I found it after googling for a day, finally a function that reads the .docx file and return you a string. Hats off to the original author of this function.
function readDocx($file_name){
$striped_content = '';
$content = '';
if(!$file_name || !file_exists($file_name))
return false;
$zip = zip_open($file_name);
if (!$zip || is_numeric($zip))
return false;
while ($zip_entry = zip_read($zip)) {
if (zip_entry_open($zip, $zip_entry) == FALSE)
continue;
if (zip_entry_name($zip_entry) != "word/document.xml")
continue;
$content .= zip_entry_read($zip_entry, zip_entry_filesize($zip_entry));
zip_entry_close($zip_entry);
}// end while
zip_close($zip);
$content = str_replace('</w:r></w:p></w:tc><w:tc>', " ", $content);
$content = str_replace('</w:r></w:p>', "\r\n", $content);
$striped_content = strip_tags($content);
return $striped_content;
}
function readDocx($file_name){
$striped_content = '';
$content = '';
if(!$file_name || !file_exists($file_name))
return false;
$zip = zip_open($file_name);
if (!$zip || is_numeric($zip))
return false;
while ($zip_entry = zip_read($zip)) {
if (zip_entry_open($zip, $zip_entry) == FALSE)
continue;
if (zip_entry_name($zip_entry) != "word/document.xml")
continue;
$content .= zip_entry_read($zip_entry, zip_entry_filesize($zip_entry));
zip_entry_close($zip_entry);
}// end while
zip_close($zip);
$content = str_replace('</w:r></w:p></w:tc><w:tc>', " ", $content);
$content = str_replace('</w:r></w:p>', "\r\n", $content);
$striped_content = strip_tags($content);
return $striped_content;
}
Comments
Post a Comment
Want to tell something about this post. Please feel free to write...