抓取資網中心活動報導到學校網頁

1. 活動報導.php
   主程式，抓取資網中心的活動報導用。
2. SchoolNews.htm
   靜態網頁，將上面抓到的最新幾則報導放入，顯示在首頁。
3. 參考網頁：
1. http://kingjoy1235.pixnet.net/blog/post/28534965-php抓網頁內容
2. http://andy.diimii.com/2009/03/php抓取網頁特定div區塊及圖片/
3. https://zh.wikipedia.org/zh-tw/正则表达式
4. https://atedev.wordpress.com/2007/11/23/正規表示式-regular-expression/
5. http://blog.bestdaylong.com/2007/06/php-big5utf-8.html

---

<?php

//顯示錯誤訊息

//ini_set('display_errors', 1);

//相關 CSS & js

$display =  <<<END_head

<link rel="stylesheet" type="text/css" href="http://www.tc.edu.tw/themes/web2011/css/960grid/960.css" media="screen" />

<link type="text/css" href="http://www.tc.edu.tw/js/jquery-ui/themes/flick/jquery.ui.all.css" media="screen" rel="stylesheet" />

<link href="http://www.tc.edu.tw/css/popeye/jquery.popeye.css" media="screen" rel="stylesheet" type="text/css" >

<link href="http://www.tc.edu.tw/css/popeye/jquery.popeye.style.css" media="screen" rel="stylesheet" type="text/css" >

<script type="text/javascript" src="http://www.tc.edu.tw/js/jquery-1.7.2.min.js"></script>

<script type="text/javascript" src="http://www.tc.edu.tw/js/jquery-ui-1.8.9.custom.min.js"></script>

<script type="text/javascript" src="http://www.tc.edu.tw/js/jquery.hoverIntent.minified.js"></script>

<script type="text/javascript" src="http://www.tc.edu.tw/js/plugins/jquery-idleTimeout.js"></script>

<script type="text/javascript" src="http://www.tc.edu.tw/js/plugins/jquery.popeye-2.0.4.min.js"></script>

<!--

.news_content {padding:5px; font-size:1.1em;}

.news_content:first-letter { font-weight: bold; font-size: 180%; float: left; color: #0055cc; margin:3px;}

.meta {text-align:right;padding:5px;  font-style: italic;}

.meta a:HOVER {text-decoration: underline;}

#main_content h3 {font-size:1.3em; }

.news_more a, .meta a{color:navy; font-weight: bold;}

#sidebar h4 {color:#33a;font-size:1.2em}

#sidebar li {color:#355; list-style: none; margin:3px}

.item-list a {color:#33a;font-weight: normal;}

.item-list a:HOVER {color:#655}

.item-list li {

   background : url(/images/icon01.jpg) left  no-repeat;

   margin: 3px;

   padding-left:20px;

   padding-bottom: 5px;

   border-bottom: thin dotted #ccc;

} 

.news_tags {background: #cce;padding:3px;margin:5px 0;}

.favoriteDiv {text-align:right; border-top: thin dotted #ccc; padding:3px; margin-top: 30px}

.favorite {

width: 16px;

    height: 16px;

    background-repeat:no-repeat;

    padding-left: 20px;

    padding-top: 0px;

    background-image: url("/images/icons/heart.png");

}

#favorite_count,.favorite_count {margin:3px; color:#e33; font-weight: bold;}

.last_update_time {border-top:thin dotted #ccc; padding-top:15px; margin-top:10px;text-align: right; font-style: italic; font-size:85%}

.sub_title {margin: 0 0 10px 0; pagging:0px ;text-align: center; font-size: 16px; color: #03e;}

.support_count {color:#f30}

/* Tag cloud */

    .tags {

        margin:0.3em;

        padding:.5em 10px;

        text-align:center;

        background:#71b5e9 url(/css/images/bg_tags.gif) repeat-x;       

        }

    .tags  a{

        text-decoration:none;

        color:#fff;

        padding:0 2px;  

        }

    .tags  a:hover{   

        color:#cff400;

        }       

    

    .tag1{font-size:100%;}

    .tag2{font-size:120%;}

    .tag3{font-size:140%;}

    .tag4{font-size:160%;}

    .tag5{font-size:180%;}

    

    /* alternative layout */

    .tags .alt{

        text-align:left;

        padding:0;

        background:none;

        }

    .tags .alt li{

        padding:2px 10px;

        background:#efefef;

        display:block;

        }

    .tags .alt .tag1, 

    .tags .alt .tag2, 

    .tags .alt .tag3, 

    .tags .alt .tag4, 

    .tags .alt .tag5{font-size:100%;}

    .tags .alt .tag1{background:#7cc0f4;}

    .tags .alt .tag2{background:#67abe0;}

    .tags .alt .tag3{background:#4d92c7;}

    .tags .alt .tag4{background:#3277ad;}

    .tags .alt .tag5{background:#266ca2;}

    

/* // Tag cloud */

-->

<script>

$(function(){

$('.ppy').popeye();

});

</script>

END_head;

//活動報導網頁

$url = "http://www.tc.edu.tw/SchoolNews/show/school/id/458";

//抓取網頁內容

$ch = curl_init();

$timeout = 5;

curl_setopt($ch, CURLOPT_URL, $url);

curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);

curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);

$contents = curl_exec($ch);

curl_close($ch);

//echo $contents;

//替換掉一些鏈結

$contents=str_replace ("/upload/","http://www.tc.edu.tw/upload/",$contents);

$contents=str_replace ("/SchoolNews/","http://www.tc.edu.tw/SchoolNews/",$contents);

//取出相關內容，並儲存至陣列 match  

preg_match_all('/<h3 [^>]*class="ui-widget-header ui-corner-top"[^>]*>(.*?)<\/h3>/si',$contents,$match[0]); 

preg_match_all('/<p [^>]*class="meta"[^>]*>(.*?)<\/p>/si',$contents,$match[1]); 

preg_match_all('/<div [^>]*class="ppy newsppy"[^>]*>(.*?) <\/span>[^.]*<\/div>[^.]*<\/div>/si',$contents,$match[2]);  

preg_match_all('/<div[^>]*class="news_content"[^>]*>(.*?)<\/div>/si',$contents,$match[3]); 

//取出最前面幾則報導

$show=3;

for ($i=0; $i<$show; $i++)

{

for ($j=0; $j<=3; $j++)

{

$display=$display.$match[$j][0][$i]."\n\n";

}

$display=$display."<div class=\"clear\"></div>\n\n";

}

$display=iconv("UTF-8","big5",$display);

echo $display;

$display=$display."<br><br><a href=\"/cnes/活動報導.php\" target=_blank>更新活動報導</a>";

//寫入 HTML 檔

$file=fopen("SchoolNews.htm","w");

fwrite($file,$display);

fclose($file);

?>