时间：2021-07-01 10:21:17 帮助过：20人阅读
* @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: 一篇新闻标题的从直接抽取</pre>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); ?> </pre><br /><br /><br /> </div> <div class=""> <ul class="m-news-opt fix"> <li class="opt-item"> <a href='/PHPjiqiao-117656.html' target='_blank'><p>< 上一篇</p><p class="ellipsis">关于doitphp,thinkphp,yii,ci,doophp等框架的性能测试对照</p></a> </li> <li class="opt-item ta-r"> <a href='/PHPjiqiao-117658.html' target='_blank'><p>下一篇 ></p><p class="ellipsis">分析几种PHP获取客户端IP的景况</p></a> </li> </ul> </div> </div> </div> <div class="g-title fix"> <h2 class="title-txt">人气教程排行</h2> </div> <div class="m-rank u-dashed mb40"> <ul> <li class="rank-item"> <a href="/PHPjiqiao-379253.html" title='php如何获取跳转前的url' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num top">1</span> php如何获取跳转前的url </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-379019.html" title='php格林威治时间转换成当前时间的方法' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num second">2</span> php格林威治时间转换成当前时间的方法 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-366629.html" title='为什么php不能做大型系统？' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num third">3</span> 为什么php不能做大型系统？ </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-207623.html" title='range函数怎么用' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">4</span> range函数怎么用 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-162433.html" title='php中计算页面加载时间几种方法总结_PHP教程' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">5</span> php中计算页面加载时间几种方法总结_PHP教程 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-140221.html" title='求帮助，关于paypal支付返回值修改订单状态' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">6</span> 求帮助，关于paypal支付返回值修改订单状态 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-103588.html" title='typecho怎么配置文章内容页?' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">7</span> typecho怎么配置文章内容页? </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-99213.html" title='PhpStorm左侧structure不显示文件的方法列表是这么回事？' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">8</span> PhpStorm左侧structure不显示文件的方法列表是这么回事？ </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-92208.html" title='查看PHP的环境变量_PHP' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">9</span> 查看PHP的环境变量_PHP </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-170.html" title='PHP Primary script unknown 解决方法总结' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">10</span> PHP Primary script unknown 解决方法总结 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-148.html" title='php的命名空间与自动加载实现方法' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">11</span> php的命名空间与自动加载实现方法 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-133.html" title='解决laravel 出现ajax请求419(unknown status)的问题' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">174次</span> <span class="g-sort-num ">12</span> 解决laravel 出现ajax请求419(unknown status)的问题 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-462817.html" title='php 如何删除mysql记录' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">13</span> php 如何删除mysql记录 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-388448.html" title='PHP如何替换数组中的指定元素' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">14</span> PHP如何替换数组中的指定元素 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-124270.html" title='怎么去除字符串中非汉字、非字母、非数字的字符' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">15</span> 怎么去除字符串中非汉字、非字母、非数字的字符 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-112291.html" title='mysql如何一次执行多条SQL语句' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">16</span> mysql如何一次执行多条SQL语句 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-110669.html" title='修改header里面的Connection为close解决方法' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">17</span> 修改header里面的Connection为close解决方法 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-153.html" title='PHP基于session.upload_progress 实现文件上传进度显示功能详解' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">18</span> PHP基于session.upload_progress 实现文件上传进度显示功能详解 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-125.html" title='php5.6.x到php7.0.x特性小结' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">173次</span> <span class="g-sort-num ">19</span> php5.6.x到php7.0.x特性小结 </a> </li> <li class="rank-item"> <a href="/PHPjiqiao-378118.html" title='php为什么会出现504错误' class="item-name ellipsis" target="_blank"> <span class="g-art-count fr">172次</span> <span class="g-sort-num ">20</span> php为什么会出现504错误 </a> </li> </ul> </div> </div> </div> <!-- / 教程内容页 --> </div> </div> <!-- 页尾 --> <div class="footer"> 本站所有资源全部来源于网络，若本站发布的内容侵害到您的隐私或者利益，请联系我们删除！</div> <!-- / 页尾 --> <script type="text/javascript" src="/kan/js/read.js"></script> <div style="display:none"> <div class="login-box" id="login-dialog"> <div class="login-top"><a class="current" rel="nofollow" id="login1" onclick="setTab('login',1,2);" >登录</a></div> <div class="login-form" id="nav-signin"> <!-- <div class="login-ico"><a rel="nofollow" class="qq" id="qqlogin" target="_blank" href="/user-center-qqlogin.html"> QQ </a></div> --> <div class="login-box-form" id="con_login_1"> <form id="loginform" action="/user-center-login.html" method="post" onsubmit="return false;"> <p class="int-text"> <input class="email" id="username" name="username" type="text" value="用户名或Email" onfocus="if(this.value=='用户名或Email'){this.value='';}" onblur="if(this.value==''){this.value='用户名或Email';};" ></p> <p class="int-text"> <input class="password1" type="password" id="password" name="password" value="******" onBlur="if(this.value=='') this.value='******';" onFocus="if(this.value=='******') this.value='';" > </p> <p class="int-info"> <label class="ui-label"> </label> <label for="agreement" class="ui-label-checkbox"> <input type="checkbox" value="" name="cookietime" id="cookietime" checked="checked" value="2592000"> <input type="hidden" name="notforward" id="notforward" value="1"> <input type="hidden" name="dosubmit" id="dosubmit" value="1">记住我的登录 </label> <a rel="nofollow" class="aright" href="/user-center-forgetpwd.html" target="_blank"> 忘记密码？ </a></p> <p class="int-btn"><a rel="nofollow" id="loginbt" class="loginbtn"><span>登录</span></a></p> </form> </div> <form id="regform" action="/user-center-reg.html" method="post"> <div class="login-reg" style="display: none;" id="con_login_2"> <input type="hidden" name="t" id="t"/> <p class="int-text"> <input id="email" name="email" type="text" value="Email" onfocus="if(this.value=='Email'){this.value='';}" onblur="if(this.value==''){this.value='Email';};"></p> <p class="int-text"> <input id="uname" name="username" type="text" value="用户名或昵称" onfocus="if(this.value=='用户名或昵称'){this.value='';}" onblur="if(this.value==''){this.value='用户名或昵称';};"></p> <p class="int-text"> <input type="password" id="pwd" name="password" value="******" onBlur="if(this.value=='') this.value='******';" onFocus="if(this.value=='******') this.value='';"> </p> <p class="int-text1"><span class="inputbox"> <input id="validate" name="validate" type="text" value="验证码" onfocus="if(this.value=='验证码'){this.value='';}" onblur="if(this.value==''){this.value='验证码';};"> </span><span class="yzm-img"><img src="/user-checkcode-index" alt="看不清楚换一张" id="indexlogin"></p> <p class="int-info"> <label> <input value="" name="agreement" id="agreement" CHECKED="checked" type="checkbox"> 我已阅读<a rel="nofollow" href="/user-center-agreement.html">用户协议</a>及<a rel="nofollow" href="/user-center-agreement.html">版权声明</a></label> </p> <p class="int-btn"><input type="hidden" name="dosubmit"/> <a rel="nofollow" class="loginbtn" id="register"><span>注册</span></a></p> </div> </form> </div> </div> </div> </div> <script type="text/javascript" src="/kan/js/foot_js.js"></script> <script> var _hmt = _hmt || []; (function() { var hm = document.createElement("script"); hm.src = "https://hm.baidu.com/hm.js?6dc1c3c5281cf70f49bc0bc860ec24f2"; var s = document.getElementsByTagName("script")[0]; s.parentNode.insertBefore(hm, s); })(); </script> <script type="text/javascript" src="/layui/layui.js"></script> <script> layui.use('code', function() { layui.code({ elem: 'pre', //默认值为.layui-code about: false, skin: 'notepad', title: 'php怎么实现数据库验证跳转代码块', encode: true //是否转义html标签。默认不开启 }); }); </script> </body> </html>