468 lines
40 KiB
HTML
468 lines
40 KiB
HTML
|
|
|||
|
<!DOCTYPE html>
|
|||
|
|
|||
|
<html xmlns="http://www.w3.org/1999/xhtml">
|
|||
|
<head>
|
|||
|
<meta charset="utf-8" />
|
|||
|
<title>xml.dom.minidom — Minimal DOM implementation — Python 3.7.4 documentation</title>
|
|||
|
<link rel="stylesheet" href="../_static/pydoctheme.css" type="text/css" />
|
|||
|
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
|
|||
|
|
|||
|
<script type="text/javascript" id="documentation_options" data-url_root="../" src="../_static/documentation_options.js"></script>
|
|||
|
<script type="text/javascript" src="../_static/jquery.js"></script>
|
|||
|
<script type="text/javascript" src="../_static/underscore.js"></script>
|
|||
|
<script type="text/javascript" src="../_static/doctools.js"></script>
|
|||
|
<script type="text/javascript" src="../_static/language_data.js"></script>
|
|||
|
|
|||
|
<script type="text/javascript" src="../_static/sidebar.js"></script>
|
|||
|
|
|||
|
<link rel="search" type="application/opensearchdescription+xml"
|
|||
|
title="Search within Python 3.7.4 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="xml.dom.pulldom — Support for building partial DOM trees" href="xml.dom.pulldom.html" />
|
|||
|
<link rel="prev" title="xml.dom — The Document Object Model API" href="xml.dom.html" />
|
|||
|
<link rel="shortcut icon" type="image/png" href="../_static/py.png" />
|
|||
|
<link rel="canonical" href="https://docs.python.org/3/library/xml.dom.minidom.html" />
|
|||
|
|
|||
|
<script type="text/javascript" src="../_static/copybutton.js"></script>
|
|||
|
<script type="text/javascript" src="../_static/switchers.js"></script>
|
|||
|
|
|||
|
|
|||
|
|
|||
|
<style>
|
|||
|
@media only screen {
|
|||
|
table.full-width-table {
|
|||
|
width: 100%;
|
|||
|
}
|
|||
|
}
|
|||
|
</style>
|
|||
|
|
|||
|
|
|||
|
</head><body>
|
|||
|
|
|||
|
<div class="related" role="navigation" aria-label="related navigation">
|
|||
|
<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="xml.dom.pulldom.html" title="xml.dom.pulldom — Support for building partial DOM trees"
|
|||
|
accesskey="N">next</a> |</li>
|
|||
|
<li class="right" >
|
|||
|
<a href="xml.dom.html" title="xml.dom — The Document Object Model API"
|
|||
|
accesskey="P">previous</a> |</li>
|
|||
|
<li><img src="../_static/py.png" alt=""
|
|||
|
style="vertical-align: middle; margin-top: -1px"/></li>
|
|||
|
<li><a href="https://www.python.org/">Python</a> »</li>
|
|||
|
<li>
|
|||
|
<span class="language_switcher_placeholder">en</span>
|
|||
|
<span class="version_switcher_placeholder">3.7.4</span>
|
|||
|
<a href="../index.html">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="right">
|
|||
|
|
|||
|
|
|||
|
<div class="inline-search" style="display: none" role="search">
|
|||
|
<form class="inline-search" action="../search.html" method="get">
|
|||
|
<input placeholder="Quick search" type="text" name="q" />
|
|||
|
<input type="submit" value="Go" />
|
|||
|
<input type="hidden" name="check_keywords" value="yes" />
|
|||
|
<input type="hidden" name="area" value="default" />
|
|||
|
</form>
|
|||
|
</div>
|
|||
|
<script type="text/javascript">$('.inline-search').show(0);</script>
|
|||
|
|
|
|||
|
</li>
|
|||
|
|
|||
|
</ul>
|
|||
|
</div>
|
|||
|
|
|||
|
<div class="document">
|
|||
|
<div class="documentwrapper">
|
|||
|
<div class="bodywrapper">
|
|||
|
<div class="body" role="main">
|
|||
|
|
|||
|
<div class="section" id="module-xml.dom.minidom">
|
|||
|
<span id="xml-dom-minidom-minimal-dom-implementation"></span><h1><a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a> — Minimal DOM implementation<a class="headerlink" href="#module-xml.dom.minidom" title="Permalink to this headline">¶</a></h1>
|
|||
|
<p><strong>Source code:</strong> <a class="reference external" href="https://github.com/python/cpython/tree/3.7/Lib/xml/dom/minidom.py">Lib/xml/dom/minidom.py</a></p>
|
|||
|
<hr class="docutils" />
|
|||
|
<p><a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a> is a minimal implementation of the Document Object
|
|||
|
Model interface, with an API similar to that in other languages. It is intended
|
|||
|
to be simpler than the full DOM and also significantly smaller. Users who are
|
|||
|
not already proficient with the DOM should consider using the
|
|||
|
<a class="reference internal" href="xml.etree.elementtree.html#module-xml.etree.ElementTree" title="xml.etree.ElementTree: Implementation of the ElementTree API."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.etree.ElementTree</span></code></a> module for their XML processing instead.</p>
|
|||
|
<div class="admonition warning">
|
|||
|
<p class="admonition-title">Warning</p>
|
|||
|
<p>The <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a> module is not secure against
|
|||
|
maliciously constructed data. If you need to parse untrusted or
|
|||
|
unauthenticated data see <a class="reference internal" href="xml.html#xml-vulnerabilities"><span class="std std-ref">XML vulnerabilities</span></a>.</p>
|
|||
|
</div>
|
|||
|
<p>DOM applications typically start by parsing some XML into a DOM. With
|
|||
|
<a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a>, this is done through the parse functions:</p>
|
|||
|
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">xml.dom.minidom</span> <span class="k">import</span> <span class="n">parse</span><span class="p">,</span> <span class="n">parseString</span>
|
|||
|
|
|||
|
<span class="n">dom1</span> <span class="o">=</span> <span class="n">parse</span><span class="p">(</span><span class="s1">'c:</span><span class="se">\\</span><span class="s1">temp</span><span class="se">\\</span><span class="s1">mydata.xml'</span><span class="p">)</span> <span class="c1"># parse an XML file by name</span>
|
|||
|
|
|||
|
<span class="n">datasource</span> <span class="o">=</span> <span class="nb">open</span><span class="p">(</span><span class="s1">'c:</span><span class="se">\\</span><span class="s1">temp</span><span class="se">\\</span><span class="s1">mydata.xml'</span><span class="p">)</span>
|
|||
|
<span class="n">dom2</span> <span class="o">=</span> <span class="n">parse</span><span class="p">(</span><span class="n">datasource</span><span class="p">)</span> <span class="c1"># parse an open file</span>
|
|||
|
|
|||
|
<span class="n">dom3</span> <span class="o">=</span> <span class="n">parseString</span><span class="p">(</span><span class="s1">'<myxml>Some data<empty/> some more data</myxml>'</span><span class="p">)</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
<p>The <a class="reference internal" href="#xml.dom.minidom.parse" title="xml.dom.minidom.parse"><code class="xref py py-func docutils literal notranslate"><span class="pre">parse()</span></code></a> function can take either a filename or an open file object.</p>
|
|||
|
<dl class="function">
|
|||
|
<dt id="xml.dom.minidom.parse">
|
|||
|
<code class="descclassname">xml.dom.minidom.</code><code class="descname">parse</code><span class="sig-paren">(</span><em>filename_or_file</em>, <em>parser=None</em>, <em>bufsize=None</em><span class="sig-paren">)</span><a class="headerlink" href="#xml.dom.minidom.parse" title="Permalink to this definition">¶</a></dt>
|
|||
|
<dd><p>Return a <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code> from the given input. <em>filename_or_file</em> may be
|
|||
|
either a file name, or a file-like object. <em>parser</em>, if given, must be a SAX2
|
|||
|
parser object. This function will change the document handler of the parser and
|
|||
|
activate namespace support; other parser configuration (like setting an entity
|
|||
|
resolver) must have been done in advance.</p>
|
|||
|
</dd></dl>
|
|||
|
|
|||
|
<p>If you have XML in a string, you can use the <a class="reference internal" href="#xml.dom.minidom.parseString" title="xml.dom.minidom.parseString"><code class="xref py py-func docutils literal notranslate"><span class="pre">parseString()</span></code></a> function
|
|||
|
instead:</p>
|
|||
|
<dl class="function">
|
|||
|
<dt id="xml.dom.minidom.parseString">
|
|||
|
<code class="descclassname">xml.dom.minidom.</code><code class="descname">parseString</code><span class="sig-paren">(</span><em>string</em>, <em>parser=None</em><span class="sig-paren">)</span><a class="headerlink" href="#xml.dom.minidom.parseString" title="Permalink to this definition">¶</a></dt>
|
|||
|
<dd><p>Return a <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code> that represents the <em>string</em>. This method creates an
|
|||
|
<a class="reference internal" href="io.html#io.StringIO" title="io.StringIO"><code class="xref py py-class docutils literal notranslate"><span class="pre">io.StringIO</span></code></a> object for the string and passes that on to <a class="reference internal" href="#xml.dom.minidom.parse" title="xml.dom.minidom.parse"><code class="xref py py-func docutils literal notranslate"><span class="pre">parse()</span></code></a>.</p>
|
|||
|
</dd></dl>
|
|||
|
|
|||
|
<p>Both functions return a <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code> object representing the content of the
|
|||
|
document.</p>
|
|||
|
<p>What the <a class="reference internal" href="#xml.dom.minidom.parse" title="xml.dom.minidom.parse"><code class="xref py py-func docutils literal notranslate"><span class="pre">parse()</span></code></a> and <a class="reference internal" href="#xml.dom.minidom.parseString" title="xml.dom.minidom.parseString"><code class="xref py py-func docutils literal notranslate"><span class="pre">parseString()</span></code></a> functions do is connect an XML
|
|||
|
parser with a “DOM builder” that can accept parse events from any SAX parser and
|
|||
|
convert them into a DOM tree. The name of the functions are perhaps misleading,
|
|||
|
but are easy to grasp when learning the interfaces. The parsing of the document
|
|||
|
will be completed before these functions return; it’s simply that these
|
|||
|
functions do not provide a parser implementation themselves.</p>
|
|||
|
<p>You can also create a <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code> by calling a method on a “DOM
|
|||
|
Implementation” object. You can get this object either by calling the
|
|||
|
<code class="xref py py-func docutils literal notranslate"><span class="pre">getDOMImplementation()</span></code> function in the <a class="reference internal" href="xml.dom.html#module-xml.dom" title="xml.dom: Document Object Model API for Python."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom</span></code></a> package or the
|
|||
|
<a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a> module. Once you have a <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code>, you
|
|||
|
can add child nodes to it to populate the DOM:</p>
|
|||
|
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">xml.dom.minidom</span> <span class="k">import</span> <span class="n">getDOMImplementation</span>
|
|||
|
|
|||
|
<span class="n">impl</span> <span class="o">=</span> <span class="n">getDOMImplementation</span><span class="p">()</span>
|
|||
|
|
|||
|
<span class="n">newdoc</span> <span class="o">=</span> <span class="n">impl</span><span class="o">.</span><span class="n">createDocument</span><span class="p">(</span><span class="kc">None</span><span class="p">,</span> <span class="s2">"some_tag"</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
|
|||
|
<span class="n">top_element</span> <span class="o">=</span> <span class="n">newdoc</span><span class="o">.</span><span class="n">documentElement</span>
|
|||
|
<span class="n">text</span> <span class="o">=</span> <span class="n">newdoc</span><span class="o">.</span><span class="n">createTextNode</span><span class="p">(</span><span class="s1">'Some textual content.'</span><span class="p">)</span>
|
|||
|
<span class="n">top_element</span><span class="o">.</span><span class="n">appendChild</span><span class="p">(</span><span class="n">text</span><span class="p">)</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
<p>Once you have a DOM document object, you can access the parts of your XML
|
|||
|
document through its properties and methods. These properties are defined in
|
|||
|
the DOM specification. The main property of the document object is the
|
|||
|
<code class="xref py py-attr docutils literal notranslate"><span class="pre">documentElement</span></code> property. It gives you the main element in the XML
|
|||
|
document: the one that holds all others. Here is an example program:</p>
|
|||
|
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="n">dom3</span> <span class="o">=</span> <span class="n">parseString</span><span class="p">(</span><span class="s2">"<myxml>Some data</myxml>"</span><span class="p">)</span>
|
|||
|
<span class="k">assert</span> <span class="n">dom3</span><span class="o">.</span><span class="n">documentElement</span><span class="o">.</span><span class="n">tagName</span> <span class="o">==</span> <span class="s2">"myxml"</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
<p>When you are finished with a DOM tree, you may optionally call the
|
|||
|
<code class="xref py py-meth docutils literal notranslate"><span class="pre">unlink()</span></code> method to encourage early cleanup of the now-unneeded
|
|||
|
objects. <code class="xref py py-meth docutils literal notranslate"><span class="pre">unlink()</span></code> is an <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a>-specific
|
|||
|
extension to the DOM API that renders the node and its descendants are
|
|||
|
essentially useless. Otherwise, Python’s garbage collector will
|
|||
|
eventually take care of the objects in the tree.</p>
|
|||
|
<div class="admonition seealso">
|
|||
|
<p class="admonition-title">See also</p>
|
|||
|
<dl class="simple">
|
|||
|
<dt><a class="reference external" href="https://www.w3.org/TR/REC-DOM-Level-1/">Document Object Model (DOM) Level 1 Specification</a></dt><dd><p>The W3C recommendation for the DOM supported by <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a>.</p>
|
|||
|
</dd>
|
|||
|
</dl>
|
|||
|
</div>
|
|||
|
<div class="section" id="dom-objects">
|
|||
|
<span id="minidom-objects"></span><h2>DOM Objects<a class="headerlink" href="#dom-objects" title="Permalink to this headline">¶</a></h2>
|
|||
|
<p>The definition of the DOM API for Python is given as part of the <a class="reference internal" href="xml.dom.html#module-xml.dom" title="xml.dom: Document Object Model API for Python."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom</span></code></a>
|
|||
|
module documentation. This section lists the differences between the API and
|
|||
|
<a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a>.</p>
|
|||
|
<dl class="method">
|
|||
|
<dt id="xml.dom.minidom.Node.unlink">
|
|||
|
<code class="descclassname">Node.</code><code class="descname">unlink</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#xml.dom.minidom.Node.unlink" title="Permalink to this definition">¶</a></dt>
|
|||
|
<dd><p>Break internal references within the DOM so that it will be garbage collected on
|
|||
|
versions of Python without cyclic GC. Even when cyclic GC is available, using
|
|||
|
this can make large amounts of memory available sooner, so calling this on DOM
|
|||
|
objects as soon as they are no longer needed is good practice. This only needs
|
|||
|
to be called on the <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code> object, but may be called on child nodes
|
|||
|
to discard children of that node.</p>
|
|||
|
<p>You can avoid calling this method explicitly by using the <a class="reference internal" href="../reference/compound_stmts.html#with"><code class="xref std std-keyword docutils literal notranslate"><span class="pre">with</span></code></a>
|
|||
|
statement. The following code will automatically unlink <em>dom</em> when the
|
|||
|
<code class="xref std std-keyword docutils literal notranslate"><span class="pre">with</span></code> block is exited:</p>
|
|||
|
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="k">with</span> <span class="n">xml</span><span class="o">.</span><span class="n">dom</span><span class="o">.</span><span class="n">minidom</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">datasource</span><span class="p">)</span> <span class="k">as</span> <span class="n">dom</span><span class="p">:</span>
|
|||
|
<span class="o">...</span> <span class="c1"># Work with dom.</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
</dd></dl>
|
|||
|
|
|||
|
<dl class="method">
|
|||
|
<dt id="xml.dom.minidom.Node.writexml">
|
|||
|
<code class="descclassname">Node.</code><code class="descname">writexml</code><span class="sig-paren">(</span><em>writer</em>, <em>indent=""</em>, <em>addindent=""</em>, <em>newl=""</em><span class="sig-paren">)</span><a class="headerlink" href="#xml.dom.minidom.Node.writexml" title="Permalink to this definition">¶</a></dt>
|
|||
|
<dd><p>Write XML to the writer object. The writer receives texts but not bytes as input,
|
|||
|
it should have a <code class="xref py py-meth docutils literal notranslate"><span class="pre">write()</span></code> method which matches that of the file object
|
|||
|
interface. The <em>indent</em> parameter is the indentation of the current node.
|
|||
|
The <em>addindent</em> parameter is the incremental indentation to use for subnodes
|
|||
|
of the current one. The <em>newl</em> parameter specifies the string to use to
|
|||
|
terminate newlines.</p>
|
|||
|
<p>For the <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code> node, an additional keyword argument <em>encoding</em> can
|
|||
|
be used to specify the encoding field of the XML header.</p>
|
|||
|
</dd></dl>
|
|||
|
|
|||
|
<dl class="method">
|
|||
|
<dt id="xml.dom.minidom.Node.toxml">
|
|||
|
<code class="descclassname">Node.</code><code class="descname">toxml</code><span class="sig-paren">(</span><em>encoding=None</em><span class="sig-paren">)</span><a class="headerlink" href="#xml.dom.minidom.Node.toxml" title="Permalink to this definition">¶</a></dt>
|
|||
|
<dd><p>Return a string or byte string containing the XML represented by
|
|||
|
the DOM node.</p>
|
|||
|
<p>With an explicit <em>encoding</em> <a class="footnote-reference brackets" href="#id3" id="id1">1</a> argument, the result is a byte
|
|||
|
string in the specified encoding.
|
|||
|
With no <em>encoding</em> argument, the result is a Unicode string, and the
|
|||
|
XML declaration in the resulting string does not specify an
|
|||
|
encoding. Encoding this string in an encoding other than UTF-8 is
|
|||
|
likely incorrect, since UTF-8 is the default encoding of XML.</p>
|
|||
|
</dd></dl>
|
|||
|
|
|||
|
<dl class="method">
|
|||
|
<dt id="xml.dom.minidom.Node.toprettyxml">
|
|||
|
<code class="descclassname">Node.</code><code class="descname">toprettyxml</code><span class="sig-paren">(</span><em>indent="\t"</em>, <em>newl="\n"</em>, <em>encoding=None</em><span class="sig-paren">)</span><a class="headerlink" href="#xml.dom.minidom.Node.toprettyxml" title="Permalink to this definition">¶</a></dt>
|
|||
|
<dd><p>Return a pretty-printed version of the document. <em>indent</em> specifies the
|
|||
|
indentation string and defaults to a tabulator; <em>newl</em> specifies the string
|
|||
|
emitted at the end of each line and defaults to <code class="docutils literal notranslate"><span class="pre">\n</span></code>.</p>
|
|||
|
<p>The <em>encoding</em> argument behaves like the corresponding argument of
|
|||
|
<a class="reference internal" href="#xml.dom.minidom.Node.toxml" title="xml.dom.minidom.Node.toxml"><code class="xref py py-meth docutils literal notranslate"><span class="pre">toxml()</span></code></a>.</p>
|
|||
|
</dd></dl>
|
|||
|
|
|||
|
</div>
|
|||
|
<div class="section" id="dom-example">
|
|||
|
<span id="id2"></span><h2>DOM Example<a class="headerlink" href="#dom-example" title="Permalink to this headline">¶</a></h2>
|
|||
|
<p>This example program is a fairly realistic example of a simple program. In this
|
|||
|
particular case, we do not take much advantage of the flexibility of the DOM.</p>
|
|||
|
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">xml.dom.minidom</span>
|
|||
|
|
|||
|
<span class="n">document</span> <span class="o">=</span> <span class="s2">"""</span><span class="se">\</span>
|
|||
|
<span class="s2"><slideshow></span>
|
|||
|
<span class="s2"><title>Demo slideshow</title></span>
|
|||
|
<span class="s2"><slide><title>Slide title</title></span>
|
|||
|
<span class="s2"><point>This is a demo</point></span>
|
|||
|
<span class="s2"><point>Of a program for processing slides</point></span>
|
|||
|
<span class="s2"></slide></span>
|
|||
|
|
|||
|
<span class="s2"><slide><title>Another demo slide</title></span>
|
|||
|
<span class="s2"><point>It is important</point></span>
|
|||
|
<span class="s2"><point>To have more than</point></span>
|
|||
|
<span class="s2"><point>one slide</point></span>
|
|||
|
<span class="s2"></slide></span>
|
|||
|
<span class="s2"></slideshow></span>
|
|||
|
<span class="s2">"""</span>
|
|||
|
|
|||
|
<span class="n">dom</span> <span class="o">=</span> <span class="n">xml</span><span class="o">.</span><span class="n">dom</span><span class="o">.</span><span class="n">minidom</span><span class="o">.</span><span class="n">parseString</span><span class="p">(</span><span class="n">document</span><span class="p">)</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">getText</span><span class="p">(</span><span class="n">nodelist</span><span class="p">):</span>
|
|||
|
<span class="n">rc</span> <span class="o">=</span> <span class="p">[]</span>
|
|||
|
<span class="k">for</span> <span class="n">node</span> <span class="ow">in</span> <span class="n">nodelist</span><span class="p">:</span>
|
|||
|
<span class="k">if</span> <span class="n">node</span><span class="o">.</span><span class="n">nodeType</span> <span class="o">==</span> <span class="n">node</span><span class="o">.</span><span class="n">TEXT_NODE</span><span class="p">:</span>
|
|||
|
<span class="n">rc</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">node</span><span class="o">.</span><span class="n">data</span><span class="p">)</span>
|
|||
|
<span class="k">return</span> <span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">rc</span><span class="p">)</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handleSlideshow</span><span class="p">(</span><span class="n">slideshow</span><span class="p">):</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"<html>"</span><span class="p">)</span>
|
|||
|
<span class="n">handleSlideshowTitle</span><span class="p">(</span><span class="n">slideshow</span><span class="o">.</span><span class="n">getElementsByTagName</span><span class="p">(</span><span class="s2">"title"</span><span class="p">)[</span><span class="mi">0</span><span class="p">])</span>
|
|||
|
<span class="n">slides</span> <span class="o">=</span> <span class="n">slideshow</span><span class="o">.</span><span class="n">getElementsByTagName</span><span class="p">(</span><span class="s2">"slide"</span><span class="p">)</span>
|
|||
|
<span class="n">handleToc</span><span class="p">(</span><span class="n">slides</span><span class="p">)</span>
|
|||
|
<span class="n">handleSlides</span><span class="p">(</span><span class="n">slides</span><span class="p">)</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"</html>"</span><span class="p">)</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handleSlides</span><span class="p">(</span><span class="n">slides</span><span class="p">):</span>
|
|||
|
<span class="k">for</span> <span class="n">slide</span> <span class="ow">in</span> <span class="n">slides</span><span class="p">:</span>
|
|||
|
<span class="n">handleSlide</span><span class="p">(</span><span class="n">slide</span><span class="p">)</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handleSlide</span><span class="p">(</span><span class="n">slide</span><span class="p">):</span>
|
|||
|
<span class="n">handleSlideTitle</span><span class="p">(</span><span class="n">slide</span><span class="o">.</span><span class="n">getElementsByTagName</span><span class="p">(</span><span class="s2">"title"</span><span class="p">)[</span><span class="mi">0</span><span class="p">])</span>
|
|||
|
<span class="n">handlePoints</span><span class="p">(</span><span class="n">slide</span><span class="o">.</span><span class="n">getElementsByTagName</span><span class="p">(</span><span class="s2">"point"</span><span class="p">))</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handleSlideshowTitle</span><span class="p">(</span><span class="n">title</span><span class="p">):</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"<title></span><span class="si">%s</span><span class="s2"></title>"</span> <span class="o">%</span> <span class="n">getText</span><span class="p">(</span><span class="n">title</span><span class="o">.</span><span class="n">childNodes</span><span class="p">))</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handleSlideTitle</span><span class="p">(</span><span class="n">title</span><span class="p">):</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"<h2></span><span class="si">%s</span><span class="s2"></h2>"</span> <span class="o">%</span> <span class="n">getText</span><span class="p">(</span><span class="n">title</span><span class="o">.</span><span class="n">childNodes</span><span class="p">))</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handlePoints</span><span class="p">(</span><span class="n">points</span><span class="p">):</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"<ul>"</span><span class="p">)</span>
|
|||
|
<span class="k">for</span> <span class="n">point</span> <span class="ow">in</span> <span class="n">points</span><span class="p">:</span>
|
|||
|
<span class="n">handlePoint</span><span class="p">(</span><span class="n">point</span><span class="p">)</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"</ul>"</span><span class="p">)</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handlePoint</span><span class="p">(</span><span class="n">point</span><span class="p">):</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"<li></span><span class="si">%s</span><span class="s2"></li>"</span> <span class="o">%</span> <span class="n">getText</span><span class="p">(</span><span class="n">point</span><span class="o">.</span><span class="n">childNodes</span><span class="p">))</span>
|
|||
|
|
|||
|
<span class="k">def</span> <span class="nf">handleToc</span><span class="p">(</span><span class="n">slides</span><span class="p">):</span>
|
|||
|
<span class="k">for</span> <span class="n">slide</span> <span class="ow">in</span> <span class="n">slides</span><span class="p">:</span>
|
|||
|
<span class="n">title</span> <span class="o">=</span> <span class="n">slide</span><span class="o">.</span><span class="n">getElementsByTagName</span><span class="p">(</span><span class="s2">"title"</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
|
|||
|
<span class="nb">print</span><span class="p">(</span><span class="s2">"<p></span><span class="si">%s</span><span class="s2"></p>"</span> <span class="o">%</span> <span class="n">getText</span><span class="p">(</span><span class="n">title</span><span class="o">.</span><span class="n">childNodes</span><span class="p">))</span>
|
|||
|
|
|||
|
<span class="n">handleSlideshow</span><span class="p">(</span><span class="n">dom</span><span class="p">)</span>
|
|||
|
</pre></div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
<div class="section" id="minidom-and-the-dom-standard">
|
|||
|
<span id="minidom-and-dom"></span><h2>minidom and the DOM standard<a class="headerlink" href="#minidom-and-the-dom-standard" title="Permalink to this headline">¶</a></h2>
|
|||
|
<p>The <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a> module is essentially a DOM 1.0-compatible DOM with
|
|||
|
some DOM 2 features (primarily namespace features).</p>
|
|||
|
<p>Usage of the DOM interface in Python is straight-forward. The following mapping
|
|||
|
rules apply:</p>
|
|||
|
<ul class="simple">
|
|||
|
<li><p>Interfaces are accessed through instance objects. Applications should not
|
|||
|
instantiate the classes themselves; they should use the creator functions
|
|||
|
available on the <code class="xref py py-class docutils literal notranslate"><span class="pre">Document</span></code> object. Derived interfaces support all
|
|||
|
operations (and attributes) from the base interfaces, plus any new operations.</p></li>
|
|||
|
<li><p>Operations are used as methods. Since the DOM uses only <a class="reference internal" href="../reference/expressions.html#in"><code class="xref std std-keyword docutils literal notranslate"><span class="pre">in</span></code></a>
|
|||
|
parameters, the arguments are passed in normal order (from left to right).
|
|||
|
There are no optional arguments. <code class="docutils literal notranslate"><span class="pre">void</span></code> operations return <code class="docutils literal notranslate"><span class="pre">None</span></code>.</p></li>
|
|||
|
<li><p>IDL attributes map to instance attributes. For compatibility with the OMG IDL
|
|||
|
language mapping for Python, an attribute <code class="docutils literal notranslate"><span class="pre">foo</span></code> can also be accessed through
|
|||
|
accessor methods <code class="xref py py-meth docutils literal notranslate"><span class="pre">_get_foo()</span></code> and <code class="xref py py-meth docutils literal notranslate"><span class="pre">_set_foo()</span></code>. <code class="docutils literal notranslate"><span class="pre">readonly</span></code>
|
|||
|
attributes must not be changed; this is not enforced at runtime.</p></li>
|
|||
|
<li><p>The types <code class="docutils literal notranslate"><span class="pre">short</span> <span class="pre">int</span></code>, <code class="docutils literal notranslate"><span class="pre">unsigned</span> <span class="pre">int</span></code>, <code class="docutils literal notranslate"><span class="pre">unsigned</span> <span class="pre">long</span> <span class="pre">long</span></code>, and
|
|||
|
<code class="docutils literal notranslate"><span class="pre">boolean</span></code> all map to Python integer objects.</p></li>
|
|||
|
<li><p>The type <code class="docutils literal notranslate"><span class="pre">DOMString</span></code> maps to Python strings. <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a> supports
|
|||
|
either bytes or strings, but will normally produce strings.
|
|||
|
Values of type <code class="docutils literal notranslate"><span class="pre">DOMString</span></code> may also be <code class="docutils literal notranslate"><span class="pre">None</span></code> where allowed to have the IDL
|
|||
|
<code class="docutils literal notranslate"><span class="pre">null</span></code> value by the DOM specification from the W3C.</p></li>
|
|||
|
<li><p><code class="docutils literal notranslate"><span class="pre">const</span></code> declarations map to variables in their respective scope (e.g.
|
|||
|
<code class="docutils literal notranslate"><span class="pre">xml.dom.minidom.Node.PROCESSING_INSTRUCTION_NODE</span></code>); they must not be changed.</p></li>
|
|||
|
<li><p><code class="docutils literal notranslate"><span class="pre">DOMException</span></code> is currently not supported in <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a>.
|
|||
|
Instead, <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a> uses standard Python exceptions such as
|
|||
|
<a class="reference internal" href="exceptions.html#TypeError" title="TypeError"><code class="xref py py-exc docutils literal notranslate"><span class="pre">TypeError</span></code></a> and <a class="reference internal" href="exceptions.html#AttributeError" title="AttributeError"><code class="xref py py-exc docutils literal notranslate"><span class="pre">AttributeError</span></code></a>.</p></li>
|
|||
|
<li><p><code class="xref py py-class docutils literal notranslate"><span class="pre">NodeList</span></code> objects are implemented using Python’s built-in list type.
|
|||
|
These objects provide the interface defined in the DOM specification, but with
|
|||
|
earlier versions of Python they do not support the official API. They are,
|
|||
|
however, much more “Pythonic” than the interface defined in the W3C
|
|||
|
recommendations.</p></li>
|
|||
|
</ul>
|
|||
|
<p>The following interfaces have no implementation in <a class="reference internal" href="#module-xml.dom.minidom" title="xml.dom.minidom: Minimal Document Object Model (DOM) implementation."><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.minidom</span></code></a>:</p>
|
|||
|
<ul class="simple">
|
|||
|
<li><p><code class="xref py py-class docutils literal notranslate"><span class="pre">DOMTimeStamp</span></code></p></li>
|
|||
|
<li><p><code class="xref py py-class docutils literal notranslate"><span class="pre">EntityReference</span></code></p></li>
|
|||
|
</ul>
|
|||
|
<p>Most of these reflect information in the XML document that is not of general
|
|||
|
utility to most DOM users.</p>
|
|||
|
<p class="rubric">Footnotes</p>
|
|||
|
<dl class="footnote brackets">
|
|||
|
<dt class="label" id="id3"><span class="brackets"><a class="fn-backref" href="#id1">1</a></span></dt>
|
|||
|
<dd><p>The encoding name included in the XML output should conform to
|
|||
|
the appropriate standards. For example, “UTF-8” is valid, but
|
|||
|
“UTF8” is not valid in an XML document’s declaration, even though
|
|||
|
Python accepts it as an encoding name.
|
|||
|
See <a class="reference external" href="https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-EncodingDecl">https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-EncodingDecl</a>
|
|||
|
and <a class="reference external" href="https://www.iana.org/assignments/character-sets/character-sets.xhtml">https://www.iana.org/assignments/character-sets/character-sets.xhtml</a>.</p>
|
|||
|
</dd>
|
|||
|
</dl>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
|
|||
|
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
|||
|
<div class="sphinxsidebarwrapper">
|
|||
|
<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">xml.dom.minidom</span></code> — Minimal DOM implementation</a><ul>
|
|||
|
<li><a class="reference internal" href="#dom-objects">DOM Objects</a></li>
|
|||
|
<li><a class="reference internal" href="#dom-example">DOM Example</a></li>
|
|||
|
<li><a class="reference internal" href="#minidom-and-the-dom-standard">minidom and the DOM standard</a></li>
|
|||
|
</ul>
|
|||
|
</li>
|
|||
|
</ul>
|
|||
|
|
|||
|
<h4>Previous topic</h4>
|
|||
|
<p class="topless"><a href="xml.dom.html"
|
|||
|
title="previous chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom</span></code> — The Document Object Model API</a></p>
|
|||
|
<h4>Next topic</h4>
|
|||
|
<p class="topless"><a href="xml.dom.pulldom.html"
|
|||
|
title="next chapter"><code class="xref py py-mod docutils literal notranslate"><span class="pre">xml.dom.pulldom</span></code> — Support for building partial DOM trees</a></p>
|
|||
|
<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/3.7/Doc/library/xml.dom.minidom.rst"
|
|||
|
rel="nofollow">Show Source
|
|||
|
</a>
|
|||
|
</li>
|
|||
|
</ul>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
</div>
|
|||
|
<div class="clearer"></div>
|
|||
|
</div>
|
|||
|
<div class="related" role="navigation" aria-label="related navigation">
|
|||
|
<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="xml.dom.pulldom.html" title="xml.dom.pulldom — Support for building partial DOM trees"
|
|||
|
>next</a> |</li>
|
|||
|
<li class="right" >
|
|||
|
<a href="xml.dom.html" title="xml.dom — The Document Object Model API"
|
|||
|
>previous</a> |</li>
|
|||
|
<li><img src="../_static/py.png" alt=""
|
|||
|
style="vertical-align: middle; margin-top: -1px"/></li>
|
|||
|
<li><a href="https://www.python.org/">Python</a> »</li>
|
|||
|
<li>
|
|||
|
<span class="language_switcher_placeholder">en</span>
|
|||
|
<span class="version_switcher_placeholder">3.7.4</span>
|
|||
|
<a href="../index.html">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="right">
|
|||
|
|
|||
|
|
|||
|
<div class="inline-search" style="display: none" role="search">
|
|||
|
<form class="inline-search" action="../search.html" method="get">
|
|||
|
<input placeholder="Quick search" type="text" name="q" />
|
|||
|
<input type="submit" value="Go" />
|
|||
|
<input type="hidden" name="check_keywords" value="yes" />
|
|||
|
<input type="hidden" name="area" value="default" />
|
|||
|
</form>
|
|||
|
</div>
|
|||
|
<script type="text/javascript">$('.inline-search').show(0);</script>
|
|||
|
|
|
|||
|
</li>
|
|||
|
|
|||
|
</ul>
|
|||
|
</div>
|
|||
|
<div class="footer">
|
|||
|
© <a href="../copyright.html">Copyright</a> 2001-2019, Python Software Foundation.
|
|||
|
<br />
|
|||
|
The Python Software Foundation is a non-profit corporation.
|
|||
|
<a href="https://www.python.org/psf/donations/">Please donate.</a>
|
|||
|
<br />
|
|||
|
Last updated on Jul 13, 2019.
|
|||
|
<a href="../bugs.html">Found a bug</a>?
|
|||
|
<br />
|
|||
|
Created using <a href="http://sphinx.pocoo.org/">Sphinx</a> 2.0.1.
|
|||
|
</div>
|
|||
|
|
|||
|
</body>
|
|||
|
</html>
|