doc/html/api/lxml.etree.HTMLParser-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.HTMLParser</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;HTMLParser
  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.HTMLParser-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 HTMLParser</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                     <strong class="uidshort">HTMLParser</strong>
  73 </pre>
  74
  75 <dl><dt>Known Subclasses:</dt>
  76 <dd>
  77       <ul class="subclass-list">
  78 <li><a href="lxml.html.HTMLParser-class.html">html.HTMLParser</a></li><li class="private">, <a href="lxml.etree.HTMLPullParser-class.html" onclick="show_private();">HTMLPullParser</a></li>  </ul>
  79 </dd></dl>
  80
  81 <hr />
  82 <p>HTMLParser(self, encoding=None, remove_blank_text=False,                    remove_comments=False, remove_pis=False, strip_cdata=True,                    no_network=True, target=None, schema: XMLSchema =None,                    recover=True, compact=True, collect_ids=True, huge_tree=False)</p>
  83 <p>The HTML parser.</p>
  84 <p>This parser allows reading HTML into a normal XML tree.  By
  85 default, it can read broken (non well-formed) HTML, depending on
  86 the capabilities of libxml2.  Use the 'recover' option to switch
  87 this off.</p>
  88 <p>Available boolean keyword arguments:</p>
  89 <ul class="rst-simple">
  90 <li>recover            - try hard to parse through broken HTML (default: True)</li>
  91 <li>no_network         - prevent network access for related files (default: True)</li>
  92 <li>remove_blank_text  - discard empty text nodes that are ignorable (i.e. not actual text content)</li>
  93 <li>remove_comments    - discard comments</li>
  94 <li>remove_pis         - discard processing instructions</li>
  95 <li>strip_cdata        - replace CDATA sections by normal text content (default: True)</li>
  96 <li>compact            - save memory for short text content (default: True)</li>
  97 <li>default_doctype    - add a default doctype even if it is not found in the HTML (default: True)</li>
  98 <li>collect_ids        - use a hash table of XML IDs for fast access (default: True)</li>
  99 <li><dl class="rst-first rst-docutils">
 100 <dt>huge_tree          - disable security restrictions and support very deep trees</dt>
 101 <dd>and very long text content (only affects libxml2 2.7+)</dd>
 102 </dl>
 103 </li>
 104 </ul>
 105 <p>Other keyword arguments:</p>
 106 <ul class="rst-simple">
 107 <li>encoding - override the document encoding</li>
 108 <li>target   - a parser target object that will receive the parse events</li>
 109 <li>schema   - an XMLSchema to validate against</li>
 110 </ul>
 111 <p>Note that you should avoid sharing parsers between threads for performance
 112 reasons.</p>
 113
 114 <!-- ==================== INSTANCE METHODS ==================== -->
 115 <a name="section-InstanceMethods"></a>
 116 <table class="summary" border="1" cellpadding="3"
 117        cellspacing="0" width="100%" bgcolor="white">
 118 <tr bgcolor="#70b0f0" class="table-header">
 119   <td colspan="2" class="table-header">
 120     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 121       <tr valign="top">
 122         <td align="left"><span class="table-header">Instance Methods</span></td>
 123         <td align="right" valign="top"
 124          ><span class="options">[<a href="#section-InstanceMethods"
 125          class="privatelink" onclick="toggle_private();"
 126          >hide private</a>]</span></td>
 127       </tr>
 128     </table>
 129   </td>
 130 </tr>
 131 <tr>
 132     <td width="15%" align="right" valign="top" class="summary">
 133       <span class="summary-type">&nbsp;</span>
 134     </td><td class="summary">
 135       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 136         <tr>
 137           <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>,
 138         <span class="summary-sig-arg">encoding</span>=<span class="summary-sig-default">None</span>,
 139         <span class="summary-sig-arg">remove_blank_text</span>=<span class="summary-sig-default">False</span>,
 140         <span class="summary-sig-arg">remove_comments</span>=<span class="summary-sig-default">False</span>,
 141         <span class="summary-sig-arg">remove_pis</span>=<span class="summary-sig-default">False</span>,
 142         <span class="summary-sig-arg">strip_cdata</span>=<span class="summary-sig-default">True</span>,
 143         <span class="summary-sig-arg">no_network</span>=<span class="summary-sig-default">True</span>,
 144         <span class="summary-sig-arg">target</span>=<span class="summary-sig-default">None</span>,
 145         <span class="summary-sig-arg">schema: XMLSchema</span>=<span class="summary-sig-default">None</span>,
 146         <span class="summary-sig-arg">recover</span>=<span class="summary-sig-default">True</span>,
 147         <span class="summary-sig-arg">compact</span>=<span class="summary-sig-default">True</span>,
 148         <span class="summary-sig-arg">collect_ids</span>=<span class="summary-sig-default">True</span>,
 149         <span class="summary-sig-arg">huge_tree</span>=<span class="summary-sig-default">False</span>)</span><br />
 150       x.__init__(...) initializes x; see help(type(x)) for signature</td>
 151           <td align="right" valign="top">
 152
 153
 154           </td>
 155         </tr>
 156       </table>
 157
 158     </td>
 159   </tr>
 160 <tr>
 161     <td width="15%" align="right" valign="top" class="summary">
 162       <span class="summary-type">a new object with type S, a subtype of T</span>
 163     </td><td class="summary">
 164       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 165         <tr>
 166           <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>,
 167         <span class="summary-sig-arg">S</span>,
 168         <span class="summary-sig-arg">...</span>)</span></td>
 169           <td align="right" valign="top">
 170
 171
 172           </td>
 173         </tr>
 174       </table>
 175
 176     </td>
 177   </tr>
 178   <tr>
 179     <td colspan="2" class="summary">
 180     <p class="indent-wrapped-lines"><b>Inherited from <code><a href="lxml.etree._FeedParser-class.html" onclick="show_private();">_FeedParser</a></code></b>:
 181       <code><a href="lxml.etree._FeedParser-class.html#close">close</a></code>,
 182       <code><a href="lxml.etree._FeedParser-class.html#feed">feed</a></code>
 183       </p>
 184     <p class="indent-wrapped-lines"><b>Inherited from <code><i>unreachable</i>._BaseParser</code></b>:
 185       <code>copy</code>,
 186       <code>makeelement</code>,
 187       <code>setElementClassLookup</code>,
 188       <code>set_element_class_lookup</code>
 189       </p>
 190     <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
 191       <code>__delattr__</code>,
 192       <code>__format__</code>,
 193       <code>__getattribute__</code>,
 194       <code>__hash__</code>,
 195       <code>__reduce__</code>,
 196       <code>__reduce_ex__</code>,
 197       <code>__repr__</code>,
 198       <code>__setattr__</code>,
 199       <code>__sizeof__</code>,
 200       <code>__str__</code>,
 201       <code>__subclasshook__</code>
 202       </p>
 203     </td>
 204   </tr>
 205 </table>
 206 <!-- ==================== PROPERTIES ==================== -->
 207 <a name="section-Properties"></a>
 208 <table class="summary" border="1" cellpadding="3"
 209        cellspacing="0" width="100%" bgcolor="white">
 210 <tr bgcolor="#70b0f0" class="table-header">
 211   <td colspan="2" class="table-header">
 212     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 213       <tr valign="top">
 214         <td align="left"><span class="table-header">Properties</span></td>
 215         <td align="right" valign="top"
 216          ><span class="options">[<a href="#section-Properties"
 217          class="privatelink" onclick="toggle_private();"
 218          >hide private</a>]</span></td>
 219       </tr>
 220     </table>
 221   </td>
 222 </tr>
 223   <tr>
 224     <td colspan="2" class="summary">
 225     <p class="indent-wrapped-lines"><b>Inherited from <code><a href="lxml.etree._FeedParser-class.html" onclick="show_private();">_FeedParser</a></code></b>:
 226       <code><a href="lxml.etree._FeedParser-class.html#feed_error_log">feed_error_log</a></code>
 227       </p>
 228     <p class="indent-wrapped-lines"><b>Inherited from <code><i>unreachable</i>._BaseParser</code></b>:
 229       <code>error_log</code>,
 230       <code>resolvers</code>,
 231       <code>target</code>,
 232       <code>version</code>
 233       </p>
 234     <p class="indent-wrapped-lines"><b>Inherited from <code>object</code></b>:
 235       <code>__class__</code>
 236       </p>
 237     </td>
 238   </tr>
 239 </table>
 240 <!-- ==================== METHOD DETAILS ==================== -->
 241 <a name="section-MethodDetails"></a>
 242 <table class="details" border="1" cellpadding="3"
 243        cellspacing="0" width="100%" bgcolor="white">
 244 <tr bgcolor="#70b0f0" class="table-header">
 245   <td colspan="2" class="table-header">
 246     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 247       <tr valign="top">
 248         <td align="left"><span class="table-header">Method Details</span></td>
 249         <td align="right" valign="top"
 250          ><span class="options">[<a href="#section-MethodDetails"
 251          class="privatelink" onclick="toggle_private();"
 252          >hide private</a>]</span></td>
 253       </tr>
 254     </table>
 255   </td>
 256 </tr>
 257 </table>
 258 <a name="__init__"></a>
 259 <div>
 260 <table class="details" border="1" cellpadding="3"
 261        cellspacing="0" width="100%" bgcolor="white">
 262 <tr><td>
 263   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 264   <tr valign="top"><td>
 265   <h3 class="epydoc"><span class="sig"><span class="sig-name">__init__</span>(<span class="sig-arg">self</span>,
 266         <span class="sig-arg">encoding</span>=<span class="sig-default">None</span>,
 267         <span class="sig-arg">remove_blank_text</span>=<span class="sig-default">False</span>,
 268         <span class="sig-arg">remove_comments</span>=<span class="sig-default">False</span>,
 269         <span class="sig-arg">remove_pis</span>=<span class="sig-default">False</span>,
 270         <span class="sig-arg">strip_cdata</span>=<span class="sig-default">True</span>,
 271         <span class="sig-arg">no_network</span>=<span class="sig-default">True</span>,
 272         <span class="sig-arg">target</span>=<span class="sig-default">None</span>,
 273         <span class="sig-arg">schema: XMLSchema</span>=<span class="sig-default">None</span>,
 274         <span class="sig-arg">recover</span>=<span class="sig-default">True</span>,
 275         <span class="sig-arg">compact</span>=<span class="sig-default">True</span>,
 276         <span class="sig-arg">collect_ids</span>=<span class="sig-default">True</span>,
 277         <span class="sig-arg">huge_tree</span>=<span class="sig-default">False</span>)</span>
 278     <br /><em class="fname">(Constructor)</em>
 279   </h3>
 280   </td><td align="right" valign="top"
 281     >&nbsp;
 282     </td>
 283   </tr></table>
 284
 285   x.__init__(...) initializes x; see help(type(x)) for signature
 286   <dl class="fields">
 287     <dt>Overrides:
 288         object.__init__
 289     </dt>
 290   </dl>
 291 </td></tr></table>
 292 </div>
 293 <a name="__new__"></a>
 294 <div>
 295 <table class="details" border="1" cellpadding="3"
 296        cellspacing="0" width="100%" bgcolor="white">
 297 <tr><td>
 298   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 299   <tr valign="top"><td>
 300   <h3 class="epydoc"><span class="sig"><span class="sig-name">__new__</span>(<span class="sig-arg">T</span>,
 301         <span class="sig-arg">S</span>,
 302         <span class="sig-arg">...</span>)</span>
 303   </h3>
 304   </td><td align="right" valign="top"
 305     >&nbsp;
 306     </td>
 307   </tr></table>
 308
 309
 310   <dl class="fields">
 311     <dt>Returns: a new object with type S, a subtype of T</dt>
 312     <dt>Overrides:
 313         object.__new__
 314     </dt>
 315   </dl>
 316 </td></tr></table>
 317 </div>
 318 <br />
 319 <!-- ==================== NAVIGATION BAR ==================== -->
 320 <table class="navbar" border="0" width="100%" cellpadding="0"
 321        bgcolor="#a0c0ff" cellspacing="0">
 322   <tr valign="middle">
 323   <!-- Home link -->
 324       <th>&nbsp;&nbsp;&nbsp;<a
 325         href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>
 326
 327   <!-- Tree link -->
 328       <th>&nbsp;&nbsp;&nbsp;<a
 329         href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>
 330
 331   <!-- Index link -->
 332       <th>&nbsp;&nbsp;&nbsp;<a
 333         href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>
 334
 335   <!-- Help link -->
 336       <th>&nbsp;&nbsp;&nbsp;<a
 337         href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>
 338
 339   <!-- Project homepage -->
 340       <th class="navbar" align="right" width="100%">
 341         <table border="0" cellpadding="0" cellspacing="0">
 342           <tr><th class="navbar" align="center"
 343             ><a class="navbar" target="_top" href="/">lxml API</a></th>
 344           </tr></table></th>
 345   </tr>
 346 </table>
 347 <table border="0" cellpadding="0" cellspacing="0" width="100%%">
 348   <tr>
 349     <td align="left" class="footer">
 350     Generated by Epydoc 3.0.1
 351     on Thu Jul  9 18:29:53 2020
 352     </td>
 353     <td align="right" class="footer">
 354       <a target="mainFrame" href="http://epydoc.sourceforge.net"
 355         >http://epydoc.sourceforge.net</a>
 356     </td>
 357   </tr>
 358 </table>
 359
 360 <script type="text/javascript">
 361   <!--
 362   // Private objects are initially displayed (because if
 363   // javascript is turned off then we want them to be
 364   // visible); but by default, we want to hide them.  So hide
 365   // them unless we have a cookie that says to show them.
 366   checkCookie();
 367   // -->
 368 </script>
 369 </body>
 370 </html>