Extract text from HTML while preserving block-level element newlines

by

Consider:

/**
 * Returns the style for a node.
 *
 * @param n The node to check.
 * @param p The property to retrieve (usually 'display').
 * @link http://www.quirksmode.org/dom/getstyles.html
 */
this.getStyle = function( n, p ) {
  return n.currentStyle ?
    n.currentStyle[p] :
    document.defaultView.getComputedStyle(n, null).getPropertyValue(p);
}

/**
 * Converts HTML to text, preserving semantic newlines for block-level
 * elements.
 *
 * @param node - The HTML node to perform text extraction.
 */
this.toText = function( node ) {
  var result="";

  if( node.nodeType == document.TEXT_NODE ) {
    // Replace repeated spaces, newlines, and tabs with a single space.
    result = node.nodeValue.replace( /\s+/g, ' ' );
  }
  else {
    for( var i = 0, j = node.childNodes.length; i < j; i++ ) {
      result += _this.toText( node.childNodes[i] );
    }

    var d = _this.getStyle( node, 'display' );

    if( d.match( /^block/ ) || d.match( /list/ ) || d.match( /row/ ) ||
        node.tagName == 'BR' || node.tagName == 'HR' ) {
      result += '\n';
    }
  }

  return result;
}

http://jsfiddle.net/3mzrV/2/

That is to say, with an exception or two, iterate through each node and print its contents, letting the browser’s computed style tell you when to insert newlines.

Leave a Comment

tech