<?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.clean</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> <a href="lxml-module.html">Home</a> </th> <!-- Tree link --> <th> <a href="module-tree.html">Trees</a> </th> <!-- Index link --> <th> <a href="identifier-index.html">Indices</a> </th> <!-- Help link --> <th> <a href="help.html">Help</a> </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 lxml</a> :: <a href="lxml.html-module.html">Package html</a> :: Module clean </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 private</a>]</span></td></tr> <tr><td align="right"><span class="options" >[<a href="frames.html" target="_top">frames</a >] | <a href="lxml.html.clean-module.html" target="_top">no frames</a>]</span></td></tr> </table> </td> </tr> </table> <!-- ==================== MODULE DESCRIPTION ==================== --> <h1 class="epydoc">Module clean</h1><p class="nomargin-top"><span class="codelink"><a href="lxml.html.clean-pysrc.html">source code</a></span></p> <p>A cleanup tool for HTML.</p> <p>Removes unwanted tags and content. See the <a href="lxml.html.clean.Cleaner-class.html" class="link">Cleaner</a> class for details.</p> <!-- ==================== 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"> </span> </td><td class="summary"> <a href="str-class.html" class="summary-name" onclick="show_private();">unicode</a><br /> str(object='') -> string </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a href="str-class.html" class="summary-name" onclick="show_private();">bytes</a><br /> str(object='') -> string </td> </tr> <tr> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a href="lxml.html.clean.Cleaner-class.html" class="summary-name">Cleaner</a><br /> Instances cleans the document of each of the possible offending elements. The cleaning is controlled by attributes; you can override attributes in a subclass, or set them in the constructor. </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 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 <= i < 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"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="_is_image_dataurl"></a><span class="summary-sig-name">_is_image_dataurl</span>(<span class="summary-sig-arg">...</span>)</span><br /> search(string[, pos[, endpos]]) --> match object or None. Scan through string looking for a match, and return a corresponding match object instance. Return None if no position in the string matches.</td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#_is_image_dataurl">source code</a></span> </td> </tr> </table> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="_is_possibly_malicious_scheme"></a><span class="summary-sig-name">_is_possibly_malicious_scheme</span>(<span class="summary-sig-arg">...</span>)</span><br /> search(string[, pos[, endpos]]) --> match object or None. Scan through string looking for a match, and return a corresponding match object instance. Return None if no position in the string matches.</td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#_is_possibly_malicious_scheme">source code</a></span> </td> </tr> </table> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="_is_javascript_scheme"></a><span class="summary-sig-name">_is_javascript_scheme</span>(<span class="summary-sig-arg">s</span>)</span></td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#_is_javascript_scheme">source code</a></span> </td> </tr> </table> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="_substitute_whitespace"></a><span class="summary-sig-name">_substitute_whitespace</span>(<span class="summary-sig-arg">...</span>)</span><br /> sub(repl, string[, count = 0]) --> 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.clean-pysrc.html#_substitute_whitespace">source code</a></span> </td> </tr> </table> </td> </tr> <tr> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="clean_html"></a><span class="summary-sig-name">clean_html</span>(<span class="summary-sig-arg">...</span>)</span></td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#clean_html">source code</a></span> </td> </tr> </table> </td> </tr> <tr> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a href="lxml.html.clean-module.html#autolink" class="summary-sig-name">autolink</a>(<span class="summary-sig-arg">el</span>, <span class="summary-sig-arg">link_regexes</span>=<span class="summary-sig-default">_link_regexes</span>, <span class="summary-sig-arg">avoid_elements</span>=<span class="summary-sig-default">_avoid_elements</span>, <span class="summary-sig-arg">avoid_hosts</span>=<span class="summary-sig-default">_avoid_hosts</span>, <span class="summary-sig-arg">avoid_classes</span>=<span class="summary-sig-default">_avoid_classes</span>)</span><br /> Turn any URLs into links.</td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink">source code</a></span> </td> </tr> </table> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="_link_text"></a><span class="summary-sig-name">_link_text</span>(<span class="summary-sig-arg">text</span>, <span class="summary-sig-arg">link_regexes</span>, <span class="summary-sig-arg">avoid_hosts</span>, <span class="summary-sig-arg">factory</span>)</span></td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#_link_text">source code</a></span> </td> </tr> </table> </td> </tr> <tr> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a href="lxml.html.clean-module.html#autolink_html" class="summary-sig-name">autolink_html</a>(<span class="summary-sig-arg">html</span>)</span><br /> Turn any URLs into links.</td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink_html">source code</a></span> </td> </tr> </table> </td> </tr> <tr> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a href="lxml.html.clean-module.html#word_break" class="summary-sig-name">word_break</a>(<span class="summary-sig-arg">el</span>, <span class="summary-sig-arg">max_width</span>=<span class="summary-sig-default">40</span>, <span class="summary-sig-arg">avoid_elements</span>=<span class="summary-sig-default">_avoid_word_break_elements</span>, <span class="summary-sig-arg">avoid_classes</span>=<span class="summary-sig-default">_avoid_word_break_classes</span>, <span class="summary-sig-arg">break_character</span>=<span class="summary-sig-default">unichr(0x200b)</span>)</span><br /> Breaks any long words found in the body of the text (not attributes).</td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#word_break">source code</a></span> </td> </tr> </table> </td> </tr> <tr> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="word_break_html"></a><span class="summary-sig-name">word_break_html</span>(<span class="summary-sig-arg">html</span>)</span></td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#word_break_html">source code</a></span> </td> </tr> </table> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="_break_text"></a><span class="summary-sig-name">_break_text</span>(<span class="summary-sig-arg">text</span>, <span class="summary-sig-arg">max_width</span>, <span class="summary-sig-arg">break_character</span>)</span></td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#_break_text">source code</a></span> </td> </tr> </table> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <table width="100%" cellpadding="0" cellspacing="0" border="0"> <tr> <td><span class="summary-sig"><a name="_insert_break"></a><span class="summary-sig-name">_insert_break</span>(<span class="summary-sig-arg">word</span>, <span class="summary-sig-arg">width</span>, <span class="summary-sig-arg">break_character</span>)</span></td> <td align="right" valign="top"> <span class="codelink"><a href="lxml.html.clean-pysrc.html#_insert_break">source 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"> </span> </td><td class="summary"> <a name="basestring"></a><span class="summary-name">basestring</span> = <code title="str, bytes">str, bytes</code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="_css_javascript_re"></a><span class="summary-name">_css_javascript_re</span> = <code title="re.compile(r'(?is)expression\s*\(.*?\)')">re.compile(r'<code class="re-flags">(?is)</code>expression\s<code class="re-op">*</code>\(.<code class="re-op">*?</code>\)')</code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="_css_import_re"></a><span class="summary-name">_css_import_re</span> = <code title="re.compile(r'(?i)@\s*import')">re.compile(r'<code class="re-flags">(?i)</code>@\s<code class="re-op">*</code>import')</code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a href="lxml.html.clean-module.html#_conditional_comment_re" class="summary-name" onclick="show_private();">_conditional_comment_re</a> = <code title="re.compile(r'(?is)\[if[\s\n\r]+.*?\][\s\n\r]*>')">re.compile(r'<code class="re-flags">(?is)</code>\[if<code class="re-group">[</code>\s\n\r<code class="re-group">]</code><code class="re-op">+</code>.<code class="re-op">*?</code>\]<code class="variable-ellipsis">...</code></code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="_find_styled_elements"></a><span class="summary-name">_find_styled_elements</span> = <code title="descendant-or-self::*[@style]">descendant-or-self::*[@style]</code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a href="lxml.html.clean-module.html#_find_external_links" class="summary-name" onclick="show_private();">_find_external_links</a> = <code title="descendant-or-self::a [normalize-space(@href) and substring(normalize\ -space(@href),1,1) != '#'] |descendant-or-self::x:a[normalize-space(@h\ ref) and substring(normalize-space(@href),1,1) != '#']">descendant-or-self::a [normalize-space<code class="variable-ellipsis">...</code></code> </td> </tr> <tr> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="clean"></a><span class="summary-name">clean</span> = <code title="<lxml.html.clean.Cleaner object>"><lxml.html.clean.Cleaner object></code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a href="lxml.html.clean-module.html#_link_regexes" class="summary-name" onclick="show_private();">_link_regexes</a> = <code title="[re.compile(r'(?i)(?P<body>https?://(?P<host>[a-z0-9\._-]+)(?:/[/-_\.,\ a-z0-9%&\?;=~]*)?(?:\([/-_\.,a-z0-9%&\?;=~]*\))?)'), re.compile(r'(?i)mailto:(?P<body>[a-z0-9\._-]+@(?P<host>[a-z0-9_\.-]+\ [a-z]))')]"><code class="variable-group">[</code>re.compile(r'<code class="re-flags">(?i)</code><code class="re-group">(?P<</code><code class="re-ref">body</code><code class="re-group">></code>https<code class="re-op">?</code>://<code class="re-group">(?P<</code><code class="re-ref">host</code><code class="re-group">></code><code class="re-group">[</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"> </span> </td><td class="summary"> <a href="lxml.html.clean-module.html#_avoid_elements" class="summary-name" onclick="show_private();">_avoid_elements</a> = <code title="['textarea', 'pre', 'code', 'head', 'select', 'a']"><code class="variable-group">[</code><code class="variable-quote">'</code><code class="variable-string">textarea</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">pre</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">code</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">head</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">select</code><code class="variable-quote">'</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"> </span> </td><td class="summary"> <a href="lxml.html.clean-module.html#_avoid_hosts" class="summary-name" onclick="show_private();">_avoid_hosts</a> = <code title="[re.compile(r'(?i)^localhost'), re.compile(r'(?i)\bexample\.(?:com|org|net)$'), re.compile(r'^127\.0\.0\.1$')]"><code class="variable-group">[</code>re.compile(r'<code class="re-flags">(?i)</code>^localhost')<code class="variable-op">, </code>re.compile(r'<code class="re-flags">(?</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"> </span> </td><td class="summary"> <a name="_avoid_classes"></a><span class="summary-name">_avoid_classes</span> = <code title="['nolink']"><code class="variable-group">[</code><code class="variable-quote">'</code><code class="variable-string">nolink</code><code class="variable-quote">'</code><code class="variable-group">]</code></code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="_avoid_word_break_elements"></a><span class="summary-name">_avoid_word_break_elements</span> = <code title="['pre', 'textarea', 'code']"><code class="variable-group">[</code><code class="variable-quote">'</code><code class="variable-string">pre</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">textarea</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">code</code><code class="variable-quote">'</code><code class="variable-group">]</code></code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="_avoid_word_break_classes"></a><span class="summary-name">_avoid_word_break_classes</span> = <code title="['nobreak']"><code class="variable-group">[</code><code class="variable-quote">'</code><code class="variable-string">nobreak</code><code class="variable-quote">'</code><code class="variable-group">]</code></code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="_break_prefer_re"></a><span class="summary-name">_break_prefer_re</span> = <code title="re.compile(r'(?i)[^a-z]')">re.compile(r'<code class="re-flags">(?i)</code><code class="re-group">[</code><code class="re-op">^</code>a<code class="re-op">-</code>z<code class="re-group">]</code>')</code> </td> </tr> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </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> <tr class="private"> <td width="15%" align="right" valign="top" class="summary"> <span class="summary-type"> </span> </td><td class="summary"> <a name="__test__"></a><span class="summary-name">__test__</span> = <code title="{}"><code class="variable-group">{</code><code class="variable-group">}</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="autolink"></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">autolink</span>(<span class="sig-arg">el</span>, <span class="sig-arg">link_regexes</span>=<span class="sig-default">_link_regexes</span>, <span class="sig-arg">avoid_elements</span>=<span class="sig-default">_avoid_elements</span>, <span class="sig-arg">avoid_hosts</span>=<span class="sig-default">_avoid_hosts</span>, <span class="sig-arg">avoid_classes</span>=<span class="sig-default">_avoid_classes</span>)</span> </h3> </td><td align="right" valign="top" ><span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink">source code</a></span> </td> </tr></table> <p>Turn any URLs into links.</p> <p>It will search for links identified by the given regular expressions (by default mailto and http(s) links).</p> <p>It won't link text in an element in avoid_elements, or an element with a class in avoid_classes. It won't link to anything with a host that matches one of the regular expressions in avoid_hosts (default localhost and 127.0.0.1).</p> <p>If you pass in an element, the element's tail will not be substituted, only the contents of the element.</p> <dl class="fields"> </dl> </td></tr></table> </div> <a name="autolink_html"></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">autolink_html</span>(<span class="sig-arg">html</span>)</span> </h3> </td><td align="right" valign="top" ><span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink_html">source code</a></span> </td> </tr></table> <p>Turn any URLs into links.</p> <p>It will search for links identified by the given regular expressions (by default mailto and http(s) links).</p> <p>It won't link text in an element in avoid_elements, or an element with a class in avoid_classes. It won't link to anything with a host that matches one of the regular expressions in avoid_hosts (default localhost and 127.0.0.1).</p> <p>If you pass in an element, the element's tail will not be substituted, only the contents of the element.</p> <dl class="fields"> </dl> </td></tr></table> </div> <a name="word_break"></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">word_break</span>(<span class="sig-arg">el</span>, <span class="sig-arg">max_width</span>=<span class="sig-default">40</span>, <span class="sig-arg">avoid_elements</span>=<span class="sig-default">_avoid_word_break_elements</span>, <span class="sig-arg">avoid_classes</span>=<span class="sig-default">_avoid_word_break_classes</span>, <span class="sig-arg">break_character</span>=<span class="sig-default">unichr(0x200b)</span>)</span> </h3> </td><td align="right" valign="top" ><span class="codelink"><a href="lxml.html.clean-pysrc.html#word_break">source code</a></span> </td> </tr></table> <p>Breaks any long words found in the body of the text (not attributes).</p> <p>Doesn't effect any of the tags in avoid_elements, by default <tt class="rst-docutils literal"><textarea></tt> and <tt class="rst-docutils literal"><pre></tt></p> <p>Breaks words by inserting &#8203;, which is a unicode character for Zero Width Space character. This generally takes up no space in rendering, but does copy as a space, and in monospace contexts usually takes up space.</p> <p>See <a class="rst-reference external" href="http://www.cs.tut.fi/~jkorpela/html/nobr.html" target="_top">http://www.cs.tut.fi/~jkorpela/html/nobr.html</a> for a discussion</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="_conditional_comment_re"></a> <div class="private"> <table class="details" border="1" cellpadding="3" cellspacing="0" width="100%" bgcolor="white"> <tr><td> <h3 class="epydoc">_conditional_comment_re</h3> <dl class="fields"> </dl> <dl class="fields"> <dt>Value:</dt> <dd><table><tr><td><pre class="variable"> re.compile(r'<code class="re-flags">(?is)</code>\[if<code class="re-group">[</code>\s\n\r<code class="re-group">]</code><code class="re-op">+</code>.<code class="re-op">*?</code>\]<code class="re-group">[</code>\s\n\r<code class="re-group">]</code><code class="re-op">*</code>>') </pre></td></tr></table> </dd> </dl> </td></tr></table> </div> <a name="_find_external_links"></a> <div class="private"> <table class="details" border="1" cellpadding="3" cellspacing="0" width="100%" bgcolor="white"> <tr><td> <h3 class="epydoc">_find_external_links</h3> <dl class="fields"> </dl> <dl class="fields"> <dt>Value:</dt> <dd><table><tr><td><pre class="variable"> descendant-or-self::a [normalize-space(@href) and substring(normalize<span class="variable-linewrap"><img src="crarr.png" alt="\" /></span> -space(@href),1,1) != '#'] |descendant-or-self::x:a[normalize-space(@h<span class="variable-linewrap"><img src="crarr.png" alt="\" /></span> ref) and substring(normalize-space(@href),1,1) != '#'] </pre></td></tr></table> </dd> </dl> </td></tr></table> </div> <a name="_link_regexes"></a> <div class="private"> <table class="details" border="1" cellpadding="3" cellspacing="0" width="100%" bgcolor="white"> <tr><td> <h3 class="epydoc">_link_regexes</h3> <dl class="fields"> </dl> <dl class="fields"> <dt>Value:</dt> <dd><table><tr><td><pre class="variable"> <code class="variable-group">[</code>re.compile(r'<code class="re-flags">(?i)</code><code class="re-group">(?P<</code><code class="re-ref">body</code><code class="re-group">></code>https<code class="re-op">?</code>://<code class="re-group">(?P<</code><code class="re-ref">host</code><code class="re-group">></code><code class="re-group">[</code>a<code class="re-op">-</code>z0<code class="re-op">-</code>9\._-<code class="re-group">]</code><code class="re-op">+</code><code class="re-group">)</code><code class="re-group">(?:</code>/<code class="re-group">[</code>/-_\.,<span class="variable-linewrap"><img src="crarr.png" alt="\" /></span> a<code class="re-op">-</code>z0<code class="re-op">-</code>9%&\?;=~<code class="re-group">]</code><code class="re-op">*</code><code class="re-group">)</code><code class="re-op">?</code><code class="re-group">(?:</code>\(<code class="re-group">[</code>/-_\.,a<code class="re-op">-</code>z0<code class="re-op">-</code>9%&\?;=~<code class="re-group">]</code><code class="re-op">*</code>\)<code class="re-group">)</code><code class="re-op">?</code><code class="re-group">)</code>')<code class="variable-op">,</code> re.compile(r'<code class="re-flags">(?i)</code>mailto:<code class="re-group">(?P<</code><code class="re-ref">body</code><code class="re-group">></code><code class="re-group">[</code>a<code class="re-op">-</code>z0<code class="re-op">-</code>9\._-<code class="re-group">]</code><code class="re-op">+</code>@<code class="re-group">(?P<</code><code class="re-ref">host</code><code class="re-group">></code><code class="re-group">[</code>a<code class="re-op">-</code>z0<code class="re-op">-</code>9_\.-<code class="re-group">]</code><code class="re-op">+</code><code class="re-group"></code><span class="variable-linewrap"><img src="crarr.png" alt="\" /></span> <code class="re-group">[</code>a<code class="re-op">-</code>z<code class="re-group">]</code><code class="re-group">)</code><code class="re-group">)</code>')<code class="variable-group">]</code> </pre></td></tr></table> </dd> </dl> </td></tr></table> </div> <a name="_avoid_elements"></a> <div class="private"> <table class="details" border="1" cellpadding="3" cellspacing="0" width="100%" bgcolor="white"> <tr><td> <h3 class="epydoc">_avoid_elements</h3> <dl class="fields"> </dl> <dl class="fields"> <dt>Value:</dt> <dd><table><tr><td><pre class="variable"> <code class="variable-group">[</code><code class="variable-quote">'</code><code class="variable-string">textarea</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">pre</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">code</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">head</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">select</code><code class="variable-quote">'</code><code class="variable-op">, </code><code class="variable-quote">'</code><code class="variable-string">a</code><code class="variable-quote">'</code><code class="variable-group">]</code> </pre></td></tr></table> </dd> </dl> </td></tr></table> </div> <a name="_avoid_hosts"></a> <div class="private"> <table class="details" border="1" cellpadding="3" cellspacing="0" width="100%" bgcolor="white"> <tr><td> <h3 class="epydoc">_avoid_hosts</h3> <dl class="fields"> </dl> <dl class="fields"> <dt>Value:</dt> <dd><table><tr><td><pre class="variable"> <code class="variable-group">[</code>re.compile(r'<code class="re-flags">(?i)</code>^localhost')<code class="variable-op">,</code> re.compile(r'<code class="re-flags">(?i)</code>\bexample\.<code class="re-group">(?:</code>com<code class="re-op">|</code>org<code class="re-op">|</code>net<code class="re-group">)</code>$')<code class="variable-op">,</code> re.compile(r'^127\.0\.0\.1$')<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> <a href="lxml-module.html">Home</a> </th> <!-- Tree link --> <th> <a href="module-tree.html">Trees</a> </th> <!-- Index link --> <th> <a href="identifier-index.html">Indices</a> </th> <!-- Help link --> <th> <a href="help.html">Help</a> </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 Sun Sep 9 15:24:18 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>