DomDocument class unable access domnode

Question

I dont parse this url: http://foldmunka.net

$ch = curl_init(\"http://foldmunka.net\");

//curl_setopt($ch, CURLOPT_NOBODY, true);
curl_setopt($ch, CURLOPT_RE         


        

Answer 1

Here is a Simple Html DOM Parser solution just for comparison. It's output is similar for the DomDocument solution's, but this one is more complicated and runs much slower (~2300ms against DomDocument's ~100ms), so I don't recommend to use it:

Updated to work with elements inside elements.

tag == 'a')
        $element->innertext = makePlainText($element->innertext, LOAD_FROM_STRING);
}

function callback_buildPlainText($element)
{
    global $processed_plain_text;

    $excluded_tags = array('script', 'style');

    switch ($element->tag)
    {
        case 'text':
            // filter when 'text' is descendant of 'a', because we are
            // processing the anchor tags with the required attributes
            // separately at the 'a' tag,
            // and also filter out other unneccessary tags
            if (($element->parent->tag != 'a') && !in_array($element->parent->tag, $excluded_tags))
                $processed_plain_text .= $element->innertext . ' ';
            break;
        case 'img':
            $processed_plain_text .= $element->alt . ' ';
            $processed_plain_text .= $element->title . ' ';
            break;
        case 'a':
            $processed_plain_text .= $element->alt . ' ';
            $processed_plain_text .= $element->title . ' ';
            $processed_plain_text .= $element->innertext . ' ';
            break;
    }
}

function makePlainText($source, $mode = LOAD_FROM_URL)
{
    global $processed_plain_text;

    if ($mode == LOAD_FROM_URL)
        $html = file_get_html($source);
    elseif ($mode == LOAD_FROM_STRING)
        $html = str_get_dom ($source);
    else
        return 'Wrong mode defined in makePlainText: ' . $mode;

    $html->set_callback('callback_cleanNestedAnchorContent');

    // processing with the first callback to clean up the anchor tags
    $html = str_get_html($html->save());
    $html->set_callback('callback_buildPlainText');

    // processing with the second callback to build the full plain text with
    // the required attributes of the 'img' and 'a' tags, and excluding the
    // unneccessary ones like script and style tags
    $html->save();

    $return = $processed_plain_text;

    // cleaning the global variable
    $processed_plain_text = '';

    return $return;
}

//$html = 'Hello this siteclick HERE Some text.';

echo makePlainText('http://foldmunka.net');
//echo makePlainText($html, LOAD_FROM_STRING);