| Server IP : 172.67.201.108 / Your IP : 216.73.216.55 Web Server : Apache/2.4.68 (Amazon Linux) OpenSSL/3.5.7 System : Linux ip-172-31-69-123.ec2.internal 6.1.177-224.371.amzn2023.x86_64 #1 SMP PREEMPT_DYNAMIC Mon Jul 27 20:28:29 UTC 2026 x86_64 User : ec2-user ( 1000) PHP Version : 8.4.24 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_IMDB($url) {
// create HTML DOM
$html = file_get_html($url);
// get title
$ret['Title'] = $html->find('title', 0)->innertext;
// get rating
$ret['Rating'] = $html->find('div[class="general rating"] b', 0)->innertext;
// get overview
foreach($html->find('div[class="info"]') as $div) {
// skip user comments
if($div->find('h5', 0)->innertext=='User Comments:')
return $ret;
$key = '';
$val = '';
foreach($div->find('*') as $node) {
if ($node->tag=='h5')
$key = $node->plaintext;
if ($node->tag=='a' && $node->plaintext!='more')
$val .= trim(str_replace("\n", '', $node->plaintext));
if ($node->tag=='text')
$val .= trim(str_replace("\n", '', $node->plaintext));
}
$ret[$key] = $val;
}
// clean up memory
$html->clear();
unset($html);
return $ret;
}
// -----------------------------------------------------------------------------
// test it!
$ret = scraping_IMDB('http://imdb.com/title/tt0335266/');
foreach($ret as $k=>$v)
echo '<strong>'.$k.' </strong>'.$v.'<br>';
?>