doc/html/api/lxml.etree.HTMLPullParser-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.etree.HTMLPullParser</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="/">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.etree-module.html">Module&nbsp;etree</a> ::
  47         Class&nbsp;HTMLPullParser
  48       </span>
  49     </td>
  50     <td>
  51       <table cellpadding="0" cellspacing="0">
  52         <!-- hide/show private -->
  53         <tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink"
  54     onclick="toggle_private();">hide&nbsp;private</a>]</span></td></tr>
  55         <tr><td align="right"><span class="options"
  56             >[<a href="frames.html" target="_top">frames</a
  57             >]&nbsp;|&nbsp;<a href="lxml.etree.HTMLPullParser-class.html"
  58             target="_top">no&nbsp;frames</a>]</span></td></tr>
  59       </table>
  60     </td>
  61   </tr>
  62 </table>
  63 <!-- ==================== CLASS DESCRIPTION ==================== -->
  64 <h1 class="epydoc">Class HTMLPullParser</h1><p class="nomargin-top"></p>
  65 <pre class="base-tree">
  66     object --+
  67              |
  68 ??._BaseParser --+
  69                  |
  70        <a href="lxml.etree._FeedParser-class.html" onclick="show_private();">_FeedParser</a> --+
  71                      |
  72             <a href="lxml.etree.HTMLParser-class.html">HTMLParser</a> --+
  73                          |
  74                         <strong class="uidshort">HTMLPullParser</strong>
  75 </pre>
  76
  77 <hr />
  78 <p>HTMLPullParser(self, events=None, <a href="#id1"><span class="rst-problematic" id="rst-rst-rst-id2">*</span></a>, tag=None, base_url=None, <a href="#id3"><span class="rst-problematic" id="rst-rst-rst-id4">**</span></a>kwargs)</p>
  79 <p>HTML parser that collects parse events in an iterator.</p>
  80 <p>The collected events are the same as for iterparse(), but the
  81 parser itself is non-blocking in the sense that it receives
  82 data chunks incrementally through its .feed() method, instead
  83 of reading them directly from a file(-like) object all by itself.</p>
  84 <p>By default, it collects Element end events.  To change that,
  85 pass any subset of the available events into the <tt class="rst-docutils literal">events</tt>
  86 argument: <tt class="rst-docutils literal">'start'</tt>, <tt class="rst-docutils literal">'end'</tt>, <tt class="rst-docutils literal"><span class="pre">'start-ns'</span></tt>,
  87 <tt class="rst-docutils literal"><span class="pre">'end-ns'</span></tt>, <tt class="rst-docutils literal">'comment'</tt>, <tt class="rst-docutils literal">'pi'</tt>.</p>
  88 <p>To support loading external dependencies relative to the input
  89 source, you can pass the <tt class="rst-docutils literal">base_url</tt>.</p>
  90
  91 <!-- ==================== INSTANCE METHODS ==================== -->
  92 <a name="section-InstanceMethods"></a>
  93 <table class="summary" border="1" cellpadding="3"
  94        cellspacing="0" width="100%" bgcolor="white">
  95 <tr bgcolor="#70b0f0" class="table-header">
  96   <td colspan="2" class="table-header">
  97     <table border="0" cellpadding="0" cellspacing="0" width="100%">
  98       <tr valign="top">
  99         <td align="left"><span class="table-header">Instance Methods</span></td>
 100         <td align="right" valign="top"
 101          ><span class="options">[<a href="#section-InstanceMethods"
 102          class="privatelink" onclick="toggle_private();"
 103          >hide private</a>]</span></td>
 104       </tr>
 105     </table>
 106   </td>
 107 </tr>
 108 <tr>
 109     <td width="15%" align="right" valign="top" class="summary">
 110       <span class="summary-type">&nbsp;</span>
 111     </td><td class="summary">
 112       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 113         <tr>
 114           <td><span class="summary-sig"><a href="lxml.etree.HTMLPullParser-class.html#__init__" class="summary-sig-name">__init__</a>(<span class="summary-sig-arg">self</span>,
 115         <span class="summary-sig-arg">events</span>=<span class="summary-sig-default">None</span>,
 116         <span class="summary-sig-arg">tag</span>=<span class="summary-sig-default">None</span>,
 117         <span class="summary-sig-arg">base_url</span>=<span class="summary-sig-default">None</span>,
 118         <span class="summary-sig-arg">*</span>,
 119         <span class="summary-sig-arg">**kwargs</span>)</span><br />
 120       x.__init__(...) initializes x; see help(type(x)) for signature</td>
 121           <td align="right" valign="top">
 122
 123
 124           </td>
 125         </tr>
 126       </table>
 127
 128     </td>
 129   </tr>
 130 <tr>
 131     <td width="15%" align="right" valign="top" class="summary">
 132       <span class="summary-type">a new object with type S, a subtype of T</span>
 133     </td><td class="summary">
 134       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 135         <tr>
 136           <td><span class="summary-sig"><a href="lxml.etree.HTMLPullParser-class.html#__new__" class="summary-sig-name">__new__</a>(<span class="summary-sig-arg">T</span>,
 137         <span class="summary-sig-arg">S</span>,
 138         <span class="summary-sig-arg">...</span>)</span></td>
 139           <td align="right" valign="top">
 140
 141
 142           </td>
 143         </tr>
 144       </table>
 145
 146     </td>
 147   </tr>
 148 <tr>
 149     <td width="15%" align="right" valign="top" class="summary">
 150       <span class="summary-type">&nbsp;</span>
 151     </td><td class="summary">
 152       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 153         <tr>
 154           <td><span class="summary-sig"><a name="read_events"></a><span class="summary-sig-name">read_events</span>(<span class="summary-sig-arg">...</span>)</span></td>
 155           <td align="right" valign="top">
 156
 157
 158           </td>
 159         </tr>
 160       </table>
 161
 162     </td>
 163   </tr>
 164   <tr>
 165     <td colspan="2" class="summary">
 166     <p class="indent-wrapped-lines"><b>Inherited from <code><a href="lxml.etree._FeedParser-class.html" onclick="show_private();">_FeedParser</a></code></b>:
 167       <code><a href="lxml.etree._FeedParser-class.html#close">close</a></code>,
 168       <code><a href="lxml.etree._FeedParser-class.html#feed">feed</a></code>
 169       </p>
 170     <p class="indent-wrapped-lines"><b>Inherited from <code><i>unreachable</i>._BaseParser</code></b>:
 171       <code>copy</code>,
 172       <code>makeelement</code>,
 173       <code>setElementClassLookup</code>,
 174       <code>set_element_class_lookup</code>
 175       </p>
 176     <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
 177       <code>__delattr__</code>,
 178       <code>__format__</code>,
 179       <code>__getattribute__</code>,
 180       <code>__hash__</code>,
 181       <code>__reduce__</code>,
 182       <code>__reduce_ex__</code>,
 183       <code>__repr__</code>,
 184       <code>__setattr__</code>,
 185       <code>__sizeof__</code>,
 186       <code>__str__</code>,
 187       <code>__subclasshook__</code>
 188       </p>
 189     </td>
 190   </tr>
 191 </table>
 192 <!-- ==================== PROPERTIES ==================== -->
 193 <a name="section-Properties"></a>
 194 <table class="summary" border="1" cellpadding="3"
 195        cellspacing="0" width="100%" bgcolor="white">
 196 <tr bgcolor="#70b0f0" class="table-header">
 197   <td colspan="2" class="table-header">
 198     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 199       <tr valign="top">
 200         <td align="left"><span class="table-header">Properties</span></td>
 201         <td align="right" valign="top"
 202          ><span class="options">[<a href="#section-Properties"
 203          class="privatelink" onclick="toggle_private();"
 204          >hide private</a>]</span></td>
 205       </tr>
 206     </table>
 207   </td>
 208 </tr>
 209   <tr>
 210     <td colspan="2" class="summary">
 211     <p class="indent-wrapped-lines"><b>Inherited from <code><a href="lxml.etree._FeedParser-class.html" onclick="show_private();">_FeedParser</a></code></b>:
 212       <code><a href="lxml.etree._FeedParser-class.html#feed_error_log">feed_error_log</a></code>
 213       </p>
 214     <p class="indent-wrapped-lines"><b>Inherited from <code><i>unreachable</i>._BaseParser</code></b>:
 215       <code>error_log</code>,
 216       <code>resolvers</code>,
 217       <code>target</code>,
 218       <code>version</code>
 219       </p>
 220     <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
 221       <code>__class__</code>
 222       </p>
 223     </td>
 224   </tr>
 225 </table>
 226 <!-- ==================== METHOD DETAILS ==================== -->
 227 <a name="section-MethodDetails"></a>
 228 <table class="details" border="1" cellpadding="3"
 229        cellspacing="0" width="100%" bgcolor="white">
 230 <tr bgcolor="#70b0f0" class="table-header">
 231   <td colspan="2" class="table-header">
 232     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 233       <tr valign="top">
 234         <td align="left"><span class="table-header">Method Details</span></td>
 235         <td align="right" valign="top"
 236          ><span class="options">[<a href="#section-MethodDetails"
 237          class="privatelink" onclick="toggle_private();"
 238          >hide private</a>]</span></td>
 239       </tr>
 240     </table>
 241   </td>
 242 </tr>
 243 </table>
 244 <a name="__init__"></a>
 245 <div>
 246 <table class="details" border="1" cellpadding="3"
 247        cellspacing="0" width="100%" bgcolor="white">
 248 <tr><td>
 249   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 250   <tr valign="top"><td>
 251   <h3 class="epydoc"><span class="sig"><span class="sig-name">__init__</span>(<span class="sig-arg">self</span>,
 252         <span class="sig-arg">events</span>=<span class="sig-default">None</span>,
 253         <span class="sig-arg">tag</span>=<span class="sig-default">None</span>,
 254         <span class="sig-arg">base_url</span>=<span class="sig-default">None</span>,
 255         <span class="sig-arg">*</span>,
 256         <span class="sig-arg">**kwargs</span>)</span>
 257     <br /><em class="fname">(Constructor)</em>
 258   </h3>
 259   </td><td align="right" valign="top"
 260     >&nbsp;
 261     </td>
 262   </tr></table>
 263
 264   x.__init__(...) initializes x; see help(type(x)) for signature
 265   <dl class="fields">
 266     <dt>Overrides:
 267         object.__init__
 268     </dt>
 269   </dl>
 270 </td></tr></table>
 271 </div>
 272 <a name="__new__"></a>
 273 <div>
 274 <table class="details" border="1" cellpadding="3"
 275        cellspacing="0" width="100%" bgcolor="white">
 276 <tr><td>
 277   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 278   <tr valign="top"><td>
 279   <h3 class="epydoc"><span class="sig"><span class="sig-name">__new__</span>(<span class="sig-arg">T</span>,
 280         <span class="sig-arg">S</span>,
 281         <span class="sig-arg">...</span>)</span>
 282   </h3>
 283   </td><td align="right" valign="top"
 284     >&nbsp;
 285     </td>
 286   </tr></table>
 287
 288
 289   <dl class="fields">
 290     <dt>Returns: a new object with type S, a subtype of T</dt>
 291     <dt>Overrides:
 292         object.__new__
 293     </dt>
 294   </dl>
 295 </td></tr></table>
 296 </div>
 297 <br />
 298 <!-- ==================== NAVIGATION BAR ==================== -->
 299 <table class="navbar" border="0" width="100%" cellpadding="0"
 300        bgcolor="#a0c0ff" cellspacing="0">
 301   <tr valign="middle">
 302   <!-- Home link -->
 303       <th>&nbsp;&nbsp;&nbsp;<a
 304         href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>
 305
 306   <!-- Tree link -->
 307       <th>&nbsp;&nbsp;&nbsp;<a
 308         href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>
 309
 310   <!-- Index link -->
 311       <th>&nbsp;&nbsp;&nbsp;<a
 312         href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>
 313
 314   <!-- Help link -->
 315       <th>&nbsp;&nbsp;&nbsp;<a
 316         href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>
 317
 318   <!-- Project homepage -->
 319       <th class="navbar" align="right" width="100%">
 320         <table border="0" cellpadding="0" cellspacing="0">
 321           <tr><th class="navbar" align="center"
 322             ><a class="navbar" target="_top" href="/">lxml API</a></th>
 323           </tr></table></th>
 324   </tr>
 325 </table>
 326 <table border="0" cellpadding="0" cellspacing="0" width="100%%">
 327   <tr>
 328     <td align="left" class="footer">
 329     Generated by Epydoc 3.0.1
 330     on Thu Jul  9 18:29:53 2020
 331     </td>
 332     <td align="right" class="footer">
 333       <a target="mainFrame" href="http://epydoc.sourceforge.net"
 334         >http://epydoc.sourceforge.net</a>
 335     </td>
 336   </tr>
 337 </table>
 338
 339 <script type="text/javascript">
 340   <!--
 341   // Private objects are initially displayed (because if
 342   // javascript is turned off then we want them to be
 343   // visible); but by default, we want to hide them.  So hide
 344   // them unless we have a cookie that says to show them.
 345   checkCookie();
 346   // -->
 347 </script>
 348 </body>
 349 </html>