PHP获取搜索引擎关键字来源的函数(支持百度和谷歌等搜索引擎)_PHP

php中文网

发布时间：2016-06-01 12:08:52

1175人浏览过

来源于php中文网

原创

最近遇到一个项目，客户需要一个功能，一个商品销售下单需要知道用户下单是从哪个途径来的，认为客服软件（53客服）和站长统计只能满足工作时间，及晚上下班和周六日休息，客服不在线，用户下单会不知道该订单的具体来源，所以嘛，又只能通过网站功能来增加一字段，获取来源关键字，如何获取来源关键字，代码发在下面，里面包含（百度、谷歌、雅虎、搜狗、搜搜、必应、有道）几大搜索引擎的获取方法，代码中均注明，希望对你有帮助，分享一下

代码如下：
复制代码代码如下:
//获取来自搜索引擎入站时的关键词
function get_keyword($url,$kw_start)
{
$start=stripos($url,$kw_start);
$url=substr($url,$start+strlen($kw_start));
$start=stripos($url,'&');
if ($start>0)
{
$start=stripos($url,'&');
$s_s_keyword=substr($url,0,$start);
}
else
{
$s_s_keyword=substr($url,0);
}
return $s_s_keyword;
}

$url=isset($_SERVER['HTTP_REFERER'])?$_SERVER['HTTP_REFERER']:'';//获取入站url。
$search_1="google.com"; //q= utf8
$search_2="baidu.com"; //wd= gbk
$search_3="yahoo.cn"; //q= utf8
$search_4="sogou.com"; //query= gbk
$search_5="soso.com"; //w= gbk
$search_6="bing.com"; //q= utf8
$search_7="youdao.com"; //q= utf8

$google=preg_match("/\b{$search_1}\b/",$url);//记录匹配情况，用于入站判断。
$baidu=preg_match("/\b{$search_2}\b/",$url);
$yahoo=preg_match("/\b{$search_3}\b/",$url);
$sogou=preg_match("/\b{$search_4}\b/",$url);
$soso=preg_match("/\b{$search_5}\b/",$url);
$bing=preg_match("/\b{$search_6}\b/",$url);
$youdao=preg_match("/\b{$search_7}\b/",$url);
$s_s_keyword="";
$bul=$_SERVER['HTTP_REFERER'];
//获取没参数域名
preg_match('@^(?:http://)?([^/]+)@i',$bul,$matches);
$burl=$matches[1];
//匹配域名设置
$curl="www.netxu.com";
if($burl!=$curl){
if ($google)
{//来自google
$s_s_keyword=get_keyword($url,'q=');//关键词前的字符为"q="。
$s_s_keyword=urldecode($s_s_keyword);
$urlname="谷歌：";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
//$s_s_keyword=iconv("GBK","UTF-8",$s_s_keyword);//引擎为gbk
}
else if($baidu)
{//来自百度
$s_s_keyword=get_keyword($url,'wd=');//关键词前的字符为"wd="。
$s_s_keyword=urldecode($s_s_keyword);
$s_s_keyword=iconv("GBK","UTF-8",$s_s_keyword);//引擎为gbk
$urlname="百度：";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
}
else if($yahoo)
{//来自雅虎
$s_s_keyword=get_keyword($url,'q=');//关键词前的字符为"q="。
$s_s_keyword=urldecode($s_s_keyword);
//$s_s_keyword=iconv("GBK","UTF-8",$s_s_keyword);//引擎为gbk
$urlname="雅虎：";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
}
else if($sogou)
{//来自搜狗
$s_s_keyword=get_keyword($url,'query=');//关键词前的字符为"query="。
$s_s_keyword=urldecode($s_s_keyword);
$s_s_keyword=iconv("GBK","UTF-8",$s_s_keyword);//引擎为gbk
$urlname="搜狗：";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
}
else if($soso)
{//来自搜搜
$s_s_keyword=get_keyword($url,'w=');//关键词前的字符为"w="。
$s_s_keyword=urldecode($s_s_keyword);
$s_s_keyword=iconv("GBK","UTF-8",$s_s_keyword);//引擎为gbk
$urlname="搜搜：";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
}
else if($bing)
{//来自必应
$s_s_keyword=get_keyword($url,'q=');//关键词前的字符为"q="。
$s_s_keyword=urldecode($s_s_keyword);
//$s_s_keyword=iconv("GBK","UTF-8",$s_s_keyword);//引擎为gbk
$urlname="必应：";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
}
else if($youdao)
{//来自有道
$s_s_keyword=get_keyword($url,'q=');//关键词前的字符为"q="。
$s_s_keyword=urldecode($s_s_keyword);
//$s_s_keyword=iconv("GBK","UTF-8",$s_s_keyword);//引擎为gbk
$urlname="有道：";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
}
else{
$urlname=$burl;
$s_s_keyword="";
$_SESSION["urlname"]=$urlname;
$_SESSION["s_s_keyword"]=$s_s_keyword;
}
$s_urlname=$urlname;
$s_urlkey=$s_s_keyword;
}
else{
$s_urlname=$_SESSION["urlname"];
$s_urlkey=$_SESSION["s_s_keyword"];
}
?>

有一点要记住，由于各搜索引擎的页面编码不一样，有的是GBK,有的是UTF8,所以在获取时会有不同对字符编码的转换
转载请注明：http://www.netxu.com/program/12.html

下面是另外一个函数，也可以参考下
复制代码代码如下:
$_SERVER['HTTP_REFERER']='http://www.baidu.com/s?wd=http://www.bitsCN.com';
echo save_www_iiwnet_com_keyword('http://www.baidu.com/s?wd=http://www.bitsCN.com','http://www.baidu.com/s?wd=http://www.bitsCN.com');
function save_www_iiwnet_com_keyword($domain,$path){
if(strpos($domain, 'google.com.tw')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'GOOGLE TAIWAN';
$keywords = urldecode($regs[1]); // google taiwan
}
if(strpos($domain,'google.cn')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'GOOGLE CHINA';
$keywords = urldecode($regs[1]); // google china
}
if(strpos($domain,'google.com')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'GOOGLE';
$keywords = urldecode($regs[1]); // google
}elseif(strpos($domain,'baidu.')!==false && preg_match('/wd=([^&]*)/i',$path,$regs)){
$searchengine = 'BAIDU';
$keywords = urldecode($regs[1]); // baidu
}elseif(strpos($domain,'baidu.')!==false && preg_match('/word=([^&]*)/i',$path,$regs)){
$searchengine = 'BAIDU';
$keywords = urldecode($regs[1]); // baidu
}elseif(strpos($domain,'114.vnet.cn')!== false && preg_match('/kw=([^&]*)/i',$path,$regs)){
$searchengine = 'CT114';
$keywords = urldecode($regs[1]); // ct114
}elseif(strpos($domain,'iask.com')!==false && preg_match('/k=([^&]*)/i',$path,$regs)){
$searchengine = 'IASK';
$keywords = urldecode($regs[1]); // iask
}elseif(strpos($domain,'soso.com')!==false && preg_match('/w=([^&]*)/i',$path,$regs)){
$searchengine = 'SOSO';
$keywords = urldecode($regs[1]); // soso
}elseif(strpos($domain, 'sogou.com')!==false && preg_match('/query=([^&]*)/i',$path,$regs)){
$searchengine = 'SOGOU';
$keywords = urldecode($regs[1]); // sogou
}elseif(strpos($domain,'so.163.com')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'NETEASE';
$keywords = urldecode($regs[1]); // netease
}elseif(strpos($domain,'yodao.com')!== false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'YODAO';
$keywords = urldecode($regs[1]); // yodao
}elseif(strpos($domain,'zhongsou.com')!==false && preg_match('/word=([^&]*)/i',$path,$regs)){
$searchengine = 'ZHONGSOU';
$keywords = urldecode($regs[1]); // zhongsou
}elseif(strpos($domain,'search.tom.com')!==false && preg_match('/w=([^&]*)/i',$path,$regs)){
$searchengine = 'TOM';
$keywords = urldecode($regs[1]); // tom
}elseif(strpos($domain,'live.com')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'MSLIVE';
$keywords = urldecode($regs[1]); // MSLIVE
}elseif(strpos($domain, 'tw.search.yahoo.com')!==false && preg_match('/p=([^&]*)/i',$path,$regs)){
$searchengine = 'YAHOO TAIWAN';
$keywords = urldecode($regs[1]); // yahoo taiwan
}elseif(strpos($domain,'cn.yahoo.')!==false && preg_match('/p=([^&]*)/i',$path,$regs)){
$searchengine = 'YAHOO CHINA';
$keywords = urldecode($regs[1]); // yahoo china
}elseif(strpos($domain,'yahoo.')!==false && preg_match('/p=([^&]*)/i',$path,$regs)){
$searchengine = 'YAHOO';
$keywords = urldecode($regs[1]); // yahoo
}elseif(strpos($domain,'msn.com.tw')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'MSN TAIWAN';
$keywords = urldecode($regs[1]); // msn taiwan
}elseif(strpos($domain,'msn.com.cn')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'MSN CHINA';
$keywords = urldecode($regs[1]); // msn china
}elseif(strpos($domain,'msn.com')!==false && preg_match('/q=([^&]*)/i',$path,$regs)){
$searchengine = 'MSN';
$keywords = urldecode($regs[1]); // msn
}
return $keywords;
}