Sophie

Sophie

distrib > CentOS > 5 > i386 > by-pkgid > 90dba77ca23efa667b541b5c0dd77497 > files > 155

python-lxml-2.0.11-2.el5.i386.rpm

<?xml version="1.0" encoding="ascii"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
          "DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
  <title>lxml.etree.HTMLParser</title>
  <link rel="stylesheet" href="epydoc.css" type="text/css" />
  <script type="text/javascript" src="epydoc.js"></script>
</head>

<body bgcolor="white" text="black" link="blue" vlink="#204080"
      alink="#204080">
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
       bgcolor="#a0c0ff" cellspacing="0">
  <tr valign="middle">
  <!-- Home link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Tree link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Index link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Help link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Project homepage -->
      <th class="navbar" align="right" width="100%">
        <table border="0" cellpadding="0" cellspacing="0">
          <tr><th class="navbar" align="center"
            ><a class="navbar" target="_top" href="http://codespeak.net/lxml/">lxml API</a></th>
          </tr></table></th>
  </tr>
</table>
<table width="100%" cellpadding="0" cellspacing="0">
  <tr valign="top">
    <td width="100%">
      <span class="breadcrumbs">
        <a href="lxml-module.html">Package&nbsp;lxml</a> ::
        <a href="lxml.etree-module.html">Module&nbsp;etree</a> ::
        Class&nbsp;HTMLParser
      </span>
    </td>
    <td>
      <table cellpadding="0" cellspacing="0">
        <!-- hide/show private -->
        <tr><td align="right"><span class="options"
            >[<a href="frames.html" target="_top">frames</a
            >]&nbsp;|&nbsp;<a href="lxml.etree.HTMLParser-class.html"
            target="_top">no&nbsp;frames</a>]</span></td></tr>
      </table>
    </td>
  </tr>
</table>
<!-- ==================== CLASS DESCRIPTION ==================== -->
<h1 class="epydoc">Class HTMLParser</h1><p class="nomargin-top"></p>
<pre class="base-tree">
 object --+        
          |        
_BaseParser --+    
              |    
    _FeedParser --+
                  |
                 <strong class="uidshort">HTMLParser</strong>
</pre>

<dl><dt>Known Subclasses:</dt>
<dd>
      <ul class="subclass-list">
<li class="private">html.HTMLParser</li>  </ul>
</dd></dl>

<hr />
<p>HTMLParser(self, recover=True, no_network=True, remove_blank_text=False, compact=True, remove_comments=False, remove_pis=False, target=None, encoding=None, schema=None)
The HTML parser.</p>
<p>This parser allows reading HTML into a normal XML tree.  By
default, it can read broken (non well-formed) HTML, depending on
the capabilities of libxml2.  Use the 'recover' option to switch
this off.</p>
<p>Available boolean keyword arguments:</p>
<ul class="rst-simple">
<li>recover            - try hard to parse through broken HTML (default: True)</li>
<li>no_network         - prevent network access for related files (default: True)</li>
<li>remove_blank_text  - discard empty text nodes</li>
<li>remove_comments    - discard comments</li>
<li>remove_pis         - discard processing instructions</li>
<li>compact            - safe memory for short text content (default: True)</li>
</ul>
<p>Other keyword arguments:</p>
<ul class="rst-simple">
<li>encoding - override the document encoding</li>
<li>target   - a parser target object that will receive the parse events</li>
<li>schema   - an XMLSchema to validate against</li>
</ul>
<p>Note that you should avoid sharing parsers between threads for performance
reasons.</p>

<!-- ==================== INSTANCE METHODS ==================== -->
<a name="section-InstanceMethods"></a>
<table class="summary" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td align="left" colspan="2" class="table-header">
    <span class="table-header">Instance Methods</span></td>
</tr>
<tr>
    <td width="15%" align="right" valign="top" class="summary">
      <span class="summary-type">&nbsp;</span>
    </td><td class="summary">
      <table width="100%" cellpadding="0" cellspacing="0" border="0">
        <tr>
          <td><span class="summary-sig"><a href="lxml.etree.HTMLParser-class.html#__init__" class="summary-sig-name">__init__</a>(<span class="summary-sig-arg">self</span>,
        <span class="summary-sig-arg">recover</span>=<span class="summary-sig-default">True</span>,
        <span class="summary-sig-arg">no_network</span>=<span class="summary-sig-default">True</span>,
        <span class="summary-sig-arg">remove_blank_text</span>=<span class="summary-sig-default">False</span>,
        <span class="summary-sig-arg">compact</span>=<span class="summary-sig-default">True</span>,
        <span class="summary-sig-arg">remove_comments</span>=<span class="summary-sig-default">False</span>,
        <span class="summary-sig-arg">remove_pis</span>=<span class="summary-sig-default">False</span>,
        <span class="summary-sig-arg">target</span>=<span class="summary-sig-default">None</span>,
        <span class="summary-sig-arg">encoding</span>=<span class="summary-sig-default">None</span>,
        <span class="summary-sig-arg">schema</span>=<span class="summary-sig-default">None</span>)</span><br />
      x.__init__(...) initializes x; see x.__class__.__doc__ for signature</td>
          <td align="right" valign="top">
            
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr>
    <td width="15%" align="right" valign="top" class="summary">
      <span class="summary-type">a new object with type S, a subtype of T</span>
    </td><td class="summary">
      <table width="100%" cellpadding="0" cellspacing="0" border="0">
        <tr>
          <td><span class="summary-sig"><a href="lxml.etree.HTMLParser-class.html#__new__" class="summary-sig-name">__new__</a>(<span class="summary-sig-arg">T</span>,
        <span class="summary-sig-arg">S</span>,
        <span class="summary-sig-arg">...</span>)</span></td>
          <td align="right" valign="top">
            
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
  <tr>
    <td colspan="2" class="summary">
    <p class="indent-wrapped-lines"><b>Inherited from <code>_FeedParser</code></b>:
      <code>close</code>,
      <code>feed</code>
      </p>
    <p class="indent-wrapped-lines"><b>Inherited from <code>_BaseParser</code></b>:
      <code>copy</code>,
      <code>makeelement</code>,
      <code>setElementClassLookup</code>,
      <code>set_element_class_lookup</code>
      </p>
    <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
      <code>__delattr__</code>,
      <code>__getattribute__</code>,
      <code>__hash__</code>,
      <code>__reduce__</code>,
      <code>__reduce_ex__</code>,
      <code>__repr__</code>,
      <code>__setattr__</code>,
      <code>__str__</code>
      </p>
    </td>
  </tr>
</table>
<!-- ==================== PROPERTIES ==================== -->
<a name="section-Properties"></a>
<table class="summary" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td align="left" colspan="2" class="table-header">
    <span class="table-header">Properties</span></td>
</tr>
  <tr>
    <td colspan="2" class="summary">
    <p class="indent-wrapped-lines"><b>Inherited from <code>_FeedParser</code></b>:
      <code>feed_error_log</code>
      </p>
    <p class="indent-wrapped-lines"><b>Inherited from <code>_BaseParser</code></b>:
      <code>error_log</code>,
      <code>resolvers</code>,
      <code>version</code>
      </p>
    <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
      <code>__class__</code>
      </p>
    </td>
  </tr>
</table>
<!-- ==================== METHOD DETAILS ==================== -->
<a name="section-MethodDetails"></a>
<table class="details" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td align="left" colspan="2" class="table-header">
    <span class="table-header">Method Details</span></td>
</tr>
</table>
<a name="__init__"></a>
<div>
<table class="details" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr><td>
  <table width="100%" cellpadding="0" cellspacing="0" border="0">
  <tr valign="top"><td>
  <h3 class="epydoc"><span class="sig"><span class="sig-name">__init__</span>(<span class="sig-arg">self</span>,
        <span class="sig-arg">recover</span>=<span class="sig-default">True</span>,
        <span class="sig-arg">no_network</span>=<span class="sig-default">True</span>,
        <span class="sig-arg">remove_blank_text</span>=<span class="sig-default">False</span>,
        <span class="sig-arg">compact</span>=<span class="sig-default">True</span>,
        <span class="sig-arg">remove_comments</span>=<span class="sig-default">False</span>,
        <span class="sig-arg">remove_pis</span>=<span class="sig-default">False</span>,
        <span class="sig-arg">target</span>=<span class="sig-default">None</span>,
        <span class="sig-arg">encoding</span>=<span class="sig-default">None</span>,
        <span class="sig-arg">schema</span>=<span class="sig-default">None</span>)</span>
    <br /><em class="fname">(Constructor)</em>
  </h3>
  </td><td align="right" valign="top"
    >&nbsp;
    </td>
  </tr></table>
  
  x.__init__(...) initializes x; see x.__class__.__doc__ for signature
  <dl class="fields">
    <dt>Overrides:
        object.__init__
    </dt>
  </dl>
</td></tr></table>
</div>
<a name="__new__"></a>
<div>
<table class="details" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr><td>
  <table width="100%" cellpadding="0" cellspacing="0" border="0">
  <tr valign="top"><td>
  <h3 class="epydoc"><span class="sig"><span class="sig-name">__new__</span>(<span class="sig-arg">T</span>,
        <span class="sig-arg">S</span>,
        <span class="sig-arg">...</span>)</span>
  </h3>
  </td><td align="right" valign="top"
    >&nbsp;
    </td>
  </tr></table>
  
  
  <dl class="fields">
    <dt>Returns: a new object with type S, a subtype of T</dt>
    <dt>Overrides:
        object.__new__
    </dt>
  </dl>
</td></tr></table>
</div>
<br />
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
       bgcolor="#a0c0ff" cellspacing="0">
  <tr valign="middle">
  <!-- Home link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Tree link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Index link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Help link -->
      <th>&nbsp;&nbsp;&nbsp;<a
        href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>

  <!-- Project homepage -->
      <th class="navbar" align="right" width="100%">
        <table border="0" cellpadding="0" cellspacing="0">
          <tr><th class="navbar" align="center"
            ><a class="navbar" target="_top" href="http://codespeak.net/lxml/">lxml API</a></th>
          </tr></table></th>
  </tr>
</table>
<table border="0" cellpadding="0" cellspacing="0" width="100%%">
  <tr>
    <td align="left" class="footer">
    Generated by Epydoc 3.0 on Fri Dec 12 22:40:31 2008
    </td>
    <td align="right" class="footer">
      <a target="mainFrame" href="http://epydoc.sourceforge.net"
        >http://epydoc.sourceforge.net</a>
    </td>
  </tr>
</table>

<script type="text/javascript">
  <!--
  // Private objects are initially displayed (because if
  // javascript is turned off then we want them to be
  // visible); but by default, we want to hide them.  So hide
  // them unless we have a cookie that says to show them.
  checkCookie();
  // -->
</script>
</body>
</html>