实用的免费中文分词服务
中文分词对于大型网站的搜索及SEO优化都是一个难点,同时也是一个重点。很多人会使用Lucene中文分词，但是想维护如此大的一个词库不是一件容易的事情，可行性值得考证。
在这种情况下为什么不使用他人提供的服务呢？
优点：
1、稳定、速度快、分词准确
2、不用维护
缺点：
1、他人的免费服务始终不放心，万一停了怎么办？
以下是百度热门相关关键字和discuz标签功能提供的免费ROA服务(php版函数)
//根据标题获得百度热门相关关键字，返回字符串
function baiduKeyword($title,$num=5,$charset="UTF-8"){
$title=iconv($charset, "GB2312", $title);
$w=file_get_contents('http://d.baidu.com/rs.php?q='.urlencode($title).'&tn=baidu');
//die($w);
//获得列表部分
preg_match_all("|<div id=con>(.*)</div>|isU",$w,$con);
$list=$con[1][0];
//获得具体内容
preg_match_all("|<ul><li class=ls>(.*)</li><li class=kwc><a target=_blank href=(.*)>(.*)</a></li><li class=bar><img src=http://img.baidu.com/img/bar_1.gif height=6 width=(\d*) align=absmiddle vspace=5></li></ul>|isU",$list,$content);
//合并成数组，被搜索次数做为键值
$c=array_combine($content[4],$content[3]);
//排序
krsort($c);
//取前N条
$r=array_slice($c, 0, $num);
//转换成字符串
$result=implode(",", $r);
$result=iconv("GB2312", $charset,$result);
return $result;
}
//通过discuz获取文章关键字(标签)，输入标题和内容 即可返回5个关键字数组
function getTags($title,$content){
$subjectenc = rawurlencode(strip_tags($title));
$messageenc = rawurlencode(strip_tags(preg_replace("/\[.+?\]/U", '',$content)));
$subjectenc =substr($subjectenc,0,60);
$messageenc=substr($messageenc,0,1200);
$data = @implode('', file("http://keyword.discuz.com/related_kw.html?title=$subjectenc&content=$messageenc&ics=utf-8&ocs=utf-8"));
$kws = array();
if($data) {
$parser = xml_parser_create();
xml_parser_set_option($parser, XML_OPTION_CASE_FOLDING, 0);
xml_parser_set_option($parser, XML_OPTION_SKIP_WHITE, 1);
xml_parse_into_struct($parser, $data, $values, $index);
xml_parser_free($parser);
foreach($values as $valuearray) {
if($valuearray['tag'] == 'kw' || $valuearray['tag'] == 'ekw') {
$kw =trim($valuearray['value']);
$kws[] =$kw ;
}
}
}
return $kws;
}
最新评论：
no.14495 beltran 5.35.69.214 2018-07-10 11:59
no.14104 support 5.188.211.35 2018-05-12 18:29
no.14087 support 5.188.211.10 2018-05-12 05:47
no.13792 cbivpcreecewexumma 46.161.9.9 2018-04-06 08:41
no.13791 jraafcreecewexumma 46.161.9.9 2018-04-06 06:15
no.13786 owrciBavaFalliawnlem 46.161.9.69 2018-04-05 19:37
no.13779 vczvnBavaFalliawnlem 46.161.9.69 2018-04-05 07:20
no.13771 matveylandikaj 146.185.223.230 2018-04-04 16:37
no.13770 matveylandikaj 146.185.223.230 2018-04-04 16:37
no.13769 matveylandikaj 146.185.223.230 2018-04-04 16:37
no.13768 matveylandikaj 146.185.223.230 2018-04-04 16:36
no.13767 matveylandikaj 146.185.223.230 2018-04-04 16:36
no.13766 matveylandikaj 146.185.223.230 2018-04-04 13:57
no.13762 matveylandikaj 146.185.223.230 2018-04-04 08:32
no.13761 matveylandikaj 146.185.223.230 2018-04-04 08:32
no.13760 matveylandikaj 146.185.223.230 2018-04-04 08:32
no.13759 matveylandikaj 146.185.223.230 2018-04-04 08:32
no.13758 matveylandikaj 146.185.223.230 2018-04-04 08:32
no.13755 juiyccreecewexumma 46.161.9.9 2018-04-04 05:50
no.13754 matveylandikaj 146.185.223.230 2018-04-04 02:40
no.13753 matveylandikaj 146.185.223.230 2018-04-04 02:40
no.13752 matveylandikaj 146.185.223.230 2018-04-04 02:40
no.13751 matveylandikaj 146.185.223.230 2018-04-04 02:40
no.13750 matveylandikaj 146.185.223.230 2018-04-04 02:40
no.13747 matveylandikaj 146.185.223.230 2018-04-04 00:47
no.13746 matveylandikaj 146.185.223.230 2018-04-04 00:46
no.13745 matveylandikaj 146.185.223.230 2018-04-04 00:46
no.13744 matveylandikaj 146.185.223.230 2018-04-04 00:46
no.13743 matveylandikaj 146.185.223.230 2018-04-04 00:46
no.13741 matveylandikaj 146.185.223.230 2018-04-03 18:45
no.13740 matveylandikaj 146.185.223.230 2018-04-03 18:45
no.13739 matveylandikaj 146.185.223.230 2018-04-03 18:45
no.13738 matveylandikaj 146.185.223.230 2018-04-03 18:45
no.13737 matveylandikaj 146.185.223.230 2018-04-03 18:45
no.13733 matveylandikaj 146.185.223.230 2018-04-03 13:07
no.13732 matveylandikaj 146.185.223.230 2018-04-03 13:07
no.13731 matveylandikaj 146.185.223.230 2018-04-03 13:07
no.13730 matveylandikaj 146.185.223.230 2018-04-03 13:07
no.13729 matveylandikaj 146.185.223.230 2018-04-03 13:07
no.13728 matveylandikaj 146.185.223.230 2018-04-03 11:30
no.13727 matveylandikaj 146.185.223.230 2018-04-03 11:30
no.13726 matveylandikaj 146.185.223.230 2018-04-03 11:30
no.13725 matveylandikaj 146.185.223.230 2018-04-03 11:30
no.13724 matveylandikaj 146.185.223.230 2018-04-03 11:29
no.13718 matveylandikaj 146.185.223.230 2018-04-03 05:44
no.13717 matveylandikaj 146.185.223.230 2018-04-03 05:44
no.13716 matveylandikaj 146.185.223.230 2018-04-03 05:44
no.13715 matveylandikaj 146.185.223.230 2018-04-03 05:44
no.13714 matveylandikaj 146.185.223.230 2018-04-03 05:44
no.13707 ndiomcreecewexumma 46.161.9.9 2018-04-02 13:46