|
1、获取页面标题
//提取标题
preg_match('/ (?<title>.*?)<＼/title>/i', $html, $titleArr);<br />
$title = $titleArr['title'];<br />
2、获取body主体内容，并将背景图片提取出来替换成其他图片地址</p>
<p>/**<br />
* 获取BODY主体区域内容<br />
* @param $html<br />
* @param $urlRoot<br />
* @return mixed<br />
*/<br />
function getBody($html,$urlRoot = null){<br />
//提取BODY主体<br />
preg_match('/<!--body-->(.*?)<!--body-->/is ', $html, $bodyArr);<br />
if(!$bodyArr){<br />
preg_match('/<body.*?>(.*?)<＼/body>/is ', $html, $bodyArr);<br />
}<br />
$body = $bodyArr[1];<br />
//替换img文件<br />
$body = preg_replace('/(<[img|IMG].*src=[＼'|"])(＼.＼.＼/)*(img.[^＼'||^"]+)/',"$1$urlRoot$3",$body);<br />
//替换html文件内的css背景图片<br />
$body = preg_replace('~＼b(background(-image)?＼s*:(.*?)＼(＼s*[＼'|"]?)(＼.＼.＼/)*(img.*?)?＼s*＼)~i',"$1$urlRoot$5)",$body);<br />
return $body;<br />
}<br />
3、提取页面Description内容</p>
<p>function getDescription($html){<br />
// Get the 'content' attribute value in a <meta name="description" ... /><br />
$matches = array();<br />
<br />
// Search for <meta name="description" content="Buy my stuff" /><br />
preg_match('/<meta.*?name=("|＼')description("|＼').*?content=("|＼')(.*?)("|＼')/i', $html, $matches);<br />
if (count($matches) > 4) {<br />
return trim($matches[4]);<br />
}<br />
<br />
// Order of attributes could be swapped around: <meta content="Buy my stuff" name="description" /><br />
preg_match('/<meta.*?content=("|＼')(.*?)("|＼').*?name=("|＼')description("|＼')/i', $html, $matches);<br />
if (count($matches) > 2) {<br />
return trim($matches[2]);<br />
}<br />
<br />
// No match<br />
return null;<br />
}<br />
4、替换css文件的背景图片地址</p>
<p>/**<br />
* 获取CSS内容<br />
* @param $cssCnt<br />
* @param $urlRoot<br />
* @return mixed<br />
*/<br />
function getCss($cssCnt,$urlRoot =null){<br />
//匹配包含 img文件夹的相对路径图片 （含义绝对路径的不包含在其中）<br />
//匹配替换不一定准确，因为只是将 含义 ../ 的地址转为url 而没有考虑 ../../ 之类的层级关系<br />
$css = preg_replace('~＼b(background(-image)?＼s*:(.*?)＼(＼s*[＼'|"]?)(＼.＼.＼/)*(img.*?)?＼s*＼)~i',"$1$urlRoot$5)",$cssCnt);<br />
//添加css前缀<br />
$css = preg_replace('/＼b.(.*?)[,|{]/',"pat .$0",$cssCnt);<br />
//TODO 压缩css<br />
return $css;<br />
}</p>
<p><br />
</p>
</td>
</tr>
</table>
<p>从上面例子来看其实都是非常的简单就是批有规律的标签为开始与结束节点，这样我们可以获取这两个字符之类的内容也就是我们要提取的内容了哦，只是在中间有字符或空格的一些处理了哦。</p></td>
</tr>
</table>
<div class="articles">
<div class="tit02">
<h4>相关文章</h4>
</div>
<ul>
<li>
<a target="_blank" href="/new/464566.htm">三国志异闻录高速冰冻控制流怎么玩 高速冰冻控制流玩法教学</a>
<span>09-18</span>
</li>
<li>
<a target="_blank" href="/new/464567.htm">鸣潮卡提希娅值得抽吗 卡提希娅抽取建议</a>
<span>09-18</span>
</li>
<li>
<a target="_blank" href="/new/464568.htm">忘川风华录王安石怎么培养 王安石养成攻略</a>
<span>09-18</span>
</li>
<li>
<a target="_blank" href="/new/464569.htm">忘川风华录唐伯虎怎么培养 唐伯虎养成攻略</a>
<span>09-18</span>
</li>
<li>
<a target="_blank" href="/new/464570.htm">无限暖暖音乐季她的回旋我的向往任务怎么过 她的回旋我的向往任务攻略</a>
<span>09-18</span>
</li>
<li>
<a target="_blank" href="/new/464571.htm">新三国志曹操传南华幻境天境9-2怎么过 南华幻境天境9-2过关攻略</a>
<span>09-18</span>
</li>
</ul>
</div>
</div>
<div class="pages art-detail"></div>
</div>
</div>
</div>
</div>
<div class="hot-column">
<div class="cont">
<div class="tit">
<h4>热门栏目</h4>
</div>
<ul class="clearfix">
<li>
<h6><a href="/list-1/" target="_blank">php教程</a></h6>
<a href="/list-45/" target="_blank">php入门</a>
<a href="/list-46/" target="_blank">php安全</a>
<a href="/list-47/" target="_blank">php安装</a>
<a href="/list-48/" target="_blank">php常用代码</a>
<a href="/list-49/" target="_blank">php高级应用</a>
</li>
<li>
<h6><a href="/list-2/" target="_blank">asp.net教程</a></h6>
<a href="/list-78/" target="_blank">基础入门</a>
<a href="/list-79/" target="_blank">.Net开发</a>
<a href="/list-80/" target="_blank">C语言</a>
<a href="/list-81/" target="_blank">VB.Net语言</a>
<a href="/list-82/" target="_blank">WebService</a>
</li>
<li>
<h6><a href="/list-6/" target="_blank">手机开发</a></h6>
<a href="/list-208/" target="_blank">安卓教程</a>
<a href="/list-209/" target="_blank">ios7教程</a>
<a href="/list-210/" target="_blank">Windows Phone</a>
<a href="/list-211/" target="_blank">Windows Mobile</a>
<a href="/list-212/" target="_blank">手机常见问题</a>
</li>
<li>
<h6><a href="/list-3/" target="_blank">css教程</a></h6>
<a href="/list-99/" target="_blank">CSS入门</a>
<a href="/list-100/" target="_blank">常用代码</a>
<a href="/list-101/" target="_blank">经典案例</a>
<a href="/list-102/" target="_blank">样式布局</a>
<a href="/list-103/" target="_blank">高级应用</a>
</li>
<li>
<h6><a href="/list-4/" target="_blank">网页制作</a></h6>
<a href="/list-136/" target="_blank">设计基础</a>
<a href="/list-137/" target="_blank">Dreamweaver</a>
<a href="/list-138/" target="_blank">Frontpage</a>
<a href="/list-139/" target="_blank">js教程</a>
<a href="/list-140/" target="_blank">XNL/XSLT</a>
</li>
<li>
<h6><a href="/list-7/" target="_blank">办公数码</a></h6>
<a href="/list-236/" target="_blank">word</a>
<a href="/list-237/" target="_blank">excel</a>
<a href="/list-238/" target="_blank">powerpoint</a>
<a href="/list-239/" target="_blank">金山WPS</a>
<a href="/list-240/" target="_blank">电脑新手</a>
</li>
<li>
<h6><a href="/list-11/" target="_blank">jsp教程</a></h6>
<a href="/list-68/" target="_blank">Application与Applet</a>
<a href="/list-69/" target="_blank">J2EE/EJB/服务器</a>
<a href="/list-70/" target="_blank">J2ME开发</a>
<a href="/list-71/" target="_blank">Java基础</a>
<a href="/list-72/" target="_blank">Java技巧及代码</a>
</li>
</ul>
</div>
</div>
<div class="footer">
<div class="cont">
<p>
<a href="/" target="_self">一聚教程网</a>|
<a href="javascript:;" class="about" target="_self">关于我们</a>|
<a href="javascript:;" class="contact" target="_self">联系我们</a>|
<a href="javascript:;" class="gg_contact" target="_self">广告合作</a>|
<a href="javascript:;" class="friend_link" target="_self">友情链接</a>|
<a href="javascript:;" class="copyright_notice" target="_self">版权声明</a>
</p>
<p>
<span>copyRight@2007-2022 www.111CN.NET AII Right Reserved <a href="https://beian.miit.gov.cn/" target="_blank" class="beian"></a></span>
</p>
<p>
<span>
网站内容来自网络整理或网友投稿如有侵权行为请邮件:111cn.com@163.com 我们24小时内处理
</span>
</p>
</div>
</div>
<script>
var advData = {"img_fixed_pc_adv":"https:\/\/img.111cn.net\/uploads\/20240509\/663c2e9729f58.jpg","img_fixed_mob_adv":"https:\/\/img.111cn.net\/uploads\/20240509\/663c2e8793225.jpg","url_adv":"http:\/\/shop.hushen.cn\/shop\/c\/baojianpin.html","str_adv":"\u864e\u795e\u5546\u57ce\uff1a\u5173\u7231\u7537\u6027\uff0c\u66f4\u61c2\u7537\u4eba\u3002\u89e3\u51b3\u5927\u4f17\u7684\u7537\u8a00\u4e4b\u9690","img_popup_adv":"https:\/\/img.111cn.net\/uploads\/20240509\/663c2e748238d.png","pc_show_img":"2","pc_show_popup":"2","pc_show_video":"2","mob_show_img":"2","mob_show_popup":"2","mob_show_video":"2","close_adv":"https:\/\/img.111cn.net\/uploads\/20240508\/663b20650801e.png","video_adv":"\/pc\/images\/pc-adv.mp4"};
</script>
<script src="/jspc/func.js" type="text/javascript"></script>
<!-- Google tag (gtag.js) -->
<script async src="https://www.googletagmanager.com/gtag/js?id=G-DSRRGRV1TL"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-DSRRGRV1TL');
</script><script src="/js/stat.js"></script>
<script src="/111/js/shCore.js"></script>
<script src="/111/js/shAutoloader.js"></script>
<script type="text/javascript">
function path() {
var args = arguments,
result = [];
for (var i = 0; i < args.length; i++)
result.push(args[i].replace('$', '/111/js/'));
return result
}
$(function() {
SyntaxHighlighter.autoloader.apply(null, path(
'applescript $shBrushAppleScript.js',
'css $shBrushCss.js',
'java $shBrushJava.js',
'js jscript javascript $shBrushJScript.js',
'php $shBrushPhp.js',
'py python $shBrushPython.js',
'ruby rails ror rb $shBrushRuby.js',
'sass scss $shBrushSass.js',
'sql $shBrushSql.js',
'vb vbnet $shBrushVb.js',
'xml xhtml xslt html $shBrushXml.js'
));
SyntaxHighlighter.all();
});
hljs.highlightAll();
</script>
</body>
</html>
|
