Read doc/docx content in javascript

Asked

Viewed 347 times

0

You can send a doc/docx through a form and read its contents in javascript?

I only care about the text that is written inside it, without images, formulas, etc.

javascript jquery

  • https://stackoverflow.com/a/27958186/4312593

  • This solution is not yet ideal. I will need to deal with this Word text later.

  • https://docxtemplater.com/

  • docxtemplater works with DOC as well or only DOCX?

1 answer

-1

There is a class in PHP calling for doc2txt.
Just give Ctrl c + Ctrl v, follow the credits in the code.
When I searched in Javascript I found for . docx or . doc separate.

example.php

<?php
/* 
this example is used to convert any doc format to text
author: Gourav Mehta
author's email: [email protected]
author's phone: +91-9888316141
*/ 
require("doc2txt.class.php");

$docObj = new Doc2Txt("test.docx");
//ou
//$docObj = new Doc2Txt("test.doc");

$txt = $docObj->convertToText();
echo $txt;
?>

doc2txt.class.php

<?php
class Doc2Txt {
private $filename;

public function __construct($filePath) {
    $this->filename = $filePath;
}

private function read_doc() {
    $fileHandle = fopen($this->filename, "r");
    $line = @fread($fileHandle, filesize($this->filename));   
    $lines = explode(chr(0x0D),$line);
    $outtext = "";
    foreach($lines as $thisline)
      {
        $pos = strpos($thisline, chr(0x00));
        if (($pos !== FALSE)||(strlen($thisline)==0))
          {
          } else {
            $outtext .= $thisline." ";
          }
      }
     $outtext = preg_replace("/[^a-zA-Z0-9\s\,\.\-\n\r\t@\/\_\(\)]/","",$outtext);
    return $outtext;
}

private function read_docx(){

    $striped_content = '';
    $content = '';

    $zip = zip_open($this->filename);

    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;
}

public function convertToText() {

    if(isset($this->filename) && !file_exists($this->filename)) {
        return "File Not exists";
    }

    $fileArray = pathinfo($this->filename);
    $file_ext  = $fileArray['extension'];
    if($file_ext == "doc" || $file_ext == "docx")
    {
        if($file_ext == "doc") {
            return $this->read_doc();
        } else {
            return $this->read_docx();
        }
    } else {
        return "Invalid File Type";
    }
 }
}
?>

  • There is a javascript solution?

Browser other questions tagged javascript jquery

You are not signed in. Login or sign up in order to post.