find('div.news-summary') as $article) {
// get title
$item['title'] = trim($article->find('h3', 0)->plaintext);
// get details
$item['details'] = trim($article->find('p', 0)->plaintext);
// get intro
$item['diggs'] = trim($article->find('li a strong', 0)->plaintext);
$ret[] = $item;
}
// clean up memory
$html->clear();
unset($html);
return $ret;
}
// -----------------------------------------------------------------------------
// test it!
// "http://digg.com" will check user_agent header...
ini_set('user_agent', 'My-Application/2.5');
$ret = scraping_digg();
foreach($ret as $v) {
echo $v['title'].'
';
echo '';
echo '- '.$v['details'].'
';
echo '- Diggs: '.$v['diggs'].'
';
echo '
';
}
?>