PHP中文分词,自动获取关键词
header("Content-Type:text/html; charset=utf-8");
define('APP_ROOT', str_replace('\\', '/', dirname(__FILE__)));
$test = '这里是一段中文测试代码!';
function get_tags_arr($title)
{
require(APP_ROOT.'/pscws4.class.php');
$pscws = new PSCWS4();
$pscws->set_dict(APP_ROOT.'/scws/dict.utf8.xdb');
$pscws->set_rule(APP_ROOT.'/scws/rules.utf8.ini');
$pscws->set_ignore(true);
$pscws->send_text($title);
$words = $pscws->get_tops(5);
$tags = array();
foreach ($words as $val) {
$tags[] = $val['word'];
}
$pscws->close();
return $tags;
}
print_r(get_tags_arr($test));
//============================================================
function get_keywords_str($content){
require(APP_ROOT.'/phpanalysis.class.php');
PhpAnalysis::$loadInit = false;
$pa = new PhpAnalysis('utf-8', 'utf-8', false);
$pa->LoadDict();
$pa->SetSource($content);
$pa->StartAnalysis( false );
$tags = $pa->GetFinallyResult();
return $tags;
}
print(get_keywords_str($test));
上一篇: 负载均衡之Nginx详解