doc/html/api/lxml.html.html5parser.XHTMLParser-class.html

   1 <?xml version="1.0" encoding="ascii"?>
   2 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
   3           "DTD/xhtml1-transitional.dtd">
   4 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
   5 <head>
   6   <title>lxml.html.html5parser.XHTMLParser</title>
   7   <link rel="stylesheet" href="epydoc.css" type="text/css" />
   8   <script type="text/javascript" src="epydoc.js"></script>
   9 </head>
  10
  11 <body bgcolor="white" text="black" link="blue" vlink="#204080"
  12       alink="#204080">
  13 <!-- ==================== NAVIGATION BAR ==================== -->
  14 <table class="navbar" border="0" width="100%" cellpadding="0"
  15        bgcolor="#a0c0ff" cellspacing="0">
  16   <tr valign="middle">
  17   <!-- Home link -->
  18       <th>&nbsp;&nbsp;&nbsp;<a
  19         href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>
  20
  21   <!-- Tree link -->
  22       <th>&nbsp;&nbsp;&nbsp;<a
  23         href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>
  24
  25   <!-- Index link -->
  26       <th>&nbsp;&nbsp;&nbsp;<a
  27         href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>
  28
  29   <!-- Help link -->
  30       <th>&nbsp;&nbsp;&nbsp;<a
  31         href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>
  32
  33   <!-- Project homepage -->
  34       <th class="navbar" align="right" width="100%">
  35         <table border="0" cellpadding="0" cellspacing="0">
  36           <tr><th class="navbar" align="center"
  37             ><a class="navbar" target="_top" href="http://codespeak.net/lxml/">lxml API</a></th>
  38           </tr></table></th>
  39   </tr>
  40 </table>
  41 <table width="100%" cellpadding="0" cellspacing="0">
  42   <tr valign="top">
  43     <td width="100%">
  44       <span class="breadcrumbs">
  45         <a href="lxml-module.html">Package&nbsp;lxml</a> ::
  46         <a href="lxml.html-module.html">Package&nbsp;html</a> ::
  47         <a href="lxml.html.html5parser-module.html">Module&nbsp;html5parser</a> ::
  48         Class&nbsp;XHTMLParser
  49       </span>
  50     </td>
  51     <td>
  52       <table cellpadding="0" cellspacing="0">
  53         <!-- hide/show private -->
  54         <tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink"
  55     onclick="toggle_private();">hide&nbsp;private</a>]</span></td></tr>
  56         <tr><td align="right"><span class="options"
  57             >[<a href="frames.html" target="_top">frames</a
  58             >]&nbsp;|&nbsp;<a href="lxml.html.html5parser.XHTMLParser-class.html"
  59             target="_top">no&nbsp;frames</a>]</span></td></tr>
  60       </table>
  61     </td>
  62   </tr>
  63 </table>
  64 <!-- ==================== CLASS DESCRIPTION ==================== -->
  65 <h1 class="epydoc">Class XHTMLParser</h1><p class="nomargin-top"><span class="codelink"><a href="lxml.html.html5parser-pysrc.html#XHTMLParser">source&nbsp;code</a></span></p>
  66 <pre class="base-tree">
  67                      object --+
  68                               |
  69 html5lib.html5parser.HTMLParser --+
  70                                   |
  71 html5lib.liberalxmlparser.XMLParser --+
  72                                       |
  73   html5lib.liberalxmlparser.XHTMLParser --+
  74                                           |
  75                                          <strong class="uidshort">XHTMLParser</strong>
  76 </pre>
  77
  78 <hr />
  79 An html5lib XHTML Parser with lxml as tree.
  80
  81 <!-- ==================== INSTANCE METHODS ==================== -->
  82 <a name="section-InstanceMethods"></a>
  83 <table class="summary" border="1" cellpadding="3"
  84        cellspacing="0" width="100%" bgcolor="white">
  85 <tr bgcolor="#70b0f0" class="table-header">
  86   <td colspan="2" class="table-header">
  87     <table border="0" cellpadding="0" cellspacing="0" width="100%">
  88       <tr valign="top">
  89         <td align="left"><span class="table-header">Instance Methods</span></td>
  90         <td align="right" valign="top"
  91          ><span class="options">[<a href="#section-InstanceMethods"
  92          class="privatelink" onclick="toggle_private();"
  93          >hide private</a>]</span></td>
  94       </tr>
  95     </table>
  96   </td>
  97 </tr>
  98 <tr>
  99     <td width="15%" align="right" valign="top" class="summary">
 100       <span class="summary-type">&nbsp;</span>
 101     </td><td class="summary">
 102       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 103         <tr>
 104           <td><span class="summary-sig"><a href="lxml.html.html5parser.XHTMLParser-class.html#__init__" class="summary-sig-name">__init__</a>(<span class="summary-sig-arg">self</span>,
 105         <span class="summary-sig-arg">strict</span>=<span class="summary-sig-default">False</span>)</span><br />
 106       strict - raise an exception when a parse error is encountered</td>
 107           <td align="right" valign="top">
 108             <span class="codelink"><a href="lxml.html.html5parser-pysrc.html#XHTMLParser.__init__">source&nbsp;code</a></span>
 109
 110           </td>
 111         </tr>
 112       </table>
 113
 114     </td>
 115   </tr>
 116   <tr>
 117     <td colspan="2" class="summary">
 118     <p class="indent-wrapped-lines"><b>Inherited from <code>html5lib.liberalxmlparser.XHTMLParser</code></b>:
 119       <code>normalizeToken</code>
 120       </p>
 121     <p class="indent-wrapped-lines"><b>Inherited from <code>html5lib.liberalxmlparser.XMLParser</code></b>:
 122       <code>parseRCDataCData</code>
 123       </p>
 124     <div class="private">    <p class="indent-wrapped-lines"><b>Inherited from <code>html5lib.liberalxmlparser.XMLParser</code></b> (private):
 125       <code>_parse</code>
 126       </p></div>
 127     <p class="indent-wrapped-lines"><b>Inherited from <code>html5lib.html5parser.HTMLParser</code></b>:
 128       <code>normalizedTokens</code>,
 129       <code>parse</code>,
 130       <code>parseError</code>,
 131       <code>parseFragment</code>,
 132       <code>resetInsertionMode</code>
 133       </p>
 134     <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
 135       <code>__delattr__</code>,
 136       <code>__getattribute__</code>,
 137       <code>__hash__</code>,
 138       <code>__new__</code>,
 139       <code>__reduce__</code>,
 140       <code>__reduce_ex__</code>,
 141       <code>__repr__</code>,
 142       <code>__setattr__</code>,
 143       <code>__str__</code>
 144       </p>
 145     </td>
 146   </tr>
 147 </table>
 148 <!-- ==================== PROPERTIES ==================== -->
 149 <a name="section-Properties"></a>
 150 <table class="summary" border="1" cellpadding="3"
 151        cellspacing="0" width="100%" bgcolor="white">
 152 <tr bgcolor="#70b0f0" class="table-header">
 153   <td colspan="2" class="table-header">
 154     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 155       <tr valign="top">
 156         <td align="left"><span class="table-header">Properties</span></td>
 157         <td align="right" valign="top"
 158          ><span class="options">[<a href="#section-Properties"
 159          class="privatelink" onclick="toggle_private();"
 160          >hide private</a>]</span></td>
 161       </tr>
 162     </table>
 163   </td>
 164 </tr>
 165   <tr>
 166     <td colspan="2" class="summary">
 167     <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
 168       <code>__class__</code>
 169       </p>
 170     </td>
 171   </tr>
 172 </table>
 173 <!-- ==================== METHOD DETAILS ==================== -->
 174 <a name="section-MethodDetails"></a>
 175 <table class="details" border="1" cellpadding="3"
 176        cellspacing="0" width="100%" bgcolor="white">
 177 <tr bgcolor="#70b0f0" class="table-header">
 178   <td colspan="2" class="table-header">
 179     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 180       <tr valign="top">
 181         <td align="left"><span class="table-header">Method Details</span></td>
 182         <td align="right" valign="top"
 183          ><span class="options">[<a href="#section-MethodDetails"
 184          class="privatelink" onclick="toggle_private();"
 185          >hide private</a>]</span></td>
 186       </tr>
 187     </table>
 188   </td>
 189 </tr>
 190 </table>
 191 <a name="__init__"></a>
 192 <div>
 193 <table class="details" border="1" cellpadding="3"
 194        cellspacing="0" width="100%" bgcolor="white">
 195 <tr><td>
 196   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 197   <tr valign="top"><td>
 198   <h3 class="epydoc"><span class="sig"><span class="sig-name">__init__</span>(<span class="sig-arg">self</span>,
 199         <span class="sig-arg">strict</span>=<span class="sig-default">False</span>)</span>
 200     <br /><em class="fname">(Constructor)</em>
 201   </h3>
 202   </td><td align="right" valign="top"
 203     ><span class="codelink"><a href="lxml.html.html5parser-pysrc.html#XHTMLParser.__init__">source&nbsp;code</a></span>&nbsp;
 204     </td>
 205   </tr></table>
 206
 207   <p>strict - raise an exception when a parse error is encountered</p>
 208 <p>tree - a treebuilder class controlling the type of tree that will be
 209 returned. Built in treebuilders can be accessed through
 210 html5lib.treebuilders.getTreeBuilder(treeType)</p>
 211 <p>tokenizer - a class that provides a stream of tokens to the treebuilder.
 212 This may be replaced for e.g. a sanitizer which converts some tags to
 213 text</p>
 214   <dl class="fields">
 215     <dt>Overrides:
 216         object.__init__
 217         <dd><em class="note">(inherited documentation)</em></dd>
 218     </dt>
 219   </dl>
 220 </td></tr></table>
 221 </div>
 222 <br />
 223 <!-- ==================== NAVIGATION BAR ==================== -->
 224 <table class="navbar" border="0" width="100%" cellpadding="0"
 225        bgcolor="#a0c0ff" cellspacing="0">
 226   <tr valign="middle">
 227   <!-- Home link -->
 228       <th>&nbsp;&nbsp;&nbsp;<a
 229         href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>
 230
 231   <!-- Tree link -->
 232       <th>&nbsp;&nbsp;&nbsp;<a
 233         href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>
 234
 235   <!-- Index link -->
 236       <th>&nbsp;&nbsp;&nbsp;<a
 237         href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>
 238
 239   <!-- Help link -->
 240       <th>&nbsp;&nbsp;&nbsp;<a
 241         href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>
 242
 243   <!-- Project homepage -->
 244       <th class="navbar" align="right" width="100%">
 245         <table border="0" cellpadding="0" cellspacing="0">
 246           <tr><th class="navbar" align="center"
 247             ><a class="navbar" target="_top" href="http://codespeak.net/lxml/">lxml API</a></th>
 248           </tr></table></th>
 249   </tr>
 250 </table>
 251 <table border="0" cellpadding="0" cellspacing="0" width="100%%">
 252   <tr>
 253     <td align="left" class="footer">
 254     Generated by Epydoc 3.0 on Fri Oct 30 14:51:47 2009
 255     </td>
 256     <td align="right" class="footer">
 257       <a target="mainFrame" href="http://epydoc.sourceforge.net"
 258         >http://epydoc.sourceforge.net</a>
 259     </td>
 260   </tr>
 261 </table>
 262
 263 <script type="text/javascript">
 264   <!--
 265   // Private objects are initially displayed (because if
 266   // javascript is turned off then we want them to be
 267   // visible); but by default, we want to hide them.  So hide
 268   // them unless we have a cookie that says to show them.
 269   checkCookie();
 270   // -->
 271 </script>
 272 </body>
 273 </html>