2 sort of silly, yet useful PHP functions to get some basic info about a webpage:
<?php
// Used to get a target URL's title
function get_target_title($target_url) {
if (!function_exists('curl_init')) {
die('CURL is not installed!');
}
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $target_url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.94 Safari/537.36');
$html = curl_exec($ch);
curl_close($ch);
$dom = new DOMDocument;
@$dom->loadHTML($html);
$title = $dom->getElementsByTagName('title')->item('0')->nodeValue;
return $title;
}
?>Similar, but slightly different…
<?php
// Used to get a target URL's metadata, open graph, twitter, etc.
function get_target_metadata($target_url) {
$url = $target_url;
$tags = array();
$tags['url'] = $url;
$meta_tags = get_meta_tags($url);
$tags['meta'] = $meta_tags;
$site_html= file_get_contents($url);
$og_matches=null;
preg_match_all('~<\s*meta\s+property="(og:[^"]+)"\s+content="([^"]*)~i', $site_html,$og_matches);
$og_tags=array();
for($i=0;$i<count($og_matches[1]);$i++) {
$og_tags[$og_matches[1][$i]]=$og_matches[2][$i];
}
$tags['open graph'] = $og_tags;
return $tags;
}
?>Published