Atenea
/
sgi


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254
							<?php
/**
 * Create MS Word file from HTML file or url
 * @author Filipp Yanukovich
 * @version 1.0
 * @name HtmlToDoc
 * https://github.com/votetake/HtmlToDoc
 */

 class HtmlToDoc
{
	private $docFile = "";
	private $title = "";
	private $htmlHead = "";
	private $htmlBody = "";
			
	/**
	 * Constructor
	 *
	 * @return void
	 */
	public function init()
	{
		$this->title = "Untitled Document";
		$this->htmlHead = "";
		$this->htmlBody = "";
	}
	
	/**
	 * Set the document file name
	 * @param string $docfile
	 * @return void
	 */
	
	protected function setDocFileName($docfile)
	{
		$this->docFile = $docfile;
		if(!preg_match("/\.doc$/i", $this->docFile))
		{
			$this->docFile .= ".doc";
		}
		return;		
	}
	
	public function setTitle($title)
	{
		$this->title = $title;
	}
	
	/**
	 * Return header of MS Doc format
	 *
	 * @return String
	 */
	protected function getHeader()
	{
		$return  = <<<EOH
		 <html xmlns:v="urn:schemas-microsoft-com:vml"
		xmlns:o="urn:schemas-microsoft-com:office:office"
		xmlns:w="urn:schemas-microsoft-com:office:word"
		xmlns="http://www.w3.org/TR/REC-html40">
		
		<head>
		<meta http-equiv=Content-Type content="text/html; charset=utf-8">
		<meta name=ProgId content=Word.Document>
		<meta name=Generator content="Microsoft Word 9">
		<meta name=Originator content="Microsoft Word 9">
		<!--[if !mso]>
		<style>
		v\:* {behavior:url(#default#VML);}
		o\:* {behavior:url(#default#VML);}
		w\:* {behavior:url(#default#VML);}
		.shape {behavior:url(#default#VML);}
		</style>
		<![endif]-->
		<title>$this->title</title>
		<!--[if gte mso 9]><xml>
		 <w:WordDocument>
			<w:View>Print</w:View>
			<w:DoNotHyphenateCaps/>
			<w:PunctuationKerning/>
			<w:DrawingGridHorizontalSpacing>9.35 pt</w:DrawingGridHorizontalSpacing>
			<w:DrawingGridVerticalSpacing>9.35 pt</w:DrawingGridVerticalSpacing>
		 </w:WordDocument>
		</xml><![endif]-->
		<style>
		<!--
		 /* Font Definitions */
		@font-face
			{font-family:Verdana;
			panose-1:2 11 6 4 3 5 4 4 2 4;
			mso-font-charset:0;
			mso-generic-font-family:swiss;
			mso-font-pitch:variable;
			mso-font-signature:536871559 0 0 0 415 0;}
		 /* Style Definitions */
		p.MsoNormal, li.MsoNormal, div.MsoNormal
			{mso-style-parent:"";
			margin:0in;
			margin-bottom:.0001pt;
			mso-pagination:widow-orphan;
			font-size:7.5pt;
			mso-bidi-font-size:8.0pt;
			font-family:"Verdana";
			mso-fareast-font-family:"Verdana";}
		p.small
			{mso-style-parent:"";
			margin:0in;
			margin-bottom:.0001pt;
			mso-pagination:widow-orphan;
			font-size:1.0pt;
			mso-bidi-font-size:1.0pt;
			font-family:"Verdana";
			mso-fareast-font-family:"Verdana";}
		@page Section1
			{size:8.5in 11.0in;
			margin:1.0in 1.25in 1.0in 1.25in;
			mso-header-margin:.5in;
			mso-footer-margin:.5in;
			mso-paper-source:0;}
		div.Section1
			{page:Section1;}
		-->
		</style>
		<!--[if gte mso 9]><xml>
		 <o:shapedefaults v:ext="edit" spidmax="1032">
			<o:colormenu v:ext="edit" strokecolor="none"/>
		 </o:shapedefaults></xml><![endif]--><!--[if gte mso 9]><xml>
		 <o:shapelayout v:ext="edit">
			<o:idmap v:ext="edit" data="1"/>
		 </o:shapelayout></xml><![endif]-->
		 $this->htmlHead
		</head>
		<body>
EOH;
	return $return;
	}
	
	/**
	 * Return footer
	 *
	 * @return String
	 */
	protected function getFotter()
	{
		return "</body></html>";
	}
	
	/**
	 * Parse the html and remove <head></head> part if present into html.
	 * Find and set html body and html head
	 * 
	 * @param String $html
	 * @return void	 
	 */
	
	private function _parseHtml($html)
	{
		$html = preg_replace("/<!DOCTYPE((.|\n)*?)>/ims","", $html);
		$html = preg_replace("/<script((.|\n)*?)>((.|\n)*?)<\/script>/ims", "", $html);
		preg_match("/<head>((.|\n)*?)<\/head>/ims", $html, $matches);
		$head = $matches[1];
		preg_match("/<title>((.|\n)*?)<\/title>/ims", $head, $matches);
		$this->title = $matches[1];
		$html = preg_replace("/<head>((.|\n)*?)<\/head>/ims", "", $html);
		$head = preg_replace("/<title>((.|\n)*?)<\/title>/ims", "", $head);
		$head = preg_replace("/<\/?head>/ims", "", $head);
		$html = preg_replace("/<\/?body((.|\n)*?)>/ims", "", $html);
		$this->htmlHead = $head;
		$this->htmlBody = $html;
		return;
	}
	
	/**
	 * Write the content int file
	 *
	 * @param String $file :: File name to be save
	 * @param String $content :: Content to be write
	 * @param [Optional] String $mode :: Write Mode
	 * @return void
	 * @access boolean True on success else false
	 */
	
	private function _writeFile($file, $content, $mode = "w")
	{
		$fp = @fopen($file, $mode);
		if(!is_resource($fp))
		{				
			return false;
		}
		fwrite($fp, $content);
		fclose($fp);
		return true;
	}
	
	
	/**
	 * Create The MS Word Document from given HTML
	 *
	 * @param String $html :: url like http://www.example.com
	 * @param String $file :: Document File Name
	 * @param Boolean $download :: Wheather to download the file or save the file
	 * @return boolean 
	 */
	
	public function createDocFromURL($url, $file, $download = false)
	{
		if(!preg_match("/^http:/",$url))
		{
			$url = "http://".$url;
		}
		$html = @file_get_contents($url);
		return $this->createDoc($html, $file, $download);	
	}

	/**
	 * Create The MS Word Document from given HTML
	 *
	 * @param String $html :: HTML Content or HTML File Name like path/to/html/file.html
	 * @param String $file :: Document File Name
	 * @param Boolean $download :: Wheather to download the file or save the file
	 * @return boolean 
	 */
	
	public function createDoc($html, $file, $download = false)
	{
		if(is_file($html))
		{
			$html = @file_get_contents($html);
		}
		
		$this->_parseHtml($html);
		$this->setDocFileName($file);
		$doc = $this->getHeader();
		$doc .= $this->htmlBody;
		$doc .= $this->getFotter();
						
		if($download)
		{
			@header("Cache-Control: ");// leave blank to avoid IE errors
			@header("Pragma: ");// leave blank to avoid IE errors
			@header("Content-type: application/octet-stream");
			@header("Content-Disposition: attachment; filename=\"$this->docFile\"");
			echo $doc;
			return true;
		}
		else 
		{
			return $this->_writeFile($this->docFile, $doc);
		}
	}
}

?>