php 模仿蜘蛛抓取内容并分析

header(“Content-Type:text/html;charset=gbk”);
$message=$_POST[‘message’];
$contents = @file_get_contents(“$message”);
if($contents==”Forbidden”){
$ch = curl_init();
$timeout = 5;
curl_setopt ($ch, CURLOPT_URL, “$message”);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_USERAGENT, “Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1)”);
curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
$contents = curl_exec($ch);
curl_close($ch);
}
preg_match_all(“/<title(.*?)</title>/is”,$contents,$title);
preg_match_all(“/<meta(.*?)>/is”,$contents,$meta);
preg_match_all(“/<body(.*?)body>/is”,$contents,$body);
echo ‘title:’.strip_tags($title[0][0]).'<br><br>’;
for($i=0;$i<count($meta[0]);$i++){
if(preg_match(“/keywords/i”,$meta[0][$i])){
preg_match_all(“/content=”(.*?)”/is”,$meta[0][$i],$keywords);

}
if(preg_match(“/description/i”,$meta[0][$i])){
preg_match_all(“/content=”(.*?)”/is”,$meta[0][$i],$description);

}
}
echo ‘keywords:’.strip_tags($keywords[1][0]).'<br><br>’;
echo ‘description:’.strip_tags($description[1][0]).'<br><br>’;
echo ‘body:’.strip_tags($body[0][0]);
?>

发表评论