Blob Blame History Raw
<?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.html.soupparser</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="/">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.html-module.html">Package&nbsp;html</a> ::
        Module&nbsp;soupparser
      </span>
    </td>
    <td>
      <table cellpadding="0" cellspacing="0">
        <!-- hide/show private -->
        <tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink"
    onclick="toggle_private();">hide&nbsp;private</a>]</span></td></tr>
        <tr><td align="right"><span class="options"
            >[<a href="frames.html" target="_top">frames</a
            >]&nbsp;|&nbsp;<a href="lxml.html.soupparser-module.html"
            target="_top">no&nbsp;frames</a>]</span></td></tr>
      </table>
    </td>
  </tr>
</table>
<!-- ==================== MODULE DESCRIPTION ==================== -->
<h1 class="epydoc">Module soupparser</h1><p class="nomargin-top"><span class="codelink"><a href="lxml.html.soupparser-pysrc.html">source&nbsp;code</a></span></p>
External interface to the BeautifulSoup HTML parser.

<!-- ==================== CLASSES ==================== -->
<a name="section-Classes"></a>
<table class="summary" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td colspan="2" class="table-header">
    <table border="0" cellpadding="0" cellspacing="0" width="100%">
      <tr valign="top">
        <td align="left"><span class="table-header">Classes</span></td>
        <td align="right" valign="top"
         ><span class="options">[<a href="#section-Classes"
         class="privatelink" onclick="toggle_private();"
         >hide private</a>]</span></td>
      </tr>
    </table>
  </td>
</tr>
<tr class="private">
    <td width="15%" align="right" valign="top" class="summary">
      <span class="summary-type">&nbsp;</span>
    </td><td class="summary">
        <a href="lxml.html.soupparser._PseudoTag-class.html" class="summary-name" onclick="show_private();">_PseudoTag</a>
    </td>
  </tr>
</table>
<!-- ==================== FUNCTIONS ==================== -->
<a name="section-Functions"></a>
<table class="summary" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td colspan="2" class="table-header">
    <table border="0" cellpadding="0" cellspacing="0" width="100%">
      <tr valign="top">
        <td align="left"><span class="table-header">Functions</span></td>
        <td align="right" valign="top"
         ><span class="options">[<a href="#section-Functions"
         class="privatelink" onclick="toggle_private();"
         >hide private</a>]</span></td>
      </tr>
    </table>
  </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.html.soupparser-module.html#fromstring" class="summary-sig-name">fromstring</a>(<span class="summary-sig-arg">data</span>,
        <span class="summary-sig-arg">beautifulsoup</span>=<span class="summary-sig-default">None</span>,
        <span class="summary-sig-arg">makeelement</span>=<span class="summary-sig-default">None</span>,
        <span class="summary-sig-arg">**bsargs</span>)</span><br />
      Parse a string of HTML data into an Element tree using the
BeautifulSoup parser.</td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#fromstring">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </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.html.soupparser-module.html#parse" class="summary-sig-name">parse</a>(<span class="summary-sig-arg">file</span>,
        <span class="summary-sig-arg">beautifulsoup</span>=<span class="summary-sig-default">None</span>,
        <span class="summary-sig-arg">makeelement</span>=<span class="summary-sig-default">None</span>,
        <span class="summary-sig-arg">**bsargs</span>)</span><br />
      Parse a file into an ElemenTree using the BeautifulSoup parser.</td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#parse">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </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.html.soupparser-module.html#convert_tree" class="summary-sig-name">convert_tree</a>(<span class="summary-sig-arg">beautiful_soup_tree</span>,
        <span class="summary-sig-arg">makeelement</span>=<span class="summary-sig-default">None</span>)</span><br />
      Convert a BeautifulSoup tree to a list of Element trees.</td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#convert_tree">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr class="private">
    <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 name="_parse"></a><span class="summary-sig-name">_parse</span>(<span class="summary-sig-arg">source</span>,
        <span class="summary-sig-arg">beautifulsoup</span>,
        <span class="summary-sig-arg">makeelement</span>,
        <span class="summary-sig-arg">**bsargs</span>)</span></td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#_parse">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr class="private">
    <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 name="_parse_doctype_declaration"></a><span class="summary-sig-name">_parse_doctype_declaration</span>(<span class="summary-sig-arg">...</span>)</span><br />
      match(string[, pos[, endpos]]) --&gt; match object or None.
Matches zero or more characters at the beginning of the string</td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#_parse_doctype_declaration">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr class="private">
    <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 name="_convert_tree"></a><span class="summary-sig-name">_convert_tree</span>(<span class="summary-sig-arg">beautiful_soup_tree</span>,
        <span class="summary-sig-arg">makeelement</span>)</span></td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#_convert_tree">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr class="private">
    <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 name="_init_node_converters"></a><span class="summary-sig-name">_init_node_converters</span>(<span class="summary-sig-arg">makeelement</span>)</span></td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#_init_node_converters">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr class="private">
    <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 name="handle_entities"></a><span class="summary-sig-name">handle_entities</span>(<span class="summary-sig-arg">...</span>)</span><br />
      sub(repl, string[, count = 0]) --&gt; newstring
Return the string obtained by replacing the leftmost non-overlapping
occurrences of pattern in string by the replacement repl.</td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#handle_entities">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr class="private">
    <td width="15%" align="right" valign="top" class="summary">
      <span class="summary-type">character</span>
    </td><td class="summary">
      <table width="100%" cellpadding="0" cellspacing="0" border="0">
        <tr>
          <td><span class="summary-sig"><a name="unichr"></a><span class="summary-sig-name">unichr</span>(<span class="summary-sig-arg">i</span>)</span><br />
      Return a string of one character with ordinal i; 0 &lt;= i &lt; 256.</td>
          <td align="right" valign="top">
            
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
<tr class="private">
    <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 name="unescape"></a><span class="summary-sig-name">unescape</span>(<span class="summary-sig-arg">string</span>)</span></td>
          <td align="right" valign="top">
            <span class="codelink"><a href="lxml.html.soupparser-pysrc.html#unescape">source&nbsp;code</a></span>
            
          </td>
        </tr>
      </table>
      
    </td>
  </tr>
</table>
<!-- ==================== VARIABLES ==================== -->
<a name="section-Variables"></a>
<table class="summary" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td colspan="2" class="table-header">
    <table border="0" cellpadding="0" cellspacing="0" width="100%">
      <tr valign="top">
        <td align="left"><span class="table-header">Variables</span></td>
        <td align="right" valign="top"
         ><span class="options">[<a href="#section-Variables"
         class="privatelink" onclick="toggle_private();"
         >hide private</a>]</span></td>
      </tr>
    </table>
  </td>
</tr>
<tr class="private">
    <td width="15%" align="right" valign="top" class="summary">
      <span class="summary-type">&nbsp;</span>
    </td><td class="summary">
        <a href="lxml.html.soupparser-module.html#_DECLARATION_OR_DOCTYPE" class="summary-name" onclick="show_private();">_DECLARATION_OR_DOCTYPE</a> = <code title="(&lt;class 'bs4.element.Declaration'&gt;, &lt;class 'bs4.element.Doctype'&gt;)"><code class="variable-group">(</code>&lt;class 'bs4.element.Declaration'&gt;<code class="variable-op">, </code><code class="variable-ellipsis">...</code></code>
    </td>
  </tr>
<tr class="private">
    <td width="15%" align="right" valign="top" class="summary">
      <span class="summary-type">&nbsp;</span>
    </td><td class="summary">
        <a name="__package__"></a><span class="summary-name">__package__</span> = <code title="'lxml.html'"><code class="variable-quote">'</code><code class="variable-string">lxml.html</code><code class="variable-quote">'</code></code>
    </td>
  </tr>
</table>
<!-- ==================== FUNCTION DETAILS ==================== -->
<a name="section-FunctionDetails"></a>
<table class="details" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td colspan="2" class="table-header">
    <table border="0" cellpadding="0" cellspacing="0" width="100%">
      <tr valign="top">
        <td align="left"><span class="table-header">Function Details</span></td>
        <td align="right" valign="top"
         ><span class="options">[<a href="#section-FunctionDetails"
         class="privatelink" onclick="toggle_private();"
         >hide private</a>]</span></td>
      </tr>
    </table>
  </td>
</tr>
</table>
<a name="fromstring"></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">fromstring</span>(<span class="sig-arg">data</span>,
        <span class="sig-arg">beautifulsoup</span>=<span class="sig-default">None</span>,
        <span class="sig-arg">makeelement</span>=<span class="sig-default">None</span>,
        <span class="sig-arg">**bsargs</span>)</span>
  </h3>
  </td><td align="right" valign="top"
    ><span class="codelink"><a href="lxml.html.soupparser-pysrc.html#fromstring">source&nbsp;code</a></span>&nbsp;
    </td>
  </tr></table>
  
  <p>Parse a string of HTML data into an Element tree using the
BeautifulSoup parser.</p>
<p>Returns the root <tt class="rst-docutils literal">&lt;html&gt;</tt> Element of the tree.</p>
<p>You can pass a different BeautifulSoup parser through the
<code class="link">beautifulsoup</code> keyword, and a diffent Element factory function
through the <code class="link">makeelement</code> keyword.  By default, the standard
<tt class="rst-docutils literal">BeautifulSoup</tt> class and the default factory of lxml.html are
used.</p>
  <dl class="fields">
  </dl>
</td></tr></table>
</div>
<a name="parse"></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">parse</span>(<span class="sig-arg">file</span>,
        <span class="sig-arg">beautifulsoup</span>=<span class="sig-default">None</span>,
        <span class="sig-arg">makeelement</span>=<span class="sig-default">None</span>,
        <span class="sig-arg">**bsargs</span>)</span>
  </h3>
  </td><td align="right" valign="top"
    ><span class="codelink"><a href="lxml.html.soupparser-pysrc.html#parse">source&nbsp;code</a></span>&nbsp;
    </td>
  </tr></table>
  
  <p>Parse a file into an ElemenTree using the BeautifulSoup parser.</p>
<p>You can pass a different BeautifulSoup parser through the
<code class="link">beautifulsoup</code> keyword, and a diffent Element factory function
through the <code class="link">makeelement</code> keyword.  By default, the standard
<tt class="rst-docutils literal">BeautifulSoup</tt> class and the default factory of lxml.html are
used.</p>
  <dl class="fields">
  </dl>
</td></tr></table>
</div>
<a name="convert_tree"></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">convert_tree</span>(<span class="sig-arg">beautiful_soup_tree</span>,
        <span class="sig-arg">makeelement</span>=<span class="sig-default">None</span>)</span>
  </h3>
  </td><td align="right" valign="top"
    ><span class="codelink"><a href="lxml.html.soupparser-pysrc.html#convert_tree">source&nbsp;code</a></span>&nbsp;
    </td>
  </tr></table>
  
  <p>Convert a BeautifulSoup tree to a list of Element trees.</p>
<p>Returns a list instead of a single root Element to support
HTML-like soup with more than one root element.</p>
<p>You can pass a different Element factory through the <code class="link">makeelement</code>
keyword.</p>
  <dl class="fields">
  </dl>
</td></tr></table>
</div>
<br />
<!-- ==================== VARIABLES DETAILS ==================== -->
<a name="section-VariablesDetails"></a>
<table class="details" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr bgcolor="#70b0f0" class="table-header">
  <td colspan="2" class="table-header">
    <table border="0" cellpadding="0" cellspacing="0" width="100%">
      <tr valign="top">
        <td align="left"><span class="table-header">Variables Details</span></td>
        <td align="right" valign="top"
         ><span class="options">[<a href="#section-VariablesDetails"
         class="privatelink" onclick="toggle_private();"
         >hide private</a>]</span></td>
      </tr>
    </table>
  </td>
</tr>
</table>
<a name="_DECLARATION_OR_DOCTYPE"></a>
<div class="private">
<table class="details" border="1" cellpadding="3"
       cellspacing="0" width="100%" bgcolor="white">
<tr><td>
  <h3 class="epydoc">_DECLARATION_OR_DOCTYPE</h3>
  
  <dl class="fields">
  </dl>
  <dl class="fields">
    <dt>Value:</dt>
      <dd><table><tr><td><pre class="variable">
<code class="variable-group">(</code>&lt;class 'bs4.element.Declaration'&gt;<code class="variable-op">, </code>&lt;class 'bs4.element.Doctype'&gt;<code class="variable-group">)</code>
</pre></td></tr></table>
</dd>
  </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="/">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 3.0.1
    on Wed Jun 27 16:05:05 2018
    </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>