I am getting the content of some websites in HTML source. About titles and description. works on: example.com/nice-photos/ doesn't work if HTML source only /nice-photos/ or /21321314/
my codes here:
<?php
if($_GET['link'])
{
$dt = fopen("content.txt","aw+");
$link = $_GET['link'];
$page = $_GET['page'];
$total_page = $_GET["total_page"];
if($page=="")
{
$page = 1;
}
else
{
$link = str_replace("1",$page,$link);
}
$source = urlCek($link);
preg_match_all('@<a href="(.*?)">@si', $source, $links); // HTML range of links in category
foreach ($links[1] as $value) { // $link[] Write the number between the parentheses and the number according to the actual link in the link range.
$kn = urlCek($value);
preg_match_all('@<meta property="og:title" content="(.*?)" />@si', $kn, $title); // HTML range specified for the title
preg_match_all('@<meta property="og:description" content="(.*?)" />@si', $kn, $content); // HTML range specified for description
$description = $content[1][0];
if(strstr($description,'ALL RIGHTS RESERVED'))
{
$description = '';
}
fwrite($dt,$title[1][0]."\n".$description."\n{}\n");
}
$next = $page+1;
if($next>$total_page)
{
echo 'done!!!';
}
else
{
echo 'It saved. Going to the next page <meta http-equiv="refresh" content="0;URL=index.php?page='.$next.'&link='.$_GET["link"].'&total_page='.$_GET["total_page"].'">';
}
}
?>