php屏蔽蜘蛛访问代码代码:
常用搜索引擎名与 http_user_agent对应值
百度baiduspider
谷歌googlebot
搜狗sogou
腾讯sosososospider
雅虎slurp
有道youdaobot
bingbingbot
msnmsnbot
alexais_archiver
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!";
}
使用php实现蜘蛛访问日志统计
$useragent = addslashes(strtolower($_server['http_user_agent']));
if (strpos($useragent, 'googlebot')!== false){$bot = 'google';}
elseif (strpos($useragent,'mediapartners-google') !== false){$bot = 'google adsense';}
elseif (strpos($useragent,'baiduspider') !== false){$bot = 'baidu';}
elseif (strpos($useragent,'sogou spider') !== false){$bot = 'sogou';}
elseif (strpos($useragent,'sogou web') !== false){$bot = 'sogou web';}
elseif (strpos($useragent,'sosospider') !== false){$bot = 'soso';}
elseif (strpos($useragent,'360spider') !== false){$bot = '360spider';}
elseif (strpos($useragent,'yahoo') !== false){$bot = 'yahoo';}
elseif (strpos($useragent,'msn') !== false){$bot = 'msn';}
elseif (strpos($useragent,'msnbot') !== false){$bot = 'msnbot';}
elseif (strpos($useragent,'sohu') !== false){$bot = 'sohu';}
elseif (strpos($useragent,'yodaobot') !== false){$bot = 'yodao';}
elseif (strpos($useragent,'twiceler') !== false){$bot = 'twiceler';}
elseif (strpos($useragent,'ia_archiver') !== false){$bot = 'alexa_';}
elseif (strpos($useragent,'iaarchiver') !== false){$bot = 'alexa';}
elseif (strpos($useragent,'slurp') !== false){$bot = '雅虎';}
elseif (strpos($useragent,'bot') !== false){$bot = '其它蜘蛛';}
if(isset($bot)){
$fp = @fopen('bot.txt','a');
fwrite($fp,date('y-m-d h:i:s')."t".$_server["remote_addr"]."t".$bot."t".'http://'.$_server['server_name'].$_server["request_uri"]."rn");
fclose($fp);
}
【说明】:本文章由站长整理发布,文章内容不代表本站观点,如文中有侵权行为,请与本站客服联系(QQ:)!