a class="reference internal" href="#html.parser.HTMLParser.handle_endtag" title="html.parser.HTMLParser.handle_endtag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_endtag()</span></code></a>.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_data">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_data" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called to process arbitrary data (e.g. text nodes and the
|
||
content of <code class="docutils literal notranslate"><span class="pre"><script>...</script></span></code> and <code class="docutils literal notranslate"><span class="pre"><style>...</style></span></code>).</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_entityref">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_entityref</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_entityref" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called to process a named character reference of the form
|
||
<code class="docutils literal notranslate"><span class="pre">&name;</span></code> (e.g. <code class="docutils literal notranslate"><span class="pre">&gt;</span></code>), where <em>name</em> is a general entity reference
|
||
(e.g. <code class="docutils literal notranslate"><span class="pre">'gt'</span></code>). This method is never called if <em>convert_charrefs</em> is
|
||
<code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_charref">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_charref</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_charref" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called to process decimal and hexadecimal numeric character
|
||
references of the form <code class="samp docutils literal notranslate"><span class="pre">&#</span><em><span class="pre">NNN</span></em><span class="pre">;</span></code> and <code class="samp docutils literal notranslate"><span class="pre">&#x</span><em><span class="pre">NNN</span></em><span class="pre">;</span></code>. For example, the decimal
|
||
equivalent for <code class="docutils literal notranslate"><span class="pre">&gt;</span></code> is <code class="docutils literal notranslate"><span class="pre">&#62;</span></code>, whereas the hexadecimal is <code class="docutils literal notranslate"><span class="pre">&#x3E;</span></code>;
|
||
in this case the method will receive <code class="docutils literal notranslate"><span class="pre">'62'</span></code> or <code class="docutils literal notranslate"><span class="pre">'x3E'</span></code>. This method
|
||
is never called if <em>convert_charrefs</em> is <code class="docutils literal notranslate"><span class="pre">True</span></code>.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_comment">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_comment</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_comment" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called when a comment is encountered (e.g. <code class="docutils literal notranslate"><span class="pre"><!--comment--></span></code>).</p>
|
||
<p>For example, the comment <code class="docutils literal notranslate"><span class="pre"><!--</span> <span class="pre">comment</span> <span class="pre">--></span></code> will cause this method to be
|
||
called with the argument <code class="docutils literal notranslate"><span class="pre">'</span> <span class="pre">comment</span> <span class="pre">'</span></code>.</p>
|
||
<p>The content of Internet Explorer conditional comments (condcoms) will also be
|
||
sent to this method, so, for <code class="docutils literal notranslate"><span class="pre"><!--[if</span> <span class="pre">IE</span> <span class="pre">9]>IE9-specific</span> <span class="pre">content<![endif]--></span></code>,
|
||
this method will receive <code class="docutils literal notranslate"><span class="pre">'[if</span> <span class="pre">IE</span> <span class="pre">9]>IE9-specific</span> <span class="pre">content<![endif]'</span></code>.</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_decl">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_decl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decl</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_decl" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called to handle an HTML doctype declaration (e.g.
|
||
<code class="docutils literal notranslate"><span class="pre"><!DOCTYPE</span> <span class="pre">html></span></code>).</p>
|
||
<p>The <em>decl</em> parameter will be the entire contents of the declaration inside
|
||
the <code class="docutils literal notranslate"><span class="pre"><!...></span></code> markup (e.g. <code class="docutils literal notranslate"><span class="pre">'DOCTYPE</span> <span class="pre">html'</span></code>).</p>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.handle_pi">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_pi</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_pi" title="Link to this definition">¶</a></dt>
|
||
<dd><p>Method called when a processing instruction is encountered. The <em>data</em>
|
||
parameter will contain the entire processing instruction. For example, for the
|
||
processing instruction <code class="docutils literal notranslate"><span class="pre"><?proc</span> <span class="pre">color='red'></span></code>, this method would be called as
|
||
<code class="docutils literal notranslate"><span class="pre">handle_pi("proc</span> <span class="pre">color='red'")</span></code>. It is intended to be overridden by a derived
|
||
class; the base class implementation does nothing.</p>
|
||
<div class="admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>The <a class="reference internal" href="#html.parser.HTMLParser" title="html.parser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> class uses the SGML syntactic rules for processing
|
||
instructions. An XHTML processing instruction using the trailing <code class="docutils literal notranslate"><span class="pre">'?'</span></code> will
|
||
cause the <code class="docutils literal notranslate"><span class="pre">'?'</span></code> to be included in <em>data</em>.</p>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="py method">
|
||
<dt class="sig sig-object py" id="html.parser.HTMLParser.unknown_decl">
|
||
<span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">unknown_decl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.unknown_decl" title="Link to this definition">¶</a></dt>
|
||
<dd><p>This method is called when an unrecognized declaration is read by the parser.</p>
|
||
<p>The <em>data</em> parameter will be the entire contents of the declaration inside
|
||
the <code class="docutils literal notranslate"><span class="pre"><![...]></span></code> markup. It is sometimes useful to be overridden by a
|
||
derived class. The base class implementation does nothing.</p>
|
||
</dd></dl>
|
||
|
||
</section>
|
||
<section id="examples">
|
||
<span id="htmlparser-examples"></span><h2>Examples<a class="headerlink" href="#examples" title="Link to this heading">¶</a></h2>
|
||
<p>The following class implements a parser that will be used to illustrate more
|
||
examples:</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><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>
|
||
<span class="kn">from</span><span class="w"> </span><span class="nn">html.entities</span><span class="w"> </span><span class="kn">import</span> <span class="n">name2codepoint</span>
|
||
|
||
<span class="k">class</span><span class="w"> </span><span class="nc">MyHTMLParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">):</span>
|
||
<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>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Start tag:"</span><span class="p">,</span> <span class="n">tag</span><span class="p">)</span>
|
||
<span class="k">for</span> <span class="n">attr</span> <span class="ow">in</span> <span class="n">attrs</span><span class="p">:</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">" attr:"</span><span class="p">,</span> <span class="n">attr</span><span class="p">)</span>
|
||
|
||
<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>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"End tag :"</span><span class="p">,</span> <span class="n">tag</span><span class="p">)</span>
|
||
|
||
<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>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Data :"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">handle_comment</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Comment :"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
|
||
|
||
<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>
|
||
<span class="n">c</span> <span class="o">=</span> <span class="nb">chr</span><span class="p">(</span><span class="n">name2codepoint</span><span class="p">[</span><span class="n">name</span><span class="p">])</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Named ent:"</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span>
|
||
|
||
<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>
|
||
<span class="k">if</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'x'</span><span class="p">):</span>
|
||
<span class="n">c</span> <span class="o">=</span> <span class="nb">chr</span><span class="p">(</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>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">c</span> <span class="o">=</span> <span class="nb">chr</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">name</span><span class="p">))</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Num ent :"</span><span class="p">,</span> <span class="n">c</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span><span class="w"> </span><span class="nf">handle_decl</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"Decl :"</span><span class="p">,</span> <span class="n">data</span><span class="p">)</span>
|
||
|
||
<span class="n">parser</span> <span class="o">=</span> <span class="n">MyHTMLParser</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Parsing a doctype:</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '</span>
|
||
<span class="gp">... </span> <span class="s1">'"http://www.w3.org/TR/html4/strict.dtd">'</span><span class="p">)</span>
|
||
<span class="go">Decl : DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Parsing an element with a few attributes and a title:</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<img src="python-logo.png" alt="The Python logo">'</span><span class="p">)</span>
|
||
<span class="go">Start tag: img</span>
|
||
<span class="go"> attr: ('src', 'python-logo.png')</span>
|
||
<span class="go"> attr: ('alt', 'The Python logo')</span>
|
||
<span class="gp">>>></span>
|
||
<span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<h1>Python</h1>'</span><span class="p">)</span>
|
||
<span class="go">Start tag: h1</span>
|
||
<span class="go">Data : Python</span>
|
||
<span class="go">End tag : h1</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>The content of <code class="docutils literal notranslate"><span class="pre">script</span></code> and <code class="docutils literal notranslate"><span class="pre">style</span></code> elements is returned as is, without
|
||
further parsing:</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<style type="text/css">#python { color: green }</style>'</span><span class="p">)</span>
|
||
<span class="go">Start tag: style</span>
|
||
<span class="go"> attr: ('type', 'text/css')</span>
|
||
<span class="go">Data : #python { color: green }</span>
|
||
<span class="go">End tag : style</span>
|
||
|
||
<span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<script type="text/javascript">'</span>
|
||
<span class="gp">... </span> <span class="s1">'alert("<strong>hello!</strong>");</script>'</span><span class="p">)</span>
|
||
<span class="go">Start tag: script</span>
|
||
<span class="go"> attr: ('type', 'text/javascript')</span>
|
||
<span class="go">Data : alert("<strong>hello!</strong>");</span>
|
||
<span class="go">End tag : script</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Parsing comments:</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<!-- a comment -->'</span>
|
||
<span class="gp">... </span> <span class="s1">'<!--[if IE 9]>IE-specific content<![endif]-->'</span><span class="p">)</span>
|
||
<span class="go">Comment : a comment</span>
|
||
<span class="go">Comment : [if IE 9]>IE-specific content<![endif]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Parsing named and numeric character references and converting them to the
|
||
correct char (note: these 3 references are all equivalent to <code class="docutils literal notranslate"><span class="pre">'>'</span></code>):</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'&gt;&#62;&#x3E;'</span><span class="p">)</span>
|
||
<span class="go">Named ent: ></span>
|
||
<span class="go">Num ent : ></span>
|
||
<span class="go">Num ent : ></span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Feeding incomplete chunks to <a class="reference internal" href="#html.parser.HTMLParser.feed" title="html.parser.HTMLParser.feed"><code class="xref py py-meth docutils literal notranslate"><span class="pre">feed()</span></code></a> works, but
|
||
<a class="reference internal" href="#html.parser.HTMLParser.handle_data" title="html.parser.HTMLParser.handle_data"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_data()</span></code></a> might be called more than once
|
||
(unless <em>convert_charrefs</em> is set to <code class="docutils literal notranslate"><span class="pre">True</span></code>):</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">for</span> <span class="n">chunk</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'<sp'</span><span class="p">,</span> <span class="s1">'an>buff'</span><span class="p">,</span> <span class="s1">'ered '</span><span class="p">,</span> <span class="s1">'text</s'</span><span class="p">,</span> <span class="s1">'pan>'</span><span class="p">]:</span>
|
||
<span class="gp">... </span> <span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span>
|
||
<span class="gp">...</span>
|
||
<span class="go">Start tag: span</span>
|
||
<span class="go">Data : buff</span>
|
||
<span class="go">Data : ered</span>
|
||
<span class="go">Data : text</span>
|
||
<span class="go">End tag : span</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>Parsing invalid HTML (e.g. unquoted attributes) also works:</p>
|
||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<p><a class=link href=#main>tag soup</p ></a>'</span><span class="p">)</span>
|
||
<span class="go">Start tag: p</span>
|
||
<span class="go">Start tag: a</span>
|
||
<span class="go"> attr: ('class', 'link')</span>
|
||
<span class="go"> attr: ('href', '#main')</span>
|
||
<span class="go">Data : tag soup</span>
|
||
<span class="go">End tag : p</span>
|
||
<span class="go">End tag : a</span>
|
||
</pre></div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
|
||
|
||
<div class="clearer"></div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<div class="sphinxsidebar" role="navigation" aria-label="Main">
|
||
<div class="sphinxsidebarwrapper">
|
||
<div>
|
||
<h3><a href="../contents.html">Table of Contents</a></h3>
|
||
<ul>
|
||
<li><a class="reference internal" href="#"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.parser</span></code> — Simple HTML and XHTML parser</a><ul>
|
||
<li><a class="reference internal" href="#example-html-parser-application">Example HTML Parser Application</a></li>
|
||
<li><a class="reference internal" href="#htmlparser-methods"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code> Methods</a></li>
|
||
<li><a class="reference internal" href="#examples">Examples</a></li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
|
||
</div>
|
||
<div>
|
||
<h4>Previous topic</h4>
|
||
<p class="topless"><a href="html.html"
|
||
title="previous chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html</span></code> — HyperText Markup Language support</a></p>
|
||
</div>
|
||
<div>
|
||
<h4>Next topic</h4>
|
||
<p class="topless"><a href="html.entities.html"
|
||
title="next chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.entities</span></code> — Definitions of HTML general entities</a></p>
|
||
</div>
|
||
<div role="note" aria-label="source link">
|
||
<h3>This Page</h3>
|
||
<ul class="this-page-menu">
|
||
<li><a href="../bugs.html">Report a Bug</a></li>
|
||
<li>
|
||
<a href="https://github.com/python/cpython/blob/main/Doc/library/html.parser.rst"
|
||
rel="nofollow">Show Source
|
||
</a>
|
||
</li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
<div id="sidebarbutton" title="Collapse sidebar">
|
||
<span>«</span>
|
||
</div>
|
||
|
||
</div>
|
||
<div class="clearer"></div>
|
||
</div>
|
||
<div class="related" role="navigation" aria-label="Related">
|
||
<h3>Navigation</h3>
|
||
<ul>
|
||
<li class="right" style="margin-right: 10px">
|
||
<a href="../genindex.html" title="General Index"
|
||
>index</a></li>
|
||
<li class="right" >
|
||
<a href="../py-modindex.html" title="Python Module Index"
|
||
>modules</a> |</li>
|
||
<li class="right" >
|
||
<a href="html.entities.html" title="html.entities — Definitions of HTML general entities"
|
||
>next</a> |</li>
|
||
<li class="right" >
|
||
<a href="html.html" title="html — HyperText Markup Language support"
|
||
>previous</a> |</li>
|
||
|
||
<li><img src="../_static/py.svg" alt="Python logo" style="vertical-align: middle; margin-top: -1px"/></li>
|
||
<li><a href="https://www.python.org/">Python</a> »</li>
|
||
<li class="switchers">
|
||
<div class="language_switcher_placeholder"></div>
|
||
<div class="version_switcher_placeholder"></div>
|
||
</li>
|
||
<li>
|
||
|
||
</li>
|
||
<li id="cpython-language-and-version">
|
||
<a href="../index.html">3.13.3 Documentation</a> »
|
||
</li>
|
||
|
||
<li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> »</li>
|
||
<li class="nav-item nav-item-2"><a href="markup.html" >Structured Markup Processing Tools</a> »</li>
|
||
<li class="nav-item nav-item-this"><a href=""><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.parser</span></code> — Simple HTML and XHTML parser</a></li>
|
||
<li class="right">
|
||
|
||
|
||
<div class="inline-search" role="search">
|
||
<form class="inline-search" action="../search.html" method="get">
|
||
<input placeholder="Quick search" aria-label="Quick search" type="search" name="q" id="search-box" />
|
||
<input type="submit" value="Go" />
|
||
</form>
|
||
</div>
|
||
|
|
||
</li>
|
||
<li class="right">
|
||
<label class="theme-selector-label">
|
||
Theme
|
||
<select class="theme-selector" oninput="activateTheme(this.value)">
|
||
<option value="auto" selected>Auto</option>
|
||
<option value="light">Light</option>
|
||
<option value="dark">Dark</option>
|
||
</select>
|
||
</label> |</li>
|
||
|
||
</ul>
|
||
</div>
|
||
<div class="footer">
|
||
©
|
||
<a href="../copyright.html">
|
||
|
||
Copyright
|
||
|
||
</a>
|
||
2001-2025, Python Software Foundation.
|
||
<br />
|
||
This page is licensed under the Python Software Foundation License Version 2.
|
||
<br />
|
||
Examples, recipes, and other code in the documentation are additionally licensed under the Zero Clause BSD License.
|
||
<br />
|
||
|
||
See <a href="/license.html">History and License</a> for more information.<br />
|
||
|
||
|
||
<br />
|
||
|
||
The Python Software Foundation is a non-profit corporation.
|
||
<a href="https://www.python.org/psf/donations/">Please donate.</a>
|
||
<br />
|
||
<br />
|
||
Last updated on Apr 08, 2025 (14:33 UTC).
|
||
|
||
<a href="/bugs.html">Found a bug</a>?
|
||
|
||
<br />
|
||
|
||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 8.2.3.
|
||
</div>
|
||
|
||
</body>
|
||
</html> |