增加python文档
This commit is contained in:
543
web/python-docs/library/html.parser.html
Normal file
543
web/python-docs/library/html.parser.html
Normal file
@@ -0,0 +1,543 @@
|
||||
|
||||
<!DOCTYPE html>
|
||||
|
||||
<html xmlns="http://www.w3.org/1999/xhtml" lang="zh_CN">
|
||||
<head>
|
||||
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
|
||||
|
||||
<title>html.parser --- 简单的 HTML 和 XHTML 解析器 — Python 3.8.20 文档</title><meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
|
||||
<link rel="stylesheet" href="../_static/pydoctheme.css" type="text/css" />
|
||||
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
|
||||
|
||||
<script id="documentation_options" data-url_root="../" src="../_static/documentation_options.js"></script>
|
||||
<script src="../_static/jquery.js"></script>
|
||||
<script src="../_static/underscore.js"></script>
|
||||
<script src="../_static/doctools.js"></script>
|
||||
<script src="../_static/language_data.js"></script>
|
||||
<script src="../_static/translations.js"></script>
|
||||
|
||||
<script src="../_static/sidebar.js"></script>
|
||||
|
||||
<link rel="search" type="application/opensearchdescription+xml"
|
||||
title="在 Python 3.8.20 文档 中搜索"
|
||||
href="../_static/opensearch.xml"/>
|
||||
<link rel="author" title="关于这些文档" href="../about.html" />
|
||||
<link rel="index" title="索引" href="../genindex.html" />
|
||||
<link rel="search" title="搜索" href="../search.html" />
|
||||
<link rel="copyright" title="版权所有" href="../copyright.html" />
|
||||
<link rel="next" title="html.entities --- HTML 一般实体的定义" href="html.entities.html" />
|
||||
<link rel="prev" title="html --- 超文本标记语言支持" 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="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>
|
||||
|
||||
</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" />
|
||||
<label for="menuToggler" class="toggler__label">
|
||||
<span></span>
|
||||
</label>
|
||||
<nav class="nav-content" role="navigation">
|
||||
<a href="https://www.python.org/" class="nav-logo">
|
||||
<img src="../_static/py.svg" alt="Logo"/>
|
||||
</a>
|
||||
<div class="version_switcher_placeholder"></div>
|
||||
<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"
|
||||
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" fill="#444"></path>
|
||||
</svg>
|
||||
<input type="text" name="q" aria-label="快速搜索"/>
|
||||
<input type="submit" value="转向"/>
|
||||
</form>
|
||||
</nav>
|
||||
<div class="menu-wrapper">
|
||||
<nav class="menu" role="navigation" aria-label="main navigation">
|
||||
<div class="language_switcher_placeholder"></div>
|
||||
<h3><a href="../contents.html">目录</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> --- 简单的 HTML 和 XHTML 解析器</a><ul>
|
||||
<li><a class="reference internal" href="#example-html-parser-application">HTML 解析器的示例程序</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> 方法</a></li>
|
||||
<li><a class="reference internal" href="#examples">例子</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<h4>上一个主题</h4>
|
||||
<p class="topless"><a href="html.html"
|
||||
title="上一章"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html</span></code> --- 超文本标记语言支持</a></p>
|
||||
<h4>下一个主题</h4>
|
||||
<p class="topless"><a href="html.entities.html"
|
||||
title="下一章"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.entities</span></code> --- HTML 一般实体的定义</a></p>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>本页</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="../bugs.html">报告 Bug</a></li>
|
||||
<li>
|
||||
<a href="https://github.com/python/cpython/blob/3.8/Doc/library/html.parser.rst"
|
||||
rel="nofollow">显示源代码
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</nav>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div id="outdated-warning" style="padding: .5em; text-align: center; background-color: #FFBABA; color: #6A0E0E;">
|
||||
这个文档所针对的是一个已不再受支持的 Python 旧版本。
|
||||
你应当升级版本，并阅读
|
||||
<a href="/3/library/html.parser.html"> Python 当前稳定版本的文档</a>.
|
||||
</div>
|
||||
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>导航</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="../genindex.html" title="总目录"
|
||||
accesskey="I">索引</a></li>
|
||||
<li class="right" >
|
||||
<a href="../py-modindex.html" title="Python 模块索引"
|
||||
>模块</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="html.entities.html" title="html.entities --- HTML 一般实体的定义"
|
||||
accesskey="N">下一页</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="html.html" title="html --- 超文本标记语言支持"
|
||||
accesskey="P">上一页</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">3.8.20 Documentation</a> »
|
||||
</li>
|
||||
|
||||
<li class="nav-item nav-item-1"><a href="index.html" >Python 标准库</a> »</li>
|
||||
<li class="nav-item nav-item-2"><a href="markup.html" accesskey="U">结构化标记处理工具</a> »</li>
|
||||
<li class="right">
|
||||
|
||||
|
||||
<div class="inline-search" role="search">
|
||||
<form class="inline-search" action="../search.html" method="get">
|
||||
<input placeholder="快速搜索" aria-label="快速搜索" type="text" name="q" />
|
||||
<input type="submit" value="转向" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
|
||||
</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><a class="reference internal" href="#module-html.parser" title="html.parser: A simple parser that can handle HTML and XHTML."><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.parser</span></code></a> --- 简单的 HTML 和 XHTML 解析器<a class="headerlink" href="#module-html.parser" title="永久链接至标题">¶</a></h1>
|
||||
<p><strong>源代码：</strong> <a class="reference external" href="https://github.com/python/cpython/tree/3.8/Lib/html/parser.py">Lib/html/parser.py</a></p>
|
||||
<hr class="docutils" id="index-0" />
|
||||
<p>这个模块定义了一个 <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> 类，为 HTML（超文本标记语言）和 XHTML 文本文件解析提供基础。</p>
|
||||
<dl class="class">
|
||||
<dt id="html.parser.HTMLParser">
|
||||
<em class="property">class </em><code class="sig-prename descclassname">html.parser.</code><code class="sig-name descname">HTMLParser</code><span class="sig-paren">(</span><em class="sig-param">*</em>, <em class="sig-param">convert_charrefs=True</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>创建一个能解析无效标记的解析器实例。</p>
|
||||
<p>如果 <em>convert_charrefs</em> 为 <code class="docutils literal notranslate"><span class="pre">True</span></code> (默认值)，则所有字符引用( <code class="docutils literal notranslate"><span class="pre">script</span></code>/<code class="docutils literal notranslate"><span class="pre">style</span></code> 元素中的除外)都会自动转换为相应的 Unicode 字符。</p>
|
||||
<p>一个 <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> 类的实例用来接受 HTML 数据，并在标记开始、标记结束、文本、注释和其他元素标记出现的时候调用对应的方法。要实现具体的行为，请使用 <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> 的子类并重写其方法。</p>
|
||||
<p>这个解析器不检查结束标记是否与开始标记匹配，也不会因外层元素完毕而隐式关闭了的元素引发结束标记处理。</p>
|
||||
<div class="versionchanged">
|
||||
<p><span class="versionmodified changed">在 3.4 版更改: </span><em>convert_charrefs</em> 关键字参数被添加。</p>
|
||||
</div>
|
||||
<div class="versionchanged">
|
||||
<p><span class="versionmodified changed">在 3.5 版更改: </span><em>convert_charrefs</em> 参数的默认值现在为 <code class="docutils literal notranslate"><span class="pre">True</span></code>。</p>
|
||||
</div>
|
||||
</dd></dl>
|
||||
|
||||
<section id="example-html-parser-application">
|
||||
<h2>HTML 解析器的示例程序<a class="headerlink" href="#example-html-parser-application" title="永久链接至标题">¶</a></h2>
|
||||
<p>下面是简单的 HTML 解析器的一个基本示例，使用 <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> 类，当遇到开始标记、结束标记以及数据的时候将内容打印出来。</p>
|
||||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">html.parser</span> <span class="kn">import</span> <span class="n">HTMLParser</span>
|
||||
|
||||
<span class="k">class</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="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="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="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>输出是:</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> 方法<a class="headerlink" href="#htmlparser-methods" title="永久链接至标题">¶</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> 实例有下列方法：</p>
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.feed">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">feed</code><span class="sig-paren">(</span><em class="sig-param">data</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.feed" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>填充一些文本到解析器中。如果包含完整的元素，则被处理；如果数据不完整，将被缓冲直到更多的数据被填充，或者 <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> 被调用。<em>data</em> 必须为 <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> 类型。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.close">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">close</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.close" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>如同后面跟着一个文件结束标记一样，强制处理所有缓冲数据。这个方法能被派生类重新定义，用于在输入的末尾定义附加处理，但是重定义的版本应当始终调用基类 <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> 的 <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> 方法。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.reset">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">reset</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.reset" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>重置实例。丢失所有未处理的数据。在实例化阶段被隐式调用。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.getpos">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">getpos</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.getpos" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>返回当前行号和偏移值。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.get_starttag_text">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">get_starttag_text</code><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.get_starttag_text" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>返回最近打开的开始标记中的文本。 结构化处理时通常应该不需要这个，但在处理“已部署”的 HTML 或是在以最小改变来重新生成输入时可能会有用处（例如可以保留属性间的空格等）。</p>
|
||||
</dd></dl>
|
||||
|
||||
<p>下列方法将在遇到数据或者标记元素的时候被调用。他们需要在子类中重写。基类的实现中没有任何实际操作（除了 <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="method">
|
||||
<dt id="html.parser.HTMLParser.handle_starttag">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_starttag</code><span class="sig-paren">(</span><em class="sig-param">tag</em>, <em class="sig-param">attrs</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_starttag" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>这个方法在标签开始的时候被调用（例如： <code class="docutils literal notranslate"><span class="pre"><div</span> <span class="pre">id="main"></span></code> ）。</p>
|
||||
<p><em>tag</em> 参数是小写的标记名。<em>attrs</em> 参数是一个 <code class="docutils literal notranslate"><span class="pre">(name,</span> <span class="pre">value)</span></code> 形式的列表，包含了所有在标记的 <code class="docutils literal notranslate"><span class="pre"><></span></code> 括号中找到的属性。<em>name</em> 转换为小写，<em>value</em> 的引号被去除，字符和实体引用都会被替换。</p>
|
||||
<p>实例中，对于标签 <code class="docutils literal notranslate"><span class="pre"><A</span> <span class="pre">HREF="https://www.cwi.nl/"></span></code>，这个方法将以下列形式被调用 <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><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> 中的所有实体引用，会被替换为属性值。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.handle_endtag">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_endtag</code><span class="sig-paren">(</span><em class="sig-param">tag</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_endtag" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>此方法被用来处理元素的结束标记（例如： <code class="docutils literal notranslate"><span class="pre"></div></span></code> ）。</p>
|
||||
<p><em>tag</em> 参数是小写的标签名。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.handle_startendtag">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_startendtag</code><span class="sig-paren">(</span><em class="sig-param">tag</em>, <em class="sig-param">attrs</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_startendtag" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>类似于 <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>, 只是在解析器遇到 XHTML 样式的空标记时被调用（ <code class="docutils literal notranslate"><span class="pre"><img</span> <span class="pre">...</span> <span class="pre">/></span></code>）。这个方法能被需要这种特殊词法信息的子类重写；默认实现仅简单调用 <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> 和 <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="method">
|
||||
<dt id="html.parser.HTMLParser.handle_data">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_data</code><span class="sig-paren">(</span><em class="sig-param">data</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_data" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>这个方法被用来处理任意数据（例如：文本节点和 <code class="docutils literal notranslate"><span class="pre"><script>...</script></span></code> 以及 <code class="docutils literal notranslate"><span class="pre"><style>...</style></span></code> 中的内容）。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.handle_entityref">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_entityref</code><span class="sig-paren">(</span><em class="sig-param">name</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_entityref" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>这个方法被用于处理 <code class="docutils literal notranslate"><span class="pre">&name;</span></code> 形式的命名字符引用（例如 <code class="docutils literal notranslate"><span class="pre">&gt;</span></code>），其中 <em>name</em> 是通用的实体引用（例如： <code class="docutils literal notranslate"><span class="pre">'gt'</span></code>）。如果 <em>convert_charrefs</em> 为 <code class="docutils literal notranslate"><span class="pre">True</span></code>，该方法永远不会被调用。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.handle_charref">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_charref</code><span class="sig-paren">(</span><em class="sig-param">name</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_charref" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>这个方法被用来处理 <code class="docutils literal notranslate"><span class="pre">&#NNN;</span></code> 和 <code class="docutils literal notranslate"><span class="pre">&#xNNN;</span></code> 形式的十进制和十六进制字符引用。例如，<code class="docutils literal notranslate"><span class="pre">&gt;</span></code> 等效的十进制形式为 <code class="docutils literal notranslate"><span class="pre">&#62;</span></code> ，而十六进制形式为 <code class="docutils literal notranslate"><span class="pre">&#x3E;</span></code> ；在这种情况下，方法将收到 <code class="docutils literal notranslate"><span class="pre">'62'</span></code> 或 <code class="docutils literal notranslate"><span class="pre">'x3E'</span></code> 。如果 <em>convert_charrefs</em> 为 <code class="docutils literal notranslate"><span class="pre">True</span></code> ，则该方法永远不会被调用。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.handle_comment">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_comment</code><span class="sig-paren">(</span><em class="sig-param">data</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_comment" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>这个方法在遇到注释的时候被调用（例如： <code class="docutils literal notranslate"><span class="pre"><!--comment--></span></code> ）。</p>
|
||||
<p>例如， <code class="docutils literal notranslate"><span class="pre"><!--</span> <span class="pre">comment</span> <span class="pre">--></span></code> 这个注释会用 <code class="docutils literal notranslate"><span class="pre">'</span> <span class="pre">comment</span> <span class="pre">'</span></code> 作为参数调用此方法。</p>
|
||||
<p>Internet Explorer 条件注释（condcoms）的内容也被发送到这个方法，因此，对于 <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> ，这个方法将接收到 <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="method">
|
||||
<dt id="html.parser.HTMLParser.handle_decl">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_decl</code><span class="sig-paren">(</span><em class="sig-param">decl</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_decl" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>这个方法用来处理 HTML doctype 申明（例如 <code class="docutils literal notranslate"><span class="pre"><!DOCTYPE</span> <span class="pre">html></span></code> ）。</p>
|
||||
<p><em>decl</em> 形参为 <code class="docutils literal notranslate"><span class="pre"><!...></span></code> 标记中的所有内容（例如： <code class="docutils literal notranslate"><span class="pre">'DOCTYPE</span> <span class="pre">html'</span></code> ）。</p>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.handle_pi">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">handle_pi</code><span class="sig-paren">(</span><em class="sig-param">data</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.handle_pi" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>此方法在遇到处理指令的时候被调用。<em>data</em> 形参将包含整个处理指令。例如，对于处理指令 <code class="docutils literal notranslate"><span class="pre"><?proc</span> <span class="pre">color='red'></span></code> ，这个方法将以 <code class="docutils literal notranslate"><span class="pre">handle_pi("proc</span> <span class="pre">color='red'")</span></code> 形式被调用。它旨在被派生类重写；基类实现中无任何实际操作。</p>
|
||||
<div class="admonition note">
|
||||
<p class="admonition-title">注解</p>
|
||||
<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> 类使用 SGML 语法规则处理指令。使用 <code class="docutils literal notranslate"><span class="pre">'?'</span></code> 结尾的 XHTML 处理指令将导致 <code class="docutils literal notranslate"><span class="pre">'?'</span></code> 包含在 <em>data</em> 中。</p>
|
||||
</div>
|
||||
</dd></dl>
|
||||
|
||||
<dl class="method">
|
||||
<dt id="html.parser.HTMLParser.unknown_decl">
|
||||
<code class="sig-prename descclassname">HTMLParser.</code><code class="sig-name descname">unknown_decl</code><span class="sig-paren">(</span><em class="sig-param">data</em><span class="sig-paren">)</span><a class="headerlink" href="#html.parser.HTMLParser.unknown_decl" title="永久链接至目标">¶</a></dt>
|
||||
<dd><p>当解析器读到无法识别的声明时，此方法被调用。</p>
|
||||
<p><em>data</em> 形参为 <code class="docutils literal notranslate"><span class="pre"><![...]></span></code> 标记中的所有内容。某些时候对派生类的重写很有用。基类实现中无任何实际操作。</p>
|
||||
</dd></dl>
|
||||
|
||||
</section>
|
||||
<section id="examples">
|
||||
<span id="htmlparser-examples"></span><h2>例子<a class="headerlink" href="#examples" title="永久链接至标题">¶</a></h2>
|
||||
<p>下面的类实现了一个解析器，用于更多示例的演示:</p>
|
||||
<div class="highlight-python3 notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">html.parser</span> <span class="kn">import</span> <span class="n">HTMLParser</span>
|
||||
<span class="kn">from</span> <span class="nn">html.entities</span> <span class="kn">import</span> <span class="n">name2codepoint</span>
|
||||
|
||||
<span class="k">class</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="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="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="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="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="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="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="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>解析一个文档类型声明:</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>解析一个具有一些属性和标题的元素:</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><code class="docutils literal notranslate"><span class="pre">script</span></code> 和 <code class="docutils literal notranslate"><span class="pre">style</span></code> 元素中的内容原样返回，无需进一步解析:</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>解析注释:</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>解析命名或数字形式的字符引用，并把他们转换到正确的字符（注意：这 3 种转义都是 <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>填充不完整的块给 <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> 执行，<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> 可能会多次调用（除非 <em>convert_charrefs</em> 被设置为 <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>解析无效的 HTML (例如：未引用的属性）也能正常运行:</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>
|
||||
</div>
|
||||
</div>
|
||||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||||
<div class="sphinxsidebarwrapper">
|
||||
<h3><a href="../contents.html">目录</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> --- 简单的 HTML 和 XHTML 解析器</a><ul>
|
||||
<li><a class="reference internal" href="#example-html-parser-application">HTML 解析器的示例程序</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> 方法</a></li>
|
||||
<li><a class="reference internal" href="#examples">例子</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
|
||||
<h4>上一个主题</h4>
|
||||
<p class="topless"><a href="html.html"
|
||||
title="上一章"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html</span></code> --- 超文本标记语言支持</a></p>
|
||||
<h4>下一个主题</h4>
|
||||
<p class="topless"><a href="html.entities.html"
|
||||
title="下一章"><code class="xref py py-mod docutils literal notranslate"><span class="pre">html.entities</span></code> --- HTML 一般实体的定义</a></p>
|
||||
<div role="note" aria-label="source link">
|
||||
<h3>本页</h3>
|
||||
<ul class="this-page-menu">
|
||||
<li><a href="../bugs.html">报告 Bug</a></li>
|
||||
<li>
|
||||
<a href="https://github.com/python/cpython/blob/3.8/Doc/library/html.parser.rst"
|
||||
rel="nofollow">显示源代码
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="clearer"></div>
|
||||
</div>
|
||||
<div class="related" role="navigation" aria-label="related navigation">
|
||||
<h3>导航</h3>
|
||||
<ul>
|
||||
<li class="right" style="margin-right: 10px">
|
||||
<a href="../genindex.html" title="总目录"
|
||||
>索引</a></li>
|
||||
<li class="right" >
|
||||
<a href="../py-modindex.html" title="Python 模块索引"
|
||||
>模块</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="html.entities.html" title="html.entities --- HTML 一般实体的定义"
|
||||
>下一页</a> |</li>
|
||||
<li class="right" >
|
||||
<a href="html.html" title="html --- 超文本标记语言支持"
|
||||
>上一页</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">3.8.20 Documentation</a> »
|
||||
</li>
|
||||
|
||||
<li class="nav-item nav-item-1"><a href="index.html" >Python 标准库</a> »</li>
|
||||
<li class="nav-item nav-item-2"><a href="markup.html" >结构化标记处理工具</a> »</li>
|
||||
<li class="right">
|
||||
|
||||
|
||||
<div class="inline-search" role="search">
|
||||
<form class="inline-search" action="../search.html" method="get">
|
||||
<input placeholder="快速搜索" aria-label="快速搜索" type="text" name="q" />
|
||||
<input type="submit" value="转向" />
|
||||
<input type="hidden" name="check_keywords" value="yes" />
|
||||
<input type="hidden" name="area" value="default" />
|
||||
</form>
|
||||
</div>
|
||||
|
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</div>
|
||||
<div class="footer">
|
||||
© <a href="../copyright.html">版权所有</a> 2001-2024, 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 />
|
||||
|
||||
<br />
|
||||
|
||||
The Python Software Foundation is a non-profit corporation.
|
||||
<a href="https://www.python.org/psf/donations/">Please donate.</a>
|
||||
<br />
|
||||
<br />
|
||||
|
||||
最后更新于 12月 09, 2024.
|
||||
<a href="https://docs.python.org/3/bugs.html">Found a bug</a>?
|
||||
<br />
|
||||
|
||||
Created using <a href="https://www.sphinx-doc.org/">Sphinx</a> 2.4.4.
|
||||
</div>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user