doc/html/api/lxml.html.clean-module.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.clean</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.html-module.html">Package&nbsp;html</a> ::
  47         Module&nbsp;clean
  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.html.clean-module.html"
  58             target="_top">no&nbsp;frames</a>]</span></td></tr>
  59       </table>
  60     </td>
  61   </tr>
  62 </table>
  63 <!-- ==================== MODULE DESCRIPTION ==================== -->
  64 <h1 class="epydoc">Module clean</h1><p class="nomargin-top"><span class="codelink"><a href="lxml.html.clean-pysrc.html">source&nbsp;code</a></span></p>
  65 <p>A cleanup tool for HTML.</p>
  66 <p>Removes unwanted tags and content.  See the <a href="lxml.html.clean.Cleaner-class.html" class="link">Cleaner</a> class for
  67 details.</p>
  68
  69 <!-- ==================== CLASSES ==================== -->
  70 <a name="section-Classes"></a>
  71 <table class="summary" border="1" cellpadding="3"
  72        cellspacing="0" width="100%" bgcolor="white">
  73 <tr bgcolor="#70b0f0" class="table-header">
  74   <td colspan="2" class="table-header">
  75     <table border="0" cellpadding="0" cellspacing="0" width="100%">
  76       <tr valign="top">
  77         <td align="left"><span class="table-header">Classes</span></td>
  78         <td align="right" valign="top"
  79          ><span class="options">[<a href="#section-Classes"
  80          class="privatelink" onclick="toggle_private();"
  81          >hide private</a>]</span></td>
  82       </tr>
  83     </table>
  84   </td>
  85 </tr>
  86 <tr class="private">
  87     <td width="15%" align="right" valign="top" class="summary">
  88       <span class="summary-type">&nbsp;</span>
  89     </td><td class="summary">
  90         <a href="str-class.html" class="summary-name" onclick="show_private();">unicode</a><br />
  91       str(object='') -&gt; string
  92     </td>
  93   </tr>
  94 <tr>
  95     <td width="15%" align="right" valign="top" class="summary">
  96       <span class="summary-type">&nbsp;</span>
  97     </td><td class="summary">
  98         <a href="lxml.html.clean.Cleaner-class.html" class="summary-name">Cleaner</a><br />
  99       Instances cleans the document of each of the possible offending
 100 elements.  The cleaning is controlled by attributes; you can
 101 override attributes in a subclass, or set them in the constructor.
 102     </td>
 103   </tr>
 104 </table>
 105 <!-- ==================== FUNCTIONS ==================== -->
 106 <a name="section-Functions"></a>
 107 <table class="summary" border="1" cellpadding="3"
 108        cellspacing="0" width="100%" bgcolor="white">
 109 <tr bgcolor="#70b0f0" class="table-header">
 110   <td colspan="2" class="table-header">
 111     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 112       <tr valign="top">
 113         <td align="left"><span class="table-header">Functions</span></td>
 114         <td align="right" valign="top"
 115          ><span class="options">[<a href="#section-Functions"
 116          class="privatelink" onclick="toggle_private();"
 117          >hide private</a>]</span></td>
 118       </tr>
 119     </table>
 120   </td>
 121 </tr>
 122 <tr class="private">
 123     <td width="15%" align="right" valign="top" class="summary">
 124       <span class="summary-type">character</span>
 125     </td><td class="summary">
 126       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 127         <tr>
 128           <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 />
 129       Return a string of one character with ordinal i; 0 &lt;= i &lt; 256.</td>
 130           <td align="right" valign="top">
 131
 132
 133           </td>
 134         </tr>
 135       </table>
 136
 137     </td>
 138   </tr>
 139 <tr class="private">
 140     <td width="15%" align="right" valign="top" class="summary">
 141       <span class="summary-type">&nbsp;</span>
 142     </td><td class="summary">
 143       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 144         <tr>
 145           <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 />
 146       search(string[, pos[, endpos]]) --&gt; match object or None.
 147 Scan through string looking for a match, and return a corresponding
 148 match object instance. Return None if no position in the string matches.</td>
 149           <td align="right" valign="top">
 150             <span class="codelink"><a href="lxml.html.clean-pysrc.html#_is_image_dataurl">source&nbsp;code</a></span>
 151
 152           </td>
 153         </tr>
 154       </table>
 155
 156     </td>
 157   </tr>
 158 <tr class="private">
 159     <td width="15%" align="right" valign="top" class="summary">
 160       <span class="summary-type">&nbsp;</span>
 161     </td><td class="summary">
 162       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 163         <tr>
 164           <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 />
 165       search(string[, pos[, endpos]]) --&gt; match object or None.
 166 Scan through string looking for a match, and return a corresponding
 167 match object instance. Return None if no position in the string matches.</td>
 168           <td align="right" valign="top">
 169             <span class="codelink"><a href="lxml.html.clean-pysrc.html#_is_possibly_malicious_scheme">source&nbsp;code</a></span>
 170
 171           </td>
 172         </tr>
 173       </table>
 174
 175     </td>
 176   </tr>
 177 <tr class="private">
 178     <td width="15%" align="right" valign="top" class="summary">
 179       <span class="summary-type">&nbsp;</span>
 180     </td><td class="summary">
 181       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 182         <tr>
 183           <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>
 184           <td align="right" valign="top">
 185             <span class="codelink"><a href="lxml.html.clean-pysrc.html#_is_javascript_scheme">source&nbsp;code</a></span>
 186
 187           </td>
 188         </tr>
 189       </table>
 190
 191     </td>
 192   </tr>
 193 <tr class="private">
 194     <td width="15%" align="right" valign="top" class="summary">
 195       <span class="summary-type">&nbsp;</span>
 196     </td><td class="summary">
 197       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 198         <tr>
 199           <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 />
 200       sub(repl, string[, count = 0]) --&gt; newstring
 201 Return the string obtained by replacing the leftmost non-overlapping
 202 occurrences of pattern in string by the replacement repl.</td>
 203           <td align="right" valign="top">
 204             <span class="codelink"><a href="lxml.html.clean-pysrc.html#_substitute_whitespace">source&nbsp;code</a></span>
 205
 206           </td>
 207         </tr>
 208       </table>
 209
 210     </td>
 211   </tr>
 212 <tr>
 213     <td width="15%" align="right" valign="top" class="summary">
 214       <span class="summary-type">&nbsp;</span>
 215     </td><td class="summary">
 216       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 217         <tr>
 218           <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>
 219           <td align="right" valign="top">
 220             <span class="codelink"><a href="lxml.html.clean-pysrc.html#clean_html">source&nbsp;code</a></span>
 221
 222           </td>
 223         </tr>
 224       </table>
 225
 226     </td>
 227   </tr>
 228 <tr>
 229     <td width="15%" align="right" valign="top" class="summary">
 230       <span class="summary-type">&nbsp;</span>
 231     </td><td class="summary">
 232       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 233         <tr>
 234           <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>,
 235         <span class="summary-sig-arg">link_regexes</span>=<span class="summary-sig-default">_link_regexes</span>,
 236         <span class="summary-sig-arg">avoid_elements</span>=<span class="summary-sig-default">_avoid_elements</span>,
 237         <span class="summary-sig-arg">avoid_hosts</span>=<span class="summary-sig-default">_avoid_hosts</span>,
 238         <span class="summary-sig-arg">avoid_classes</span>=<span class="summary-sig-default">_avoid_classes</span>)</span><br />
 239       Turn any URLs into links.</td>
 240           <td align="right" valign="top">
 241             <span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink">source&nbsp;code</a></span>
 242
 243           </td>
 244         </tr>
 245       </table>
 246
 247     </td>
 248   </tr>
 249 <tr class="private">
 250     <td width="15%" align="right" valign="top" class="summary">
 251       <span class="summary-type">&nbsp;</span>
 252     </td><td class="summary">
 253       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 254         <tr>
 255           <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>,
 256         <span class="summary-sig-arg">link_regexes</span>,
 257         <span class="summary-sig-arg">avoid_hosts</span>,
 258         <span class="summary-sig-arg">factory</span>)</span></td>
 259           <td align="right" valign="top">
 260             <span class="codelink"><a href="lxml.html.clean-pysrc.html#_link_text">source&nbsp;code</a></span>
 261
 262           </td>
 263         </tr>
 264       </table>
 265
 266     </td>
 267   </tr>
 268 <tr>
 269     <td width="15%" align="right" valign="top" class="summary">
 270       <span class="summary-type">&nbsp;</span>
 271     </td><td class="summary">
 272       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 273         <tr>
 274           <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 />
 275       Turn any URLs into links.</td>
 276           <td align="right" valign="top">
 277             <span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink_html">source&nbsp;code</a></span>
 278
 279           </td>
 280         </tr>
 281       </table>
 282
 283     </td>
 284   </tr>
 285 <tr>
 286     <td width="15%" align="right" valign="top" class="summary">
 287       <span class="summary-type">&nbsp;</span>
 288     </td><td class="summary">
 289       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 290         <tr>
 291           <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>,
 292         <span class="summary-sig-arg">max_width</span>=<span class="summary-sig-default">40</span>,
 293         <span class="summary-sig-arg">avoid_elements</span>=<span class="summary-sig-default">_avoid_word_break_elements</span>,
 294         <span class="summary-sig-arg">avoid_classes</span>=<span class="summary-sig-default">_avoid_word_break_classes</span>,
 295         <span class="summary-sig-arg">break_character</span>=<span class="summary-sig-default">unichr(0x200b)</span>)</span><br />
 296       Breaks any long words found in the body of the text (not attributes).</td>
 297           <td align="right" valign="top">
 298             <span class="codelink"><a href="lxml.html.clean-pysrc.html#word_break">source&nbsp;code</a></span>
 299
 300           </td>
 301         </tr>
 302       </table>
 303
 304     </td>
 305   </tr>
 306 <tr>
 307     <td width="15%" align="right" valign="top" class="summary">
 308       <span class="summary-type">&nbsp;</span>
 309     </td><td class="summary">
 310       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 311         <tr>
 312           <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>
 313           <td align="right" valign="top">
 314             <span class="codelink"><a href="lxml.html.clean-pysrc.html#word_break_html">source&nbsp;code</a></span>
 315
 316           </td>
 317         </tr>
 318       </table>
 319
 320     </td>
 321   </tr>
 322 <tr class="private">
 323     <td width="15%" align="right" valign="top" class="summary">
 324       <span class="summary-type">&nbsp;</span>
 325     </td><td class="summary">
 326       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 327         <tr>
 328           <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>,
 329         <span class="summary-sig-arg">max_width</span>,
 330         <span class="summary-sig-arg">break_character</span>)</span></td>
 331           <td align="right" valign="top">
 332             <span class="codelink"><a href="lxml.html.clean-pysrc.html#_break_text">source&nbsp;code</a></span>
 333
 334           </td>
 335         </tr>
 336       </table>
 337
 338     </td>
 339   </tr>
 340 <tr class="private">
 341     <td width="15%" align="right" valign="top" class="summary">
 342       <span class="summary-type">&nbsp;</span>
 343     </td><td class="summary">
 344       <table width="100%" cellpadding="0" cellspacing="0" border="0">
 345         <tr>
 346           <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>,
 347         <span class="summary-sig-arg">width</span>,
 348         <span class="summary-sig-arg">break_character</span>)</span></td>
 349           <td align="right" valign="top">
 350             <span class="codelink"><a href="lxml.html.clean-pysrc.html#_insert_break">source&nbsp;code</a></span>
 351
 352           </td>
 353         </tr>
 354       </table>
 355
 356     </td>
 357   </tr>
 358 </table>
 359 <!-- ==================== VARIABLES ==================== -->
 360 <a name="section-Variables"></a>
 361 <table class="summary" border="1" cellpadding="3"
 362        cellspacing="0" width="100%" bgcolor="white">
 363 <tr bgcolor="#70b0f0" class="table-header">
 364   <td colspan="2" class="table-header">
 365     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 366       <tr valign="top">
 367         <td align="left"><span class="table-header">Variables</span></td>
 368         <td align="right" valign="top"
 369          ><span class="options">[<a href="#section-Variables"
 370          class="privatelink" onclick="toggle_private();"
 371          >hide private</a>]</span></td>
 372       </tr>
 373     </table>
 374   </td>
 375 </tr>
 376 <tr class="private">
 377     <td width="15%" align="right" valign="top" class="summary">
 378       <span class="summary-type">&nbsp;</span>
 379     </td><td class="summary">
 380         <a name="basestring"></a><span class="summary-name">basestring</span> = <code title="str, bytes">str, bytes</code>
 381     </td>
 382   </tr>
 383 <tr class="private">
 384     <td width="15%" align="right" valign="top" class="summary">
 385       <span class="summary-type">&nbsp;</span>
 386     </td><td class="summary">
 387         <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>
 388     </td>
 389   </tr>
 390 <tr class="private">
 391     <td width="15%" align="right" valign="top" class="summary">
 392       <span class="summary-type">&nbsp;</span>
 393     </td><td class="summary">
 394         <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>
 395     </td>
 396   </tr>
 397 <tr class="private">
 398     <td width="15%" align="right" valign="top" class="summary">
 399       <span class="summary-type">&nbsp;</span>
 400     </td><td class="summary">
 401         <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]*&gt;')">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>
 402     </td>
 403   </tr>
 404 <tr class="private">
 405     <td width="15%" align="right" valign="top" class="summary">
 406       <span class="summary-type">&nbsp;</span>
 407     </td><td class="summary">
 408         <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>
 409     </td>
 410   </tr>
 411 <tr class="private">
 412     <td width="15%" align="right" valign="top" class="summary">
 413       <span class="summary-type">&nbsp;</span>
 414     </td><td class="summary">
 415         <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\
 416 -space(@href),1,1) != '#'] |descendant-or-self::x:a[normalize-space(@h\
 417 ref) and substring(normalize-space(@href),1,1) != '#']">descendant-or-self::a  [normalize-space<code class="variable-ellipsis">...</code></code>
 418     </td>
 419   </tr>
 420 <tr>
 421     <td width="15%" align="right" valign="top" class="summary">
 422       <span class="summary-type">&nbsp;</span>
 423     </td><td class="summary">
 424         <a name="clean"></a><span class="summary-name">clean</span> = <code title="&lt;lxml.html.clean.Cleaner object&gt;">&lt;lxml.html.clean.Cleaner object&gt;</code>
 425     </td>
 426   </tr>
 427 <tr class="private">
 428     <td width="15%" align="right" valign="top" class="summary">
 429       <span class="summary-type">&nbsp;</span>
 430     </td><td class="summary">
 431         <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&lt;body&gt;https?://(?P&lt;host&gt;[a-z0-9\._-]+)(?:/[/-_\.,\
 432 a-z0-9%&amp;\?;=~]*)?(?:\([/-_\.,a-z0-9%&amp;\?;=~]*\))?)'),
 433  re.compile(r'(?i)mailto:(?P&lt;body&gt;[a-z0-9\._-]+@(?P&lt;host&gt;[a-z0-9_\.-]+\
 434 [a-z]))')]"><code class="variable-group">[</code>re.compile(r'<code class="re-flags">(?i)</code><code class="re-group">(?P&lt;</code><code class="re-ref">body</code><code class="re-group">&gt;</code>https<code class="re-op">?</code>://<code class="re-group">(?P&lt;</code><code class="re-ref">host</code><code class="re-group">&gt;</code><code class="re-group">[</code><code class="variable-ellipsis">...</code></code>
 435     </td>
 436   </tr>
 437 <tr class="private">
 438     <td width="15%" align="right" valign="top" class="summary">
 439       <span class="summary-type">&nbsp;</span>
 440     </td><td class="summary">
 441         <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>
 442     </td>
 443   </tr>
 444 <tr class="private">
 445     <td width="15%" align="right" valign="top" class="summary">
 446       <span class="summary-type">&nbsp;</span>
 447     </td><td class="summary">
 448         <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'),
 449  re.compile(r'(?i)\bexample\.(?:com|org|net)$'),
 450  re.compile(r'^127\.0\.0\.1$')]"><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>
 451     </td>
 452   </tr>
 453 <tr class="private">
 454     <td width="15%" align="right" valign="top" class="summary">
 455       <span class="summary-type">&nbsp;</span>
 456     </td><td class="summary">
 457         <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>
 458     </td>
 459   </tr>
 460 <tr class="private">
 461     <td width="15%" align="right" valign="top" class="summary">
 462       <span class="summary-type">&nbsp;</span>
 463     </td><td class="summary">
 464         <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>
 465     </td>
 466   </tr>
 467 <tr class="private">
 468     <td width="15%" align="right" valign="top" class="summary">
 469       <span class="summary-type">&nbsp;</span>
 470     </td><td class="summary">
 471         <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>
 472     </td>
 473   </tr>
 474 <tr class="private">
 475     <td width="15%" align="right" valign="top" class="summary">
 476       <span class="summary-type">&nbsp;</span>
 477     </td><td class="summary">
 478         <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>
 479     </td>
 480   </tr>
 481 <tr class="private">
 482     <td width="15%" align="right" valign="top" class="summary">
 483       <span class="summary-type">&nbsp;</span>
 484     </td><td class="summary">
 485         <a name="__package__"></a><span class="summary-name">__package__</span> = <code title="None">None</code><br />
 486       hash(x)
 487     </td>
 488   </tr>
 489 <tr class="private">
 490     <td width="15%" align="right" valign="top" class="summary">
 491       <span class="summary-type">&nbsp;</span>
 492     </td><td class="summary">
 493         <a name="__test__"></a><span class="summary-name">__test__</span> = <code title="{}"><code class="variable-group">{</code><code class="variable-group">}</code></code>
 494     </td>
 495   </tr>
 496 </table>
 497 <!-- ==================== FUNCTION DETAILS ==================== -->
 498 <a name="section-FunctionDetails"></a>
 499 <table class="details" border="1" cellpadding="3"
 500        cellspacing="0" width="100%" bgcolor="white">
 501 <tr bgcolor="#70b0f0" class="table-header">
 502   <td colspan="2" class="table-header">
 503     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 504       <tr valign="top">
 505         <td align="left"><span class="table-header">Function Details</span></td>
 506         <td align="right" valign="top"
 507          ><span class="options">[<a href="#section-FunctionDetails"
 508          class="privatelink" onclick="toggle_private();"
 509          >hide private</a>]</span></td>
 510       </tr>
 511     </table>
 512   </td>
 513 </tr>
 514 </table>
 515 <a name="autolink"></a>
 516 <div>
 517 <table class="details" border="1" cellpadding="3"
 518        cellspacing="0" width="100%" bgcolor="white">
 519 <tr><td>
 520   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 521   <tr valign="top"><td>
 522   <h3 class="epydoc"><span class="sig"><span class="sig-name">autolink</span>(<span class="sig-arg">el</span>,
 523         <span class="sig-arg">link_regexes</span>=<span class="sig-default">_link_regexes</span>,
 524         <span class="sig-arg">avoid_elements</span>=<span class="sig-default">_avoid_elements</span>,
 525         <span class="sig-arg">avoid_hosts</span>=<span class="sig-default">_avoid_hosts</span>,
 526         <span class="sig-arg">avoid_classes</span>=<span class="sig-default">_avoid_classes</span>)</span>
 527   </h3>
 528   </td><td align="right" valign="top"
 529     ><span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink">source&nbsp;code</a></span>&nbsp;
 530     </td>
 531   </tr></table>
 532
 533   <p>Turn any URLs into links.</p>
 534 <p>It will search for links identified by the given regular
 535 expressions (by default mailto and http(s) links).</p>
 536 <p>It won't link text in an element in avoid_elements, or an element
 537 with a class in avoid_classes.  It won't link to anything with a
 538 host that matches one of the regular expressions in avoid_hosts
 539 (default localhost and 127.0.0.1).</p>
 540 <p>If you pass in an element, the element's tail will not be
 541 substituted, only the contents of the element.</p>
 542   <dl class="fields">
 543   </dl>
 544 </td></tr></table>
 545 </div>
 546 <a name="autolink_html"></a>
 547 <div>
 548 <table class="details" border="1" cellpadding="3"
 549        cellspacing="0" width="100%" bgcolor="white">
 550 <tr><td>
 551   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 552   <tr valign="top"><td>
 553   <h3 class="epydoc"><span class="sig"><span class="sig-name">autolink_html</span>(<span class="sig-arg">html</span>)</span>
 554   </h3>
 555   </td><td align="right" valign="top"
 556     ><span class="codelink"><a href="lxml.html.clean-pysrc.html#autolink_html">source&nbsp;code</a></span>&nbsp;
 557     </td>
 558   </tr></table>
 559
 560   <p>Turn any URLs into links.</p>
 561 <p>It will search for links identified by the given regular
 562 expressions (by default mailto and http(s) links).</p>
 563 <p>It won't link text in an element in avoid_elements, or an element
 564 with a class in avoid_classes.  It won't link to anything with a
 565 host that matches one of the regular expressions in avoid_hosts
 566 (default localhost and 127.0.0.1).</p>
 567 <p>If you pass in an element, the element's tail will not be
 568 substituted, only the contents of the element.</p>
 569   <dl class="fields">
 570   </dl>
 571 </td></tr></table>
 572 </div>
 573 <a name="word_break"></a>
 574 <div>
 575 <table class="details" border="1" cellpadding="3"
 576        cellspacing="0" width="100%" bgcolor="white">
 577 <tr><td>
 578   <table width="100%" cellpadding="0" cellspacing="0" border="0">
 579   <tr valign="top"><td>
 580   <h3 class="epydoc"><span class="sig"><span class="sig-name">word_break</span>(<span class="sig-arg">el</span>,
 581         <span class="sig-arg">max_width</span>=<span class="sig-default">40</span>,
 582         <span class="sig-arg">avoid_elements</span>=<span class="sig-default">_avoid_word_break_elements</span>,
 583         <span class="sig-arg">avoid_classes</span>=<span class="sig-default">_avoid_word_break_classes</span>,
 584         <span class="sig-arg">break_character</span>=<span class="sig-default">unichr(0x200b)</span>)</span>
 585   </h3>
 586   </td><td align="right" valign="top"
 587     ><span class="codelink"><a href="lxml.html.clean-pysrc.html#word_break">source&nbsp;code</a></span>&nbsp;
 588     </td>
 589   </tr></table>
 590
 591   <p>Breaks any long words found in the body of the text (not attributes).</p>
 592 <p>Doesn't effect any of the tags in avoid_elements, by default
 593 <tt class="rst-docutils literal">&lt;textarea&gt;</tt> and <tt class="rst-docutils literal">&lt;pre&gt;</tt></p>
 594 <p>Breaks words by inserting &amp;#8203;, which is a unicode character
 595 for Zero Width Space character.  This generally takes up no space
 596 in rendering, but does copy as a space, and in monospace contexts
 597 usually takes up space.</p>
 598 <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>
 599   <dl class="fields">
 600   </dl>
 601 </td></tr></table>
 602 </div>
 603 <br />
 604 <!-- ==================== VARIABLES DETAILS ==================== -->
 605 <a name="section-VariablesDetails"></a>
 606 <table class="details" border="1" cellpadding="3"
 607        cellspacing="0" width="100%" bgcolor="white">
 608 <tr bgcolor="#70b0f0" class="table-header">
 609   <td colspan="2" class="table-header">
 610     <table border="0" cellpadding="0" cellspacing="0" width="100%">
 611       <tr valign="top">
 612         <td align="left"><span class="table-header">Variables Details</span></td>
 613         <td align="right" valign="top"
 614          ><span class="options">[<a href="#section-VariablesDetails"
 615          class="privatelink" onclick="toggle_private();"
 616          >hide private</a>]</span></td>
 617       </tr>
 618     </table>
 619   </td>
 620 </tr>
 621 </table>
 622 <a name="_conditional_comment_re"></a>
 623 <div class="private">
 624 <table class="details" border="1" cellpadding="3"
 625        cellspacing="0" width="100%" bgcolor="white">
 626 <tr><td>
 627   <h3 class="epydoc">_conditional_comment_re</h3>
 628
 629   <dl class="fields">
 630   </dl>
 631   <dl class="fields">
 632     <dt>Value:</dt>
 633       <dd><table><tr><td><pre class="variable">
 634 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>&gt;')
 635 </pre></td></tr></table>
 636 </dd>
 637   </dl>
 638 </td></tr></table>
 639 </div>
 640 <a name="_find_external_links"></a>
 641 <div class="private">
 642 <table class="details" border="1" cellpadding="3"
 643        cellspacing="0" width="100%" bgcolor="white">
 644 <tr><td>
 645   <h3 class="epydoc">_find_external_links</h3>
 646
 647   <dl class="fields">
 648   </dl>
 649   <dl class="fields">
 650     <dt>Value:</dt>
 651       <dd><table><tr><td><pre class="variable">
 652 descendant-or-self::a  [normalize-space(@href) and substring(normalize<span class="variable-linewrap"><img src="crarr.png" alt="\" /></span>
 653 -space(@href),1,1) != '#'] |descendant-or-self::x:a[normalize-space(@h<span class="variable-linewrap"><img src="crarr.png" alt="\" /></span>
 654 ref) and substring(normalize-space(@href),1,1) != '#']
 655 </pre></td></tr></table>
 656 </dd>
 657   </dl>
 658 </td></tr></table>
 659 </div>
 660 <a name="_link_regexes"></a>
 661 <div class="private">
 662 <table class="details" border="1" cellpadding="3"
 663        cellspacing="0" width="100%" bgcolor="white">
 664 <tr><td>
 665   <h3 class="epydoc">_link_regexes</h3>
 666
 667   <dl class="fields">
 668   </dl>
 669   <dl class="fields">
 670     <dt>Value:</dt>
 671       <dd><table><tr><td><pre class="variable">
 672 <code class="variable-group">[</code>re.compile(r'<code class="re-flags">(?i)</code><code class="re-group">(?P&lt;</code><code class="re-ref">body</code><code class="re-group">&gt;</code>https<code class="re-op">?</code>://<code class="re-group">(?P&lt;</code><code class="re-ref">host</code><code class="re-group">&gt;</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>
 673 a<code class="re-op">-</code>z0<code class="re-op">-</code>9%&amp;\?;=~<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>\(<code class="re-group">[</code>/-_\.,a<code class="re-op">-</code>z0<code class="re-op">-</code>9%&amp;\?;=~<code class="re-group">]</code><code class="re-op">*</code>\)<code class="re-group">)</code><code class="re-op">?</code><code class="re-group">)</code>')<code class="variable-op">,</code>
 674  re.compile(r'<code class="re-flags">(?i)</code>mailto:<code class="re-group">(?P&lt;</code><code class="re-ref">body</code><code class="re-group">&gt;</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&lt;</code><code class="re-ref">host</code><code class="re-group">&gt;</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>
 675 <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>
 676 </pre></td></tr></table>
 677 </dd>
 678   </dl>
 679 </td></tr></table>
 680 </div>
 681 <a name="_avoid_elements"></a>
 682 <div class="private">
 683 <table class="details" border="1" cellpadding="3"
 684        cellspacing="0" width="100%" bgcolor="white">
 685 <tr><td>
 686   <h3 class="epydoc">_avoid_elements</h3>
 687
 688   <dl class="fields">
 689   </dl>
 690   <dl class="fields">
 691     <dt>Value:</dt>
 692       <dd><table><tr><td><pre class="variable">
 693 <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>
 694 </pre></td></tr></table>
 695 </dd>
 696   </dl>
 697 </td></tr></table>
 698 </div>
 699 <a name="_avoid_hosts"></a>
 700 <div class="private">
 701 <table class="details" border="1" cellpadding="3"
 702        cellspacing="0" width="100%" bgcolor="white">
 703 <tr><td>
 704   <h3 class="epydoc">_avoid_hosts</h3>
 705
 706   <dl class="fields">
 707   </dl>
 708   <dl class="fields">
 709     <dt>Value:</dt>
 710       <dd><table><tr><td><pre class="variable">
 711 <code class="variable-group">[</code>re.compile(r'<code class="re-flags">(?i)</code>^localhost')<code class="variable-op">,</code>
 712  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>$')<code class="variable-op">,</code>
 713  re.compile(r'^127\.0\.0\.1$')<code class="variable-group">]</code>
 714 </pre></td></tr></table>
 715 </dd>
 716   </dl>
 717 </td></tr></table>
 718 </div>
 719 <br />
 720 <!-- ==================== NAVIGATION BAR ==================== -->
 721 <table class="navbar" border="0" width="100%" cellpadding="0"
 722        bgcolor="#a0c0ff" cellspacing="0">
 723   <tr valign="middle">
 724   <!-- Home link -->
 725       <th>&nbsp;&nbsp;&nbsp;<a
 726         href="lxml-module.html">Home</a>&nbsp;&nbsp;&nbsp;</th>
 727
 728   <!-- Tree link -->
 729       <th>&nbsp;&nbsp;&nbsp;<a
 730         href="module-tree.html">Trees</a>&nbsp;&nbsp;&nbsp;</th>
 731
 732   <!-- Index link -->
 733       <th>&nbsp;&nbsp;&nbsp;<a
 734         href="identifier-index.html">Indices</a>&nbsp;&nbsp;&nbsp;</th>
 735
 736   <!-- Help link -->
 737       <th>&nbsp;&nbsp;&nbsp;<a
 738         href="help.html">Help</a>&nbsp;&nbsp;&nbsp;</th>
 739
 740   <!-- Project homepage -->
 741       <th class="navbar" align="right" width="100%">
 742         <table border="0" cellpadding="0" cellspacing="0">
 743           <tr><th class="navbar" align="center"
 744             ><a class="navbar" target="_top" href="/">lxml API</a></th>
 745           </tr></table></th>
 746   </tr>
 747 </table>
 748 <table border="0" cellpadding="0" cellspacing="0" width="100%%">
 749   <tr>
 750     <td align="left" class="footer">
 751     Generated by Epydoc 3.0.1
 752     on Wed Jan 29 12:26:21 2020
 753     </td>
 754     <td align="right" class="footer">
 755       <a target="mainFrame" href="http://epydoc.sourceforge.net"
 756         >http://epydoc.sourceforge.net</a>
 757     </td>
 758   </tr>
 759 </table>
 760
 761 <script type="text/javascript">
 762   <!--
 763   // Private objects are initially displayed (because if
 764   // javascript is turned off then we want them to be
 765   // visible); but by default, we want to hide them.  So hide
 766   // them unless we have a cookie that says to show them.
 767   checkCookie();
 768   // -->
 769 </script>
 770 </body>
 771 </html>