How to write this into php code? Alt of the Image - php

How to write this into code please?
if the alt of the image is "your alt here" then its 1.
Here is the code that i made.
public function getSiteAdvisor($domain)
{
try
{
$callback_url = "https://www.mcafee.com/threat-intelligence/site/default.aspx?url=" . $domain;
$curl_response = $this->curl->get($callback_url);
if ($curl_response->headers['Status-Code'] == "200") {
libxml_use_internal_errors(TRUE);
$this->dom_doc->loadHTML($curl_response);
libxml_use_internal_errors(FALSE);
$xpath = new DOMXPath($this->dom_doc);
$tmp = $xpath->query('/html/body//div[#class="threeFourth"]//img/#alt')->item(0);
I don't know how to code the 'alt' of the image.
I add some code but not sure if this is correct.
if ($tmp->hasAttribute('src')) {
$tmp = $tmp->getAttribute('src');
if (stripos($tmp, "Minimal") !== false) {
$siteadvisor_rating = 1;
} elseif (stripos($tmp, "Moderate") !== false) {
$siteadvisor_rating = 2;
} elseif (stripos($tmp, "High") !== false) {
$siteadvisor_rating = 3;
} else {
$siteadvisor_rating = 0;
}
} else {
$siteadvisor_rating = 0;
}
} else {
$siteadvisor_rating = 0;
}
$response = array(
'status' => 'success',
'data' => array(
'siteadvisor' => (int)$siteadvisor_rating
)
);
}
catch (Exception $e)
{
$response = array(
'status' => 'error',
'msg' => $e->getMessage()
);
}
return $response;
}
Thanks

I found an answer by using this:
if ($tmp->hasAttribute('src')) {
$tmp = $tmp->getAttribute('alt');
if (stripos($tmp, "Minimal") !== false) {
$siteadvisor_rating = 1;
} elseif (stripos($tmp, "Moderate") !== false) {
$siteadvisor_rating = 2;
} elseif (stripos($tmp, "High") !== false) {
$siteadvisor_rating = 3;
} else {
$siteadvisor_rating = 0;
}
} else {
$siteadvisor_rating = 0;
}
} else {
$siteadvisor_rating = 0;

Related

Error in PHP Generator

What is the best way to inform who use my generator function if something errors occurs, instead of writing weird return or raising exception like this piece of code
function csv_file_generator($csvFilename, $delimiter = ";", $enclousure = '"') {
if(($csvHandler = fopen($csvFilename, 'rb')) === false) {
return;
}
while (($row = fgetcsv($csvHandler, 0, $delimiter, $enclousure)) !== false) {
yield $row;
}
if (feof($csvHandler) === false) {
return;
}
if (fclose($csvHandler) === false) {
return;
}
return; /* Exit Generator */
}
<?php
class CsvFileGenerator {
protected $fp;
protected $delimiter;
protected $enclousure;
public function __construct($filename, $delimiter = ";", $enclousure = '"'){
$this->delimiter=$delimiter;
$this->enclousure=$enclousure;
if(!file_exists($filename)){
throw new Exception("file [$filename] dont exists");
}
if(!is_readable($filename)){
throw new Exception("file [$filename] is not readable");
}
$this->fp = fopen($filename, 'rb');
if($this->fp === false){
throw new Exception("cant open [$filename]");
}
}
public function getGenerator(){
while (($row = fgetcsv($this->fp, 0, $this->delimiter, $this->enclousure)) !== false) {
yield $row;
}
}
public function __destruct() {
if($this->fp){
fclose($this->fp);
}
}
}
foreach( (new CsvFileGenerator('mycsvfile.csv'))->getGenerator() as $line){
#do some
}
One way to rome. :-)
How about callbacks?
function gen($i, $on_close = null, $on_error = null) {
while ($i--) {
yield $i;
if ($i === 5 && is_callable($on_close)) {
$on_close();
}
}
}
$closed = false;
$gen = gen(10, function () use (&$closed) {
$closed = true;
});
foreach ($gen as $x) {
if ($closed) {
break;
}
echo $x, PHP_EOL;
}
I'll admit its not pretty. Another options could be to return instances of special classes to let your main code know something is wrong.

PHP uploading files using <input> multiple Attribute

I'm currently having several <input type="file" fields for uploading images. I want to convert the input fields to one single field using the html multiple attribute.
My working code with multiple input fields:
<input type="file" name="popup_images_1">
<input type="file" name="popup_images_2">
<input type="file" name="popup_images_3">...
for ($i = 1; $i <= 3; $i++) {
if (is_uploaded_file($_FILES['popup_images_' . $i]['tmp_name'])) {
$products_image = new upload('popup_images_' . $i);
$products_image->set_destination(DIR_FS_CATALOG_IMAGES);
if ($products_image->parse() && $products_image->save()) {
$products_image_name = $products_image->filename;
// do database stuff
}
}
}
My new code, which is not working, with a single input field:
<input type="file" name="popup_images[]" multiple="multiple">
$num_files = count($HTTP_POST_FILES['popup_images']['tmp_name']);
for ($i = 1; $i <= $num_files; $i++) {
if (is_uploaded_file($HTTP_POST_FILES['popup_images']['tmp_name'][$i])) {
$products_image = new upload('popup_images' . $i);
$products_image->set_destination(DIR_FS_CATALOG_IMAGES);
if ($products_image->parse() && $products_image->save()) {
$products_image_name = $products_image->filename;
// do database stuff
}
}
}
Things seems to go wrong at the line where new upload('popup_images' . $i) is set. Any ideas?
This is the upload class:
class upload {
var $file, $filename, $destination, $permissions, $extensions, $tmp_filename, $message_location;
function upload($file = '', $destination = '', $permissions = '777', $extensions = '') {
$this->set_file($file);
$this->set_destination($destination);
$this->set_permissions($permissions);
$this->set_extensions($extensions);
$this->set_output_messages('direct');
if (tep_not_null($this->file) && tep_not_null($this->destination)) {
$this->set_output_messages('session');
if ( ($this->parse() == true) && ($this->save() == true) ) {
return true;
} else {
return false;
}
}
}
function parse() {
global $HTTP_POST_FILES, $messageStack;
$file = array();
if (isset($_FILES[$this->file])) {
$file = array('name' => $_FILES[$this->file]['name'],
'type' => $_FILES[$this->file]['type'],
'size' => $_FILES[$this->file]['size'],
'tmp_name' => $_FILES[$this->file]['tmp_name']);
} elseif (isset($HTTP_POST_FILES[$this->file])) {
$file = array('name' => $HTTP_POST_FILES[$this->file]['name'],
'type' => $HTTP_POST_FILES[$this->file]['type'],
'size' => $HTTP_POST_FILES[$this->file]['size'],
'tmp_name' => $HTTP_POST_FILES[$this->file]['tmp_name']);
}
if ( tep_not_null($file['tmp_name']) && ($file['tmp_name'] != 'none') && is_uploaded_file($file['tmp_name']) ) {
if (sizeof($this->extensions) > 0) {
if (!in_array(strtolower(substr($file['name'], strrpos($file['name'], '.')+1)), $this->extensions)) {
if ($this->message_location == 'direct') {
$messageStack->add(ERROR_FILETYPE_NOT_ALLOWED, 'error');
} else {
$messageStack->add_session(ERROR_FILETYPE_NOT_ALLOWED, 'error');
}
return false;
}
}
$this->set_file($file);
$this->set_filename($file['name']);
$this->set_tmp_filename($file['tmp_name']);
return $this->check_destination();
} else {
if ($this->message_location == 'direct') {
$messageStack->add(WARNING_NO_FILE_UPLOADED, 'warning');
} else {
$messageStack->add_session(WARNING_NO_FILE_UPLOADED, 'warning');
}
return false;
}
}
function save() {
global $messageStack;
if (substr($this->destination, -1) != '/') $this->destination .= '/';
if (move_uploaded_file($this->file['tmp_name'], $this->destination . $this->filename)) {
chmod($this->destination . $this->filename, $this->permissions);
if ($this->message_location == 'direct') {
$messageStack->add(SUCCESS_FILE_SAVED_SUCCESSFULLY, 'success');
} else {
$messageStack->add_session(SUCCESS_FILE_SAVED_SUCCESSFULLY, 'success');
}
return true;
} else {
if ($this->message_location == 'direct') {
$messageStack->add(ERROR_FILE_NOT_SAVED, 'error');
} else {
$messageStack->add_session(ERROR_FILE_NOT_SAVED, 'error');
}
return false;
}
}

Why base64_encode() return null

I have a 22M docx file and want to encode it using base64_encode() function in php. But It always returns NULL value after running this function. Is there any limit file size or condition for this function. My code:
$handle = fopen($fullpathfile, "rb");
$imagestr = base64_encode(fread($handle, filesize($fullpathfile)));
fclose($handle);
Try this code
$fh = fopen($fullpathfile, 'rb');
$cache = '';
$eof = false;
while (1) {
if (!$eof) {
if (!feof($fh)) {
$row = fgets($fh, 4096);
} else {
$row = '';
$eof = true;
}
}
if ($cache !== '')
$row = $cache.$row;
elseif ($eof)
break;
$b64 = base64_encode($row);
$put = '';
if (strlen($b64) < 76) {
if ($eof) {
$put = $b64."\n";
$cache = '';
} else {
$cache = $row;
}
} elseif (strlen($b64) > 76) {
do {
$put .= substr($b64, 0, 76)."\n";
$b64 = substr($b64, 76);
} while (strlen($b64) > 76);
$cache = base64_decode($b64);
} else {
if (!$eof && $b64{75} == '=') {
$cache = $row;
} else {
$put = $b64."\n";
$cache = '';
}
}
if ($put !== '') {
echo $put;
}
}
fclose($fh);

PHP DOCX convert to HTML [duplicate]

I want to be able to upload an MS word document and export it a page in my site.
Is there any way to accomplish this?
//FUNCTION :: read a docx file and return the string
function readDocx($filePath) {
// Create new ZIP archive
$zip = new ZipArchive;
$dataFile = 'word/document.xml';
// Open received archive file
if (true === $zip->open($filePath)) {
// If done, search for the data file in the archive
if (($index = $zip->locateName($dataFile)) !== false) {
// If found, read it to the string
$data = $zip->getFromIndex($index);
// Close archive file
$zip->close();
// Load XML from a string
// Skip errors and warnings
$xml = DOMDocument::loadXML($data, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING);
// Return data without XML formatting tags
$contents = explode('\n',strip_tags($xml->saveXML()));
$text = '';
foreach($contents as $i=>$content) {
$text .= $contents[$i];
}
return $text;
}
$zip->close();
}
// In case of failure return empty string
return "";
}
ZipArchive and DOMDocument are both inside PHP so you don't need to install/include/require additional libraries.
One may use PHPDocX.
It has support for practically all HTML CSS styles. Moreover you may use templates to add extra formatting to your HTML via the replaceTemplateVariableByHTML.
The HTML methods of PHPDocX also allow for the direct use of Word styles. You may use something like this:
$docx->embedHTML($myHTML, array('tableStyle' => 'MediumGrid3-accent5PHPDOCX'));
If you want that all your tables use the MediumGrid3-accent5 Word style. The embedHTML method as well as its version for templates (replaceTemplateVariableByHTML) preserve inheritance, meaning by that that you may use a predefined Word style and override with CSS any of its properties.
You may also extract selected parts of your HTML using 'JQuery type' selectors.
You can convert Word docx documents to html using Print2flash library. Here is an PHP excerpt from my client's site which converts a document to html:
include("const.php");
$p2fServ = new COM("Print2Flash4.Server2");
$p2fServ->DefaultProfile->DocumentType=HTML5;
$p2fServ->ConvertFile($wordfile,$htmlFile);
It converts a document which path is specified in $wordfile variable to a html page file specified by $htmlFile variable. All formatting, hyperlinks and charts are retained. You can get the required const.php file altogether with a fuller sample from Print2flash SDK.
this is a workaround based on David Lin's answer above
removing "w:" in a docx's xml tags leave behing Html like tags
function readDocx($filePath) {
// Create new ZIP archive
$zip = new ZipArchive;
$dataFile = 'word/document.xml';
// Open received archive file
if (true === $zip->open($filePath)) {
// If done, search for the data file in the archive
if (($index = $zip->locateName($dataFile)) !== false) {
// If found, read it to the string
$data = $zip->getFromIndex($index);
// Close archive file
$zip->close();
// Load XML from a string
// Skip errors and warnings
$xml = new DOMDocument("1.0", "utf-8");
$xml->loadXML($data, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING|LIBXML_PARSEHUGE);
$xml->encoding = "utf-8";
// Return data without XML formatting tags
$output = $xml->saveXML();
$output = str_replace("w:","",$output);
return $output;
}
$zip->close();
}
// In case of failure return empty string
return "";
}
Ok Im in very late, but thought I'd post this to save you all some time.
This is some php code I have put together not just to read the text from docx but the images too, currently it does not support floating images / text, but what I have done so far is a massive move forwards to whats already been posted on here - note you need to update https://example.co.uk to YOUR domain name.
<?php
class Docx_ws_imglnk {
public $originalpath = '';
public $extractedpath = '';
}
class Docx_ws_rel {
public $Id = '';
public $Target = '';
}
class Docx_ws_def {
public $styleId = '';
public $type = '';
public $color = '000000';
}
class Docx_p_def {
public $data = array();
public $text = "";
}
class Docx_p_item {
public $name = "";
public $value = "";
public $innerstyle = "";
public $type = "text";
}
class Docx_reader {
private $fileData = false;
private $errors = array();
public $rels = array();
public $imglnks = array();
public $styles = array();
public $document = null;
public $paragraphs = array();
public $path = '';
private $saveimgpath = 'docimages';
public function __construct() {
}
private function load($file) {
if (file_exists($file)) {
$zip = new ZipArchive();
$openedZip = $zip->open($file);
if ($openedZip === true) {
$this->path = $file;
//read and save images
for ( $i = 0; $i < $zip->numFiles; $i ++ ) {
$zip_element = $zip->statIndex( $i );
if ( preg_match( "([^\s]+(\.(?i)(jpg|jpeg|png|gif|bmp))$)", $zip_element['name'] ) ) {
$imglnk = new Docx_ws_imglnk;
$imglnk->originalpath = $zip_element['name'];
$imagename = explode( '/', $zip_element['name'] );
$imagename = end( $imagename );
$imglnk->extractedpath = dirname( __FILE__ ) . '/' . $this->savepath . $imagename;
$putres = file_put_contents( $imglnk->extractedpath, $zip->getFromIndex( $i ));
$imglnk->extractedpath = str_replace('var/www/', 'https://example.co.uk/', $imglnk->extractedpath);
$imglnk->extractedpath = substr($imglnk->extractedpath, 1);
array_push($this->imglnks, $imglnk);
}
}
//read relationships
if (($styleIndex = $zip->locateName('word/_rels/document.xml.rels')) !== false) {
$stylesRels = $zip->getFromIndex($styleIndex);
$xml = simplexml_load_string($stylesRels);
$XMLTEXT = $xml->saveXML();
$doc = new DOMDocument();
$doc->loadXML($XMLTEXT);
foreach($doc->documentElement->childNodes as $childnode)
{
$nodename = $childnode->nodeName;
if($childnode->hasAttributes())
{
$rel = new Docx_ws_rel;
for ($a = 0; $a < $childnode->attributes->count(); $a++)
{
$attrNode = $childnode->attributes->item($a);
if (strcmp( $attrNode->nodeName, 'Id') == 0)
{
$rel->Id = $attrNode->nodeValue;
}
if (strcmp( $attrNode->nodeName, 'Target') == 0)
{
$rel->Target = $attrNode->nodeValue;
}
}
array_push($this->rels, $rel);
}
}
}
//attempt to load styles:
if (($styleIndex = $zip->locateName('word/styles.xml')) !== false) {
$stylesXml = $zip->getFromIndex($styleIndex);
$xml = simplexml_load_string($stylesXml);
$XMLTEXT = $xml->saveXML();
$doc = new DOMDocument();
$doc->loadXML($XMLTEXT);
foreach($doc->documentElement->childNodes as $childnode)
{
$nodename = $childnode->nodeName;
//get style
if (strcmp($nodename, "w:style") == 0)
{
$ws_def = new Docx_ws_def;
for ($a=0; $a < $childnode->attributes->count(); $a++ )
{
$item = $childnode->attributes->item($a);
//style id
if (strcmp($item->nodeName, "w:styleId") == 0)
{
$ws_def->styleId = $item->nodeValue;
}
//style type
if (strcmp($item->nodeName, "w:type") == 0)
{
$ws_def->type = $item->nodeValue;
}
}
}
//push style to the array of styles
if (strcmp($ws_def->styleId, "") != 0 && strcmp($ws_def->type, "") != 0)
{
array_push($this->styles, $ws_def);
}
}
}
if (($index = $zip->locateName('word/document.xml')) !== false) {
$stylesDoc = $zip->getFromIndex($index);
$xml = simplexml_load_string($stylesDoc);
$XMLTEXT = $xml->saveXML();
$this->document = new DOMDocument();
$this->document->loadXML($XMLTEXT);
}
$zip->close();
} else {
switch($openedZip) {
case ZipArchive::ER_EXISTS:
$this->errors[] = 'File exists.';
break;
case ZipArchive::ER_INCONS:
$this->errors[] = 'Inconsistent zip file.';
break;
case ZipArchive::ER_MEMORY:
$this->errors[] = 'Malloc failure.';
break;
case ZipArchive::ER_NOENT:
$this->errors[] = 'No such file.';
break;
case ZipArchive::ER_NOZIP:
$this->errors[] = 'File is not a zip archive.';
break;
case ZipArchive::ER_OPEN:
$this->errors[] = 'Could not open file.';
break;
case ZipArchive::ER_READ:
$this->errors[] = 'Read error.';
break;
case ZipArchive::ER_SEEK:
$this->errors[] = 'Seek error.';
break;
}
}
} else {
$this->errors[] = 'File does not exist.';
}
}
public function setFile($path) {
$this->fileData = $this->load($path);
}
public function to_plain_text() {
if ($this->fileData) {
return strip_tags($this->fileData);
} else {
return false;
}
}
public function processDocument() {
$html = '';
foreach($this->document->documentElement->childNodes as $childnode)
{
$nodename = $childnode->nodeName;
//get the body of the document
if (strcmp($nodename, "w:body") == 0)
{
foreach($childnode->childNodes as $subchildnode)
{
$pnodename = $subchildnode->nodeName;
//process every paragraph
if (strcmp($pnodename, "w:p") == 0)
{
$pdef = new Docx_p_def;
foreach($subchildnode->childNodes as $pchildnode)
{
//process any inner children
if (strcmp($pchildnode, "w:pPr") == 0)
{
foreach($pchildnode->childNodes as $prchildnode)
{
//process text alignment
if (strcmp($prchildnode->nodeName, "w:pStyle") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'styleId';
$pitem->value = $prchildnode->attributes->getNamedItem('val')->nodeValue;
array_push($pdef->data, $pitem);
}
//process text alignment
if (strcmp($prchildnode->nodeName, "w:jc") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'align';
$pitem->value = $prchildnode->attributes->getNamedItem('val')->nodeValue;
if (strcmp($pitem->value, "left") == 0)
{
$pitem->innerstyle .= "text-align:" . $pitem->value . ";";
}
if (strcmp($pitem->value, "center") == 0)
{
$pitem->innerstyle .= "text-align:" . $pitem->value . ";";
}
if (strcmp($pitem->value, "right") == 0)
{
$pitem->innerstyle .= "text-align:" . $pitem->value . ";";
}
if (strcmp($pitem->value, "both") == 0)
{
$pitem->innerstyle .= "word-spacing:" . 10 . "px;";
}
array_push($pdef->data, $pitem);
}
//process drawing
if (strcmp($prchildnode->nodeName, "w:drawing") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'drawing';
$pitem->value = '';
$pitem->type = 'graphic';
$extents = $prchildnode->getElementsByTagName('extent')[0];
$cx = $extents->attributes->getNamedItem('cx')->nodeValue;
$cy = $extents->attributes->getNamedItem('cy')->nodeValue;
$pcx = (int)$cx / 9525;
$pcy = (int)$cy / 9525;
$pitem->innerstyle .= "width:" . $pcx . "px;";
$pitem->innerstyle .= "height:" . $pcy . "px;";
$blip = $prchildnode->getElementsByTagName('blip')[0];
$pitem->value = $blip->attributes->getNamedItem('embed')->nodeValue;
array_push($pdef->data, $pitem);
}
//process spacing
if (strcmp($prchildnode->nodeName, "w:spacing") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'paragraphSpacing';
$bval = $prchildnode->attributes->getNamedItem('before')->nodeValue;
if (strcmp($bval, '') == 0)
$bval = 0;
$pitem->innerstyle .= "padding-top:" . $bval . "px;";
$aval = $prchildnode->attributes->getNamedItem('after')->nodeValue;
if (strcmp($aval, '') == 0)
$aval = 0;
$pitem->innerstyle .= "padding-bottom:" . $aval . "px;";
array_push($pdef->data, $pitem);
}
}
}
if (strcmp($pchildnode, "w:r") == 0)
{
foreach($pchildnode->childNodes as $rchildnode)
{
//process text
if (strcmp($rchildnode->nodeName, "w:t") == 0)
{
$pdef->text .= $rchildnode->nodeValue;
if (count($pdef->data) == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'styleId';
$pitem->value = '';
array_push($pdef->data, $pitem);
}
}
if (strcmp($rchildnode->nodeName, "w:rPr") == 0)
{
foreach($rchildnode->childNodes as $rPrchildnode)
{
if (strcmp($rPrchildnode->nodeName, "w:b") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textBold';
$pitem->value = '';
$pitem->innerstyle .= "text-weight: 500;";
array_push($pdef->data, $pitem);
}
if (strcmp($rPrchildnode->nodeName, "w:i") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textItalic';
$pitem->value = '';
$pitem->innerstyle .= "text-style: italic;";
array_push($pdef->data, $pitem);
}
if (strcmp($rPrchildnode->nodeName, "w:u") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textUnderline';
$pitem->value = '';
$pitem->innerstyle .= "text-decoration: underline;";
array_push($pdef->data, $pitem);
}
if (strcmp($rPrchildnode->nodeName, "w:sz") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textSize';
$sz = $rPrchildnode->attributes->getNamedItem('val')->nodeValue;
if ($sz == '')
{
$sz=0;
}
$pitem->value = $sz;
array_push($pdef->data, $pitem);
}
}
}
}
}
}
array_push($this->paragraphs, $pdef);
}
}
}
}
}
public function to_html()
{
$html = '';
foreach($this->paragraphs as $para)
{
$styleselect = null;
$type = 'text';
$content = $para->text;
$sz = 0;
$extent = '';
$embedid = '';
$pinnerstylesid = '';
$pinnerstylesunderline = '';
$pinnerstylessz = '';
if (count($para->data) > 0)
{
foreach($para->data as $node)
{
if (strcmp($node->name, "styleId") == 0)
{
$type = $node->type;
$pinnerstylesid = $node->innerstyle;
foreach($this->styles as $style)
{
if (strcmp ($node->value, $style->styleId) == 0)
{
$styleselect = $style;
}
}
}
if (strcmp($node->name, "align") == 0)
{
$pinnerstylesid .= $node->innerstyle. ";";
}
if (strcmp($node->name, "drawing") == 0)
{
$type = $node->type;
$extent = $node->innerstyle;
$embedid = $node->value;
}
if (strcmp($node->name, "textSize") == 0)
{
$sz = $node->value;
}
if (strcmp($node->name, "textUnderline") == 0)
{
$pinnerstylesunderline = $node->innerstyle;
}
}
}
if (strcmp($type, 'text') == 0)
{
//echo "has valid para";
//echo "<br>";
if ($styleselect != null)
{
//echo "has valid style";
//echo "<br>";
if (strcmp($styleselect->color, '') != 0)
{
$pinnerstylesid .= "color:#" . $styleselect->color. ";";
}
}
if ($sz != 0)
{
$pinnerstylesid .= 'font-size:' . $sz . 'px;';
//echo "sz<br>";
}
$span = "<p style='". $pinnerstylesid . $pinnerstylesunderline ."'>";
$span .= $content;
$span .= "</p>";
//echo $span;
$html .= $span;
}
if (strcmp($type, 'graphic') == 0)
{
$imglnk = '';
foreach($this->rels as $rel)
{
if(strcmp($embedid, '') != 0 && strcmp($rel->Id, $embedid) == 0)
{
foreach($this->imglnks as $imgpathdef)
{
if (strpos($imgpathdef->extractedpath, $rel->Target) >= 0)
{
$imglnk = $imgpathdef->extractedpath;
//echo "has img link<br>";
//echo $imglnk . "<br>";
}
}
}
}
if ($styleselect != null)
{
//echo "has valid style";
//echo "<br>";
if (strcmp($styleselect->color, '') != 0)
{
$pinnerstylesid .= "color:#" . $styleselect->color. ";";
}
}
if ($sz != 0)
{
$pinnerstylesid .= 'font-size:' . $sz . 'px;';
//echo "sz<br>";
}
$span = "<p style='". $pinnerstylesid . $pinnerstylesunderline ."'>";
$span .= "<img style='". $extent ."' alt='image coming soon' src ='". $imglnk ."'/>";
$span .= "</p>";
//echo $span;
$html .= $span;
}
}
return $html;
}
public function get_errors() {
return $this->errors;
}
private function getStyles() {
}
}
function getDocX($path)
{
//echo $path;
$doc = new Docx_reader();
$doc->setFile($path);
if(!$doc->get_errors()) {
$doc->processDocument();
$html = $doc->to_html();
echo $html;
}
return "";
}
?>

How can I convert a docx document to html using php?

I want to be able to upload an MS word document and export it a page in my site.
Is there any way to accomplish this?
//FUNCTION :: read a docx file and return the string
function readDocx($filePath) {
// Create new ZIP archive
$zip = new ZipArchive;
$dataFile = 'word/document.xml';
// Open received archive file
if (true === $zip->open($filePath)) {
// If done, search for the data file in the archive
if (($index = $zip->locateName($dataFile)) !== false) {
// If found, read it to the string
$data = $zip->getFromIndex($index);
// Close archive file
$zip->close();
// Load XML from a string
// Skip errors and warnings
$xml = DOMDocument::loadXML($data, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING);
// Return data without XML formatting tags
$contents = explode('\n',strip_tags($xml->saveXML()));
$text = '';
foreach($contents as $i=>$content) {
$text .= $contents[$i];
}
return $text;
}
$zip->close();
}
// In case of failure return empty string
return "";
}
ZipArchive and DOMDocument are both inside PHP so you don't need to install/include/require additional libraries.
One may use PHPDocX.
It has support for practically all HTML CSS styles. Moreover you may use templates to add extra formatting to your HTML via the replaceTemplateVariableByHTML.
The HTML methods of PHPDocX also allow for the direct use of Word styles. You may use something like this:
$docx->embedHTML($myHTML, array('tableStyle' => 'MediumGrid3-accent5PHPDOCX'));
If you want that all your tables use the MediumGrid3-accent5 Word style. The embedHTML method as well as its version for templates (replaceTemplateVariableByHTML) preserve inheritance, meaning by that that you may use a predefined Word style and override with CSS any of its properties.
You may also extract selected parts of your HTML using 'JQuery type' selectors.
You can convert Word docx documents to html using Print2flash library. Here is an PHP excerpt from my client's site which converts a document to html:
include("const.php");
$p2fServ = new COM("Print2Flash4.Server2");
$p2fServ->DefaultProfile->DocumentType=HTML5;
$p2fServ->ConvertFile($wordfile,$htmlFile);
It converts a document which path is specified in $wordfile variable to a html page file specified by $htmlFile variable. All formatting, hyperlinks and charts are retained. You can get the required const.php file altogether with a fuller sample from Print2flash SDK.
this is a workaround based on David Lin's answer above
removing "w:" in a docx's xml tags leave behing Html like tags
function readDocx($filePath) {
// Create new ZIP archive
$zip = new ZipArchive;
$dataFile = 'word/document.xml';
// Open received archive file
if (true === $zip->open($filePath)) {
// If done, search for the data file in the archive
if (($index = $zip->locateName($dataFile)) !== false) {
// If found, read it to the string
$data = $zip->getFromIndex($index);
// Close archive file
$zip->close();
// Load XML from a string
// Skip errors and warnings
$xml = new DOMDocument("1.0", "utf-8");
$xml->loadXML($data, LIBXML_NOENT | LIBXML_XINCLUDE | LIBXML_NOERROR | LIBXML_NOWARNING|LIBXML_PARSEHUGE);
$xml->encoding = "utf-8";
// Return data without XML formatting tags
$output = $xml->saveXML();
$output = str_replace("w:","",$output);
return $output;
}
$zip->close();
}
// In case of failure return empty string
return "";
}
Ok Im in very late, but thought I'd post this to save you all some time.
This is some php code I have put together not just to read the text from docx but the images too, currently it does not support floating images / text, but what I have done so far is a massive move forwards to whats already been posted on here - note you need to update https://example.co.uk to YOUR domain name.
<?php
class Docx_ws_imglnk {
public $originalpath = '';
public $extractedpath = '';
}
class Docx_ws_rel {
public $Id = '';
public $Target = '';
}
class Docx_ws_def {
public $styleId = '';
public $type = '';
public $color = '000000';
}
class Docx_p_def {
public $data = array();
public $text = "";
}
class Docx_p_item {
public $name = "";
public $value = "";
public $innerstyle = "";
public $type = "text";
}
class Docx_reader {
private $fileData = false;
private $errors = array();
public $rels = array();
public $imglnks = array();
public $styles = array();
public $document = null;
public $paragraphs = array();
public $path = '';
private $saveimgpath = 'docimages';
public function __construct() {
}
private function load($file) {
if (file_exists($file)) {
$zip = new ZipArchive();
$openedZip = $zip->open($file);
if ($openedZip === true) {
$this->path = $file;
//read and save images
for ( $i = 0; $i < $zip->numFiles; $i ++ ) {
$zip_element = $zip->statIndex( $i );
if ( preg_match( "([^\s]+(\.(?i)(jpg|jpeg|png|gif|bmp))$)", $zip_element['name'] ) ) {
$imglnk = new Docx_ws_imglnk;
$imglnk->originalpath = $zip_element['name'];
$imagename = explode( '/', $zip_element['name'] );
$imagename = end( $imagename );
$imglnk->extractedpath = dirname( __FILE__ ) . '/' . $this->savepath . $imagename;
$putres = file_put_contents( $imglnk->extractedpath, $zip->getFromIndex( $i ));
$imglnk->extractedpath = str_replace('var/www/', 'https://example.co.uk/', $imglnk->extractedpath);
$imglnk->extractedpath = substr($imglnk->extractedpath, 1);
array_push($this->imglnks, $imglnk);
}
}
//read relationships
if (($styleIndex = $zip->locateName('word/_rels/document.xml.rels')) !== false) {
$stylesRels = $zip->getFromIndex($styleIndex);
$xml = simplexml_load_string($stylesRels);
$XMLTEXT = $xml->saveXML();
$doc = new DOMDocument();
$doc->loadXML($XMLTEXT);
foreach($doc->documentElement->childNodes as $childnode)
{
$nodename = $childnode->nodeName;
if($childnode->hasAttributes())
{
$rel = new Docx_ws_rel;
for ($a = 0; $a < $childnode->attributes->count(); $a++)
{
$attrNode = $childnode->attributes->item($a);
if (strcmp( $attrNode->nodeName, 'Id') == 0)
{
$rel->Id = $attrNode->nodeValue;
}
if (strcmp( $attrNode->nodeName, 'Target') == 0)
{
$rel->Target = $attrNode->nodeValue;
}
}
array_push($this->rels, $rel);
}
}
}
//attempt to load styles:
if (($styleIndex = $zip->locateName('word/styles.xml')) !== false) {
$stylesXml = $zip->getFromIndex($styleIndex);
$xml = simplexml_load_string($stylesXml);
$XMLTEXT = $xml->saveXML();
$doc = new DOMDocument();
$doc->loadXML($XMLTEXT);
foreach($doc->documentElement->childNodes as $childnode)
{
$nodename = $childnode->nodeName;
//get style
if (strcmp($nodename, "w:style") == 0)
{
$ws_def = new Docx_ws_def;
for ($a=0; $a < $childnode->attributes->count(); $a++ )
{
$item = $childnode->attributes->item($a);
//style id
if (strcmp($item->nodeName, "w:styleId") == 0)
{
$ws_def->styleId = $item->nodeValue;
}
//style type
if (strcmp($item->nodeName, "w:type") == 0)
{
$ws_def->type = $item->nodeValue;
}
}
}
//push style to the array of styles
if (strcmp($ws_def->styleId, "") != 0 && strcmp($ws_def->type, "") != 0)
{
array_push($this->styles, $ws_def);
}
}
}
if (($index = $zip->locateName('word/document.xml')) !== false) {
$stylesDoc = $zip->getFromIndex($index);
$xml = simplexml_load_string($stylesDoc);
$XMLTEXT = $xml->saveXML();
$this->document = new DOMDocument();
$this->document->loadXML($XMLTEXT);
}
$zip->close();
} else {
switch($openedZip) {
case ZipArchive::ER_EXISTS:
$this->errors[] = 'File exists.';
break;
case ZipArchive::ER_INCONS:
$this->errors[] = 'Inconsistent zip file.';
break;
case ZipArchive::ER_MEMORY:
$this->errors[] = 'Malloc failure.';
break;
case ZipArchive::ER_NOENT:
$this->errors[] = 'No such file.';
break;
case ZipArchive::ER_NOZIP:
$this->errors[] = 'File is not a zip archive.';
break;
case ZipArchive::ER_OPEN:
$this->errors[] = 'Could not open file.';
break;
case ZipArchive::ER_READ:
$this->errors[] = 'Read error.';
break;
case ZipArchive::ER_SEEK:
$this->errors[] = 'Seek error.';
break;
}
}
} else {
$this->errors[] = 'File does not exist.';
}
}
public function setFile($path) {
$this->fileData = $this->load($path);
}
public function to_plain_text() {
if ($this->fileData) {
return strip_tags($this->fileData);
} else {
return false;
}
}
public function processDocument() {
$html = '';
foreach($this->document->documentElement->childNodes as $childnode)
{
$nodename = $childnode->nodeName;
//get the body of the document
if (strcmp($nodename, "w:body") == 0)
{
foreach($childnode->childNodes as $subchildnode)
{
$pnodename = $subchildnode->nodeName;
//process every paragraph
if (strcmp($pnodename, "w:p") == 0)
{
$pdef = new Docx_p_def;
foreach($subchildnode->childNodes as $pchildnode)
{
//process any inner children
if (strcmp($pchildnode, "w:pPr") == 0)
{
foreach($pchildnode->childNodes as $prchildnode)
{
//process text alignment
if (strcmp($prchildnode->nodeName, "w:pStyle") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'styleId';
$pitem->value = $prchildnode->attributes->getNamedItem('val')->nodeValue;
array_push($pdef->data, $pitem);
}
//process text alignment
if (strcmp($prchildnode->nodeName, "w:jc") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'align';
$pitem->value = $prchildnode->attributes->getNamedItem('val')->nodeValue;
if (strcmp($pitem->value, "left") == 0)
{
$pitem->innerstyle .= "text-align:" . $pitem->value . ";";
}
if (strcmp($pitem->value, "center") == 0)
{
$pitem->innerstyle .= "text-align:" . $pitem->value . ";";
}
if (strcmp($pitem->value, "right") == 0)
{
$pitem->innerstyle .= "text-align:" . $pitem->value . ";";
}
if (strcmp($pitem->value, "both") == 0)
{
$pitem->innerstyle .= "word-spacing:" . 10 . "px;";
}
array_push($pdef->data, $pitem);
}
//process drawing
if (strcmp($prchildnode->nodeName, "w:drawing") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'drawing';
$pitem->value = '';
$pitem->type = 'graphic';
$extents = $prchildnode->getElementsByTagName('extent')[0];
$cx = $extents->attributes->getNamedItem('cx')->nodeValue;
$cy = $extents->attributes->getNamedItem('cy')->nodeValue;
$pcx = (int)$cx / 9525;
$pcy = (int)$cy / 9525;
$pitem->innerstyle .= "width:" . $pcx . "px;";
$pitem->innerstyle .= "height:" . $pcy . "px;";
$blip = $prchildnode->getElementsByTagName('blip')[0];
$pitem->value = $blip->attributes->getNamedItem('embed')->nodeValue;
array_push($pdef->data, $pitem);
}
//process spacing
if (strcmp($prchildnode->nodeName, "w:spacing") == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'paragraphSpacing';
$bval = $prchildnode->attributes->getNamedItem('before')->nodeValue;
if (strcmp($bval, '') == 0)
$bval = 0;
$pitem->innerstyle .= "padding-top:" . $bval . "px;";
$aval = $prchildnode->attributes->getNamedItem('after')->nodeValue;
if (strcmp($aval, '') == 0)
$aval = 0;
$pitem->innerstyle .= "padding-bottom:" . $aval . "px;";
array_push($pdef->data, $pitem);
}
}
}
if (strcmp($pchildnode, "w:r") == 0)
{
foreach($pchildnode->childNodes as $rchildnode)
{
//process text
if (strcmp($rchildnode->nodeName, "w:t") == 0)
{
$pdef->text .= $rchildnode->nodeValue;
if (count($pdef->data) == 0)
{
$pitem = new Docx_p_item;
$pitem->name = 'styleId';
$pitem->value = '';
array_push($pdef->data, $pitem);
}
}
if (strcmp($rchildnode->nodeName, "w:rPr") == 0)
{
foreach($rchildnode->childNodes as $rPrchildnode)
{
if (strcmp($rPrchildnode->nodeName, "w:b") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textBold';
$pitem->value = '';
$pitem->innerstyle .= "text-weight: 500;";
array_push($pdef->data, $pitem);
}
if (strcmp($rPrchildnode->nodeName, "w:i") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textItalic';
$pitem->value = '';
$pitem->innerstyle .= "text-style: italic;";
array_push($pdef->data, $pitem);
}
if (strcmp($rPrchildnode->nodeName, "w:u") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textUnderline';
$pitem->value = '';
$pitem->innerstyle .= "text-decoration: underline;";
array_push($pdef->data, $pitem);
}
if (strcmp($rPrchildnode->nodeName, "w:sz") == 0 )
{
$pitem = new Docx_p_item;
$pitem->name = 'textSize';
$sz = $rPrchildnode->attributes->getNamedItem('val')->nodeValue;
if ($sz == '')
{
$sz=0;
}
$pitem->value = $sz;
array_push($pdef->data, $pitem);
}
}
}
}
}
}
array_push($this->paragraphs, $pdef);
}
}
}
}
}
public function to_html()
{
$html = '';
foreach($this->paragraphs as $para)
{
$styleselect = null;
$type = 'text';
$content = $para->text;
$sz = 0;
$extent = '';
$embedid = '';
$pinnerstylesid = '';
$pinnerstylesunderline = '';
$pinnerstylessz = '';
if (count($para->data) > 0)
{
foreach($para->data as $node)
{
if (strcmp($node->name, "styleId") == 0)
{
$type = $node->type;
$pinnerstylesid = $node->innerstyle;
foreach($this->styles as $style)
{
if (strcmp ($node->value, $style->styleId) == 0)
{
$styleselect = $style;
}
}
}
if (strcmp($node->name, "align") == 0)
{
$pinnerstylesid .= $node->innerstyle. ";";
}
if (strcmp($node->name, "drawing") == 0)
{
$type = $node->type;
$extent = $node->innerstyle;
$embedid = $node->value;
}
if (strcmp($node->name, "textSize") == 0)
{
$sz = $node->value;
}
if (strcmp($node->name, "textUnderline") == 0)
{
$pinnerstylesunderline = $node->innerstyle;
}
}
}
if (strcmp($type, 'text') == 0)
{
//echo "has valid para";
//echo "<br>";
if ($styleselect != null)
{
//echo "has valid style";
//echo "<br>";
if (strcmp($styleselect->color, '') != 0)
{
$pinnerstylesid .= "color:#" . $styleselect->color. ";";
}
}
if ($sz != 0)
{
$pinnerstylesid .= 'font-size:' . $sz . 'px;';
//echo "sz<br>";
}
$span = "<p style='". $pinnerstylesid . $pinnerstylesunderline ."'>";
$span .= $content;
$span .= "</p>";
//echo $span;
$html .= $span;
}
if (strcmp($type, 'graphic') == 0)
{
$imglnk = '';
foreach($this->rels as $rel)
{
if(strcmp($embedid, '') != 0 && strcmp($rel->Id, $embedid) == 0)
{
foreach($this->imglnks as $imgpathdef)
{
if (strpos($imgpathdef->extractedpath, $rel->Target) >= 0)
{
$imglnk = $imgpathdef->extractedpath;
//echo "has img link<br>";
//echo $imglnk . "<br>";
}
}
}
}
if ($styleselect != null)
{
//echo "has valid style";
//echo "<br>";
if (strcmp($styleselect->color, '') != 0)
{
$pinnerstylesid .= "color:#" . $styleselect->color. ";";
}
}
if ($sz != 0)
{
$pinnerstylesid .= 'font-size:' . $sz . 'px;';
//echo "sz<br>";
}
$span = "<p style='". $pinnerstylesid . $pinnerstylesunderline ."'>";
$span .= "<img style='". $extent ."' alt='image coming soon' src ='". $imglnk ."'/>";
$span .= "</p>";
//echo $span;
$html .= $span;
}
}
return $html;
}
public function get_errors() {
return $this->errors;
}
private function getStyles() {
}
}
function getDocX($path)
{
//echo $path;
$doc = new Docx_reader();
$doc->setFile($path);
if(!$doc->get_errors()) {
$doc->processDocument();
$html = $doc->to_html();
echo $html;
}
return "";
}
?>

Categories