getting webpage contents using curl_init not working for some links
Posted
by
Manish
on Stack Overflow
See other posts from Stack Overflow
or by Manish
Published on 2012-09-26T05:22:53Z
Indexed on
2012/10/25
5:02 UTC
Read the original article
Hit count: 160
I am using this code to get contents of a url entered:-
class MetaTagParser
{
public $metadata;
private $html;
private $url;
public function __construct($url)
{
$this->url=$url;
$this->html= $this->file_get_contents_curl();
$this->set_title();
$this->set_meta_properties();
}
public function file_get_contents_curl()
{
$ch = curl_init();
curl_setopt($ch, CURLOPT_HEADER, 0);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_URL, $this->url);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
$data = curl_exec($ch);
curl_close($ch);
return $data;
}
public function set_title()
{
$doc = new DOMDocument();
@$doc->loadHTML($this->html);
$nodes = $doc->getElementsByTagName('title');
$this->metadata['title'] = $nodes->item(0)->nodeValue;
}
this class works for some pages but for some url like this one - http://www.dnaindia.com/india/report_in-a-first-upa-govt-tweets-the-press_1745346 when I try to fetch data I get this error:-"Warning: get_meta_tags(http://www.dnaindia.com/india/report_in-a-first-upa-govt-tweets-the-press_1745346): failed to open stream: HTTP request failed! HTTP/1.1 403 Forbidden in C:\xampp\htdocs\prac\index.php on line 52"
it is not working, any ideas why this is happening??
© Stack Overflow or respective owner