Count number of words from (doc txt docx ) files

Question

I\'m trying to count number of words in file. The following code is working fine with .txt file. But When I try to read .doc docx .xls files. Its give

Answer 1

I am working in the same issues with you. All you need to do is parse the .doc docx .xls file in the right way. Then use the count_words

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;
}

Answer 2

if you run on linux try this :

system("wc -w " . $filename);