<?php
/**
pay salary的英文翻译,pay salary的造句 * @author pqcc <struts.ec@mgail.com>
* @date: 2011-06-18
* Description: 给定一个网页内容,提取网页的标题. 提取的标题不包括 seo 关键字.
* e.g: 一篇新闻标题的从<title>直接抽取结果为 "大学英语四六级本周六开考 909万人参考_新浪教育_新浪网",
* 但我们希望的结果是:"大学英语四六级本周六开考 909万人参考".
* 适用范围: 文章最终页标题的提取, 不包括专题页等.
*/
class TitlePurify{
private $matches_preg = '[-_\s|—]';
function getTitle($contents){/*{{{*/
$preg = "/<title[^>]*>([\w|\t|\r|\W]*?)<\/title>/i";
preg_match($preg, $contents, $matches);
if(count($matches)<=1){
return "标题抽取失败";
}
$title = $matches[1];
return $this->trimTitle($title, $contents);
}/*}}}*/
function trimMeta($contents){/*{{{*/
// 首先去除 <title> 内容, <meta> 内容.
$preg = "/<title[^>]*>([\w|\t|\r|\W]*?)<\/title>/i";
$contents = preg_replace($preg, '', $contents);
$preg = "/<meta[^>]*>/i";
$contents = preg_replace($preg, '', $contents);
return $contents;
}/*}}}*/
// 获取长度最长的 item 所处的index.
function getMaxIndex($titles){/*{{{*/
$maxItemIndex = 0;
$maxLength = 0;
$loop = 0;
foreach($titles as $item){
if(strlen($item)>$maxLength){
$maxLength = strlen($item);
$maxItemIndex = $loop;
}
$loop++;
}
return $maxItemIndex;
}/*}}}*/
function trim($title, $titles, $contents, $maxItemIndex){/*{{{*/
//@todo : 此处可优化contents
// 如果查找成功. result = tempTitle.
$tempTitle = $titles[$maxItemIndex];
$result = $tempTitle;
$count = count($titles);
// while 从当前index 向左进行迭代(直到到达第一个或者匹配失败才中止).
$leftIndex = $maxItemIndex-1;
while(true && $leftIndex>=0){
// tempTitle+左一个.
preg_match("/({$this->matches_preg}+{$tempTitle})/i", $title, $matches);
if(count($matches)>1){
// temp 用于匹配失败后,进行回滚.
$temp = $titles[$leftIndex] . $matches[1];
$tempTitle = $titles[$leftIndex] . $matches[1];
// 继续拿着 tempTitle 去匹配.
preg_match("/$tempTitle/i", $contents, $matches);
// 如果查找失败....
if(count($matches)<1){
$tempTitle = $temp;
break;
}else{
$result = $tempTitle;
}
}else{ // 正常情况下, 不会出现该情况.
break;
}
$leftIndex--;
}
// match(current[i-1].[|-].tempTitle), 如果成功, tempTitle = match 成功的值,继续.
// while 左边失败后, 从右边开始.
$rightIndex = $maxItemIndex+1;
while(true && ($rightIndex<=$count)){
preg_match("/({$tempTitle}{$this->matches_preg}+)/i", $title, $matches);
if(count($matches)>1){
// temp 用于匹配失败后,进行回滚.
$temp = $matches[1] . $titles[$rightIndex];
$tempTitle = $matches[1] . $titles[$rightIndex];
// 继续拿着 tempTitle 去匹配.
preg_match("/$tempTitle/i", $contents, $matches);
// 如果查找失败....
if(count($matches)<1){
$tempTitle = $temp;
break;
}else{
$result = $tempTitle;
}
}else{ // 正常情况下, 不会出现该情况.
break;
}
$rightIndex++;
}
return $result;
}/*}}}*/
function trimTitle($title, $contents){/*{{{*/
$contents = $this->trimMeta($contents);
// 配置切割标题的规则.
$titles = preg_split("/$this->matches_preg/i", $title);
$count = count($titles);
//var_dump($titles);exit;
// 将当前最长的 item 从全文查找.
$maxItemIndex = $this->getMaxIndex($titles);
$tempTitle = $titles[$maxItemIndex];
preg_match("/$tempTitle/i", $contents, $matches);
// 如果查找失败....
if(count($matches)<1){
return $title;
}
return $this->trim($title, $titles, $contents, $maxItemIndex);
}/*}}}*/
}
// ------------- test code ------------------------------
function convertEncoding($contents){
preg_match("/charset=([\w|\-]+);?/i", $contents, $match);
$charset = isset($match[1])? $match[1] : 'UTF-8';
$contents = mb_convert_encoding($contents, 'UTF-8', $charset);
return $contents;
}
$url = 'http://china.nba.com/news/4/2011/0617/61383331/10451.html';
$contents = file_get_contents($url);
$contents = convertEncoding($contents);
$startTime = microtime();
$purify = new TitlePurify();
$title = $purify->getTitle($contents);
$endTime = microtime();
echo "标题: $title ";
echo "cost: " . ($endTime-$startTime);
?>