The conversion of HTML into MS Word Document mainly used in the web application to generate a .doc\/.docx file with dynamic HTML content. Microsoft word document is the most popular file format to export dynamic content for offline use. Export HTML content to MS word<\/b> functionality can be easily implemented using JavaScript. But, if you want to convert dynamic content to Doc, server-side interaction is needed.<\/p>\n
The server-side export to word functionality is very useful to convert dynamic HTML content to MS word document and download as a .docx file. The MS word document can be easily generated with HTML content using PHP. In this tutorial, we will show you how to convert HTML to MS word document in PHP<\/b>.<\/p>\nHTML To Word (DOC\/DOCX) Library<\/h2>\n
The HTML_TO_DOC class is a custom library that helps to generate MS word documents and include the HTML formatted content in the Word document using PHP.<\/p>\n
<?php
<\/span>\/**
* Convert HTML to MS Word document
* @name HTML_TO_DOC
* @version 2.0
* @author CodexWorld
* @link https:\/\/www.codexworld.com
*\/
<\/span>class <\/span>HTML_TO_DOC
<\/span>{
var <\/span>$docFile <\/span>= <\/span>''<\/span>;
var <\/span>$title <\/span>= <\/span>''<\/span>;
var <\/span>$htmlHead <\/span>= <\/span>''<\/span>;
var <\/span>$htmlBody <\/span>= <\/span>''<\/span>;
<\/span>\/**
* Constructor
*
* @return void
*\/
<\/span>function <\/span>__construct<\/span>(){
<\/span>$this<\/span>-><\/span>title <\/span>= <\/span>''<\/span>;
<\/span>$this<\/span>-><\/span>htmlHead <\/span>= <\/span>''<\/span>;
<\/span>$this<\/span>-><\/span>htmlBody <\/span>= <\/span>''<\/span>;
}
<\/span>\/**
* Set the document file name
*
* @param String $docfile
*\/
<\/span>function <\/span>setDocFileName<\/span>(<\/span>$docfile<\/span>){
<\/span>$this<\/span>-><\/span>docFile <\/span>= <\/span>$docfile<\/span>;
if(!<\/span>preg_match<\/span>(<\/span>\"\/\\.doc$\/i\"<\/span>,<\/span>$this<\/span>-><\/span>docFile<\/span>) && !<\/span>preg_match<\/span>(<\/span>\"\/\\.docx$\/i\"<\/span>,<\/span>$this<\/span>-><\/span>docFile<\/span>)){
<\/span>$this<\/span>-><\/span>docFile <\/span>.= <\/span>'.doc'<\/span>;
}
return;
}
<\/span>\/**
* Set the document title
*
* @param String $title
*\/
<\/span>function <\/span>setTitle<\/span>(<\/span>$title<\/span>){
<\/span>$this<\/span>-><\/span>title <\/span>= <\/span>$title<\/span>;
}
<\/span>\/**
* Return header of MS Doc
*
* @return String
*\/
<\/span>function <\/span>getHeader<\/span>(){
<\/span>$return <\/span>= <<<EOH
<\/span> <html xmlns:v=\"urn:schemas-microsoft-com:vml\"
xmlns:o=\"urn:schemas-microsoft-com:office:office\"
xmlns:w=\"urn:schemas-microsoft-com:office:word\"
xmlns=\"http:\/\/www.w3.org\/TR\/REC-html40\">
<head>
<meta http-equiv=Content-Type content=\"text\/html; charset=utf-8\">
<meta name=ProgId content=Word.Document>
<meta name=Generator content=\"Microsoft Word 9\">
<meta name=Originator content=\"Microsoft Word 9\">
<!--[if !mso]>
<style>
v\\:* {behavior:url(#default#VML);}
o\\:* {behavior:url(#default#VML);}
w\\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
<\/style>
<![endif]-->
<title><\/span>$this<\/span>-><\/span>title<\/span><\/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]-->
<\/span>$this<\/span>-><\/span>htmlHead<\/span>
<\/head>
<body>
<\/span>EOH;
return <\/span>$return<\/span>;
}
<\/span>\/**
* Return Document footer
*
* @return String
*\/
<\/span>function <\/span>getFotter<\/span>(){
return <\/span>\"<\/body><\/html>\"<\/span>;
}
<\/span>\/**
* 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 $download :: Wheather to download the file or save the file
* @return boolean
*\/
<\/span>function <\/span>createDoc<\/span>(<\/span>$html<\/span>, <\/span>$file<\/span>, <\/span>$download <\/span>= <\/span>false<\/span>){
if(<\/span>is_file<\/span>(<\/span>$html<\/span>)){
<\/span>$html <\/span>= @<\/span>file_get_contents<\/span>(<\/span>$html<\/span>);
}
<\/span>$this<\/span>-><\/span>_parseHtml<\/span>(<\/span>$html<\/span>);
<\/span>$this<\/span>-><\/span>setDocFileName<\/span>(<\/span>$file<\/span>);
<\/span>$doc <\/span>= <\/span>$this<\/span>-><\/span>getHeader<\/span>();
<\/span>$doc <\/span>.= <\/span>$this<\/span>-><\/span>htmlBody<\/span>;
<\/span>$doc <\/span>.= <\/span>$this<\/span>-><\/span>getFotter<\/span>();
if(<\/span>$download<\/span>){
@<\/span>header<\/span>(<\/span>\"Cache-Control: \"<\/span>);<\/span>\/\/ leave blank to avoid IE errors
<\/span>@<\/span>header<\/span>(<\/span>\"Pragma: \"<\/span>);<\/span>\/\/ leave blank to avoid IE errors
<\/span>@<\/span>header<\/span>(<\/span>\"Content-type: application\/octet-stream\"<\/span>);
@<\/span>header<\/span>(<\/span>\"Content-Disposition: attachment; filename=\\\"<\/span>$this<\/span>-><\/span>docFile<\/span>\\\"\"<\/span>);
echo <\/span>$doc<\/span>;
return <\/span>true<\/span>;
}else {
return <\/span>$this<\/span>-><\/span>write_file<\/span>(<\/span>$this<\/span>-><\/span>docFile<\/span>, <\/span>$doc<\/span>);
}
}
<\/span>\/**
* Parse the html and remove <head><\/head> part if present into html
*
* @param String $html
* @return void
* @access Private
*\/
<\/span>function <\/span>_parseHtml<\/span>(<\/span>$html<\/span>){
<\/span>$html <\/span>= <\/span>preg_replace<\/span>(<\/span>\"\/<!DOCTYPE((.|\\n)*?)>\/ims\"<\/span>, <\/span>\"\"<\/span>, <\/span>$html<\/span>);
<\/span>$html <\/span>= <\/span>preg_replace<\/span>(<\/span>\"\/<script((.|\\n)*?)>((.|\\n)*?)<\\\/script>\/ims\"<\/span>, <\/span>\"\"<\/span>, <\/span>$html<\/span>);
<\/span>preg_match<\/span>(<\/span>\"\/<head>((.|\\n)*?)<\\\/head>\/ims\"<\/span>, <\/span>$html<\/span>, <\/span>$matches<\/span>