| Server IP : 172.67.201.108 / Your IP : 216.73.216.101 Web Server : Apache/2.4.68 (Amazon Linux) OpenSSL/3.5.5 System : Linux ip-172-31-69-123.ec2.internal 6.1.176-223.369.amzn2023.x86_64 #1 SMP PREEMPT_DYNAMIC Fri Jul 24 13:34:27 UTC 2026 x86_64 User : ec2-user ( 1000) PHP Version : 8.4.23 Disable Function : NONE MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : OFF | Sudo : ON | Pkexec : ON Directory : /home/mitzvahm/public_html/_scripts/html_parser/example/scraping/ |
Upload File : |
<?php
include_once('../../simple_html_dom.php');
function scraping_digg() {
// create HTML DOM
$html = file_get_html('http://digg.com/');
// get news block
foreach($html->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 $v['title'].'<br>';
echo '<ul>';
echo '<li>'.$v['details'].'</li>';
echo '<li>Diggs: '.$v['diggs'].'</li>';
echo '</ul>';
}
?>