php判断来访者是否是搜索引擎的蜘蛛

我们可以通过HTTP_USER_AGENT来判断是否是蜘蛛，搜索引擎的蜘蛛都有自己的独特标志，下面列取了一部分。

function is_crawler() {

$userAgent = strtolower($_SERVER['HTTP_USER_AGENT']);

$spiders = array(

'Googlebot', // Google 爬虫

'Baiduspider', // 百度爬虫

'Yahoo! Slurp', // 雅虎爬虫

'YodaoBot', // 有道爬虫

'msnbot' // Bing爬虫

// 更多爬虫关键字

);

foreach ($spiders as $spider) {

$spider = strtolower($spider);

if (strpos($userAgent, $spider) !== false) {

return true;

}

}

return false;

}

下面的php代码附带了更多的蜘蛛标识

function isCrawler() {

echo $agent= strtolower($_SERVER['HTTP_USER_AGENT']);

if (!empty($agent)) {

$spiderSite= array(

"TencentTraveler",

"Baiduspider+",

"BaiduGame",

"Googlebot",

"msnbot",

"Sosospider+",

"Sogou web spider",

"ia_archiver",

"Yahoo! Slurp",

"YoudaoBot",

"Yahoo Slurp",

"MSNBot",

"Java (Often spam bot)",

"BaiDuSpider",

"Voila",

"Yandex bot",

"BSpider",

"twiceler",

"Sogou Spider",

"Speedy Spider",

"Google AdSense",

"Heritrix",

"Python-urllib",

"Alexa (IA Archiver)",

"Ask",

"Exabot",

"Custo",

"OutfoxBot/YodaoBot",

"yacy",

"SurveyBot",

"legs",

"lwp-trivial",

"Nutch",

"StackRambler",

"The web archive (IA Archiver)",

"Perl tool",

"MJ12bot",

"Netcraft",

"MSIECrawler",

"WGet tools",

"larbin",

"Fish search",

);

foreach($spiderSite as $val) {

$str = strtolower($val);

if (strpos($agent, $str) !== false) {

return true;

}

}

} else {

return false;

}

}

if (isCrawler()){

echo "你好蜘蛛精！";

}

else{

echo "你不是蜘蛛精啊！";

}