Это сделает это (или поможет хотя бы):
$pageRaw = fread_url('www.example.com');
//link extraction regex
preg_match_all ("/a[\s]+[^>]*?href[\s]?=[\s\"\']+".
"(.*?)[\"\']+.*?>"."([^<]+|.*?)?<\/a>/",
$pageRaw, &$matches);
$matches = $matches[1];
foreach($matches as $link)
{
echo $link. '<br />';
}
//falls back to fopen if curl is not there
function fread_url($url,$ref="")
{
if(function_exists("curl_init")){
$ch = curl_init();
$user_agent = "Mozilla/4.0 (compatible; MSIE 5.01; ".
"Windows NT 5.0)";
$ch = curl_init();
curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
curl_setopt( $ch, CURLOPT_HTTPGET, 1 );
curl_setopt( $ch, CURLOPT_RETURNTRANSFER, 1 );
curl_setopt( $ch, CURLOPT_FOLLOWLOCATION , 1 );
curl_setopt( $ch, CURLOPT_FOLLOWLOCATION , 1 );
curl_setopt( $ch, CURLOPT_URL, $url );
curl_setopt( $ch, CURLOPT_REFERER, $ref );
curl_setopt ($ch, CURLOPT_COOKIEJAR, 'cookie.txt');
$html = curl_exec($ch);
curl_close($ch);
}
else{
$hfile = fopen($url,"r");
if($hfile){
while(!feof($hfile)){
$html.=fgets($hfile,1024);
}
}
}
return $html;
}