I dont parse this url: http://foldmunka.net
$ch = curl_init("http://foldmunka.net");
//curl_setopt($ch, CURLOPT_NOBODY, true);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
//curl_setopt($ch, CURLOPT_HEADER, true);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); //not necessary unless the file redirects (like the PHP example we're using here)
$data = curl_exec($ch);
$info = curl_getinfo($ch);
curl_close($ch);
clearstatcache();
if ($data === false) {
echo 'cURL failed';
exit;
}
$dom = new DOMDocument();
$data = mb_convert_encoding($data, 'HTML-ENTITIES', "utf-8");
$data = preg_replace('/<!--[if(.*)]>/', '', $data);
$data = str_replace('<![endif]-->', '', $data);
$data = str_replace('<!--', '', $data);
$data = str_replace('-->', '', $data);
$data = preg_replace('@<script[^>]*?>.*?</script>@si', '', $data);
$data = preg_replace('@<style[^>]*?>.*?</style>@si', '', $data);
$data = mb_convert_encoding($data, 'HTML-ENTITIES', "utf-8");
@$dom->loadHTML($data);
$els = $dom->getElementsByTagName('*');
foreach($els as $el){
print $el->nodeName." | ".$el->getAttribute('content')."<hr />";
if($el->getAttribute('title'))$el->nodeValue = $el->getAttribute('title')." ".$el->nodeValue;
if($el->getAttribute('alt'))$el->nodeValue = $el->getAttribute('alt')." ".$el->nodeValue;
print $el->nodeName." | ".$el->nodeValue."<hr />";
}
I need sequentially the alt, title attributes and the simple text, but this page i cannot access the nodes within the body tag.
See Question&Answers more detail:
os 与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…