www.espnstar.com.cn.html

一个java+Mysql写的主题爬虫,可以通过给定初始的url爬取到相关的网页

<style>
.box {
	background: url(http://210.192.114.181/new/CustomMyTeam/images/ranks_031.png) no-repeat top right;
	height:24px;
	overflow:hidden;
	line-height:24px;
	margin-bottom:5px;
}
.box_lbg {
	background:url(http://210.192.114.181/new/CustomMyTeam/images/ranks_011.png) no-repeat top left;
	padding-left:5px;
	display:block;
	text-align:center;
}
.box a {
	color:red;
}
</style>
<div class="box"><span class="box_lbg"><a href="http://zqwm1.espnstar.com.cn?3" target=_blank title="掌控曼联米兰命运尽在网页足球经理游戏《足球文明》">掌控曼联米兰命运尽在网页足球经理游戏《足球文明》</a></span></div>

<!-- 搜索 begin -->
<div id="search_new">
	<script type="text/javascript">
	function postsearchform(posttype){
		if (posttype == "news"){
			document.getElementById("keyword").value = document.getElementById("keyword_new").value;
			document.getElementById("search_form").action="/new/search/";
		}else if(posttype == "img"){
			document.getElementById("keyword").value = document.getElementById("keyword_img").value;
			document.getElementById("search_form").action="/new/search/img.asp";
		}else if(posttype == "program"){
			document.getElementById("keyword").value = document.getElementById("keyword_program").value;
			document.getElementById("search_form").action="/new/search/program.asp";
		}else{
			document.getElementById("keyword").value = document.getElementById("keyword_video").value;
			document.getElementById("search_form").action="/new/search/fvideo.asp";
		}
		
		if (document.getElementById("keyword").value == "")
			return false;
	}
	function search_result() {
		var W,X,y,i,x
		var frmSearch = document.getElementById("search_form");
		x = frmSearch.selectmonth.options[frmSearch.selectmonth.options.selectedIndex].value;
		W = new Date(x);
		y=W.getFullYear();
		X=W.getMonth()+1;
		i=frmSearch.selectday.options[frmSearch.selectday.options.selectedIndex].value;
		var str = "StaticHomepage/" + y + "-" + X + "-" + i;
		window.open(str);
	}
	</script>
	<form id="search_form" action="/new/search/" method="get" target="_blank">
	<div id="TabbedPanels8" class="TabbedPanels">
	    <ul class="TabbedPanelsTabGroup">
	        <li class="TabbedPanelsTab" tabindex="0"><span>新闻</span></li>
	        <li class="TabbedPanelsTab" tabindex="0"><span>图片</span></li>
	        <li class="TabbedPanelsTab" tabindex="0"><span>视频</span></li>
	        <li class="TabbedPanelsTab" tabindex="0"><span>历史首页</span></li>
	        <li class="TabbedPanelsTab" tabindex="0"><span>节目查询</span></li>
	    </ul>
    	<div class="TabbedPanelsContentGroup">
        	<div class="TabbedPanelsContent">
        	<input id="keyword_new" name="keyword_new" type="text" size="25" class="text"/> <input type="submit" value="新闻搜索" id="newsclick" class="button" onclick="return postsearchform('news')"/>
        	<br>
        	<a href="/new/search/?keyword=尤文图斯" target="_blank">尤文图斯</a>  <a href="/new/search/?keyword=官网" target="_blank">官网</a>  <a href="/new/search/?keyword=丁俊晖" target="_blank">丁俊晖</a>  <a href="/new/search/?keyword=姚明" target="_blank">姚明</a>  <a href="/new/search/?keyword=火箭" target="_blank">火箭</a>  <a href="/new/search/?keyword=鲁能" target="_blank">鲁能</a>  <a href="/new/search/?keyword=米兰" target="_blank">米兰</a>  <a href="/new/search/?keyword=杨云" target="_blank">杨云</a>  
	   </div>
    <div class="TabbedPanelsContent">
    	<input id="keyword_img" name="keyword_img" type="text" size="25" class="text" onkeydown="if(event.keyCode == 13){document.getElementById('imgclick').click();}"/> <input type="submit" value="图片搜索" class="button" id="imgclick" onclick="return postsearchform('img')"/>
    	<br>
        	<a href="/new/search/img.asp?keyword=美女" target="_blank">美女</a>  <a href="/new/search/img.asp?keyword=伊万诺维奇" target="_blank">伊万诺维奇</a>  <a href="/new/search/img.asp?keyword=火箭" target="_blank">火箭</a>  <a href="/new/search/img.asp?keyword=姚明" target="_blank">姚明</a>  <a href="/new/search/img.asp?keyword=米兰" target="_blank">米兰</a>  <a href="/new/search/img.asp?keyword=宝贝" target="_blank">宝贝</a>  <a href="/new/search/img.asp?keyword=曼联" target="_blank">曼联</a>  <a href="/new/search/img.asp?keyword=巴萨" target="_blank">巴萨</a>  
    </div>
    <div class="TabbedPanelsContent">
    	<input id="keyword_video" name="keyword_video" type="text" size="25" class="text" onkeydown="if(event.keyCode == 13){document.getElementById('videoclick').click();}" /> <input type="submit" value="视频搜索" id="videoclick" class="button" onclick="return postsearchform('video')"/>
    	<br>
    	<a href="/new/search/fvideo.asp?keyword=意甲" target="_blank">意甲</a>  <a href="/new/search/fvideo.asp?keyword=米兰" target="_blank">米兰</a>  <a href="/new/search/fvideo.asp?keyword=欧冠" target="_blank">欧冠</a>  <a href="/new/search/fvideo.asp?keyword=NCAA" target="_blank">NCAA</a>  <a href="/new/search/fvideo.asp?keyword=摔角" target="_blank">摔角</a>  <a href="/new/search/fvideo.asp?keyword=滑板" target="_blank">滑板</a>  <a href="/new/search/fvideo.asp?keyword=九球" target="_blank">九球</a>  <a href="/new/search/fvideo.asp?keyword=PGA" target="_blank">PGA</a>  
    </div>
    <div class="TabbedPanelsContent">
    	
		<select name="selectmonth" style="background-color:#214C77;color:#fff;">
		<option value="1/1/2007" >2007-1</option>
		<option value="2/1/2007" >2007-2</option>
		<option value="3/1/2007" >2007-3</option>
		<option value="4/1/2007" >2007-4</option>
		<option value="5/1/2007" >2007-5</option>
		<option value="6/1/2007" >2007-6</option>
		<option value="7/1/2007" >2007-7</option>
		<option value="8/1/2007" >2007-8</option>
		<option value="9/1/2007" >2007-9</option>
		<option value="10/1/2007" >2007-10</option>
		<option value="11/1/2007" >2007-11</option>
		<option value="12/1/2007" >2007-12</option>
		<option value="1/1/2008" >2008-1</option>
		<option value="2/1/2008" >2008-2</option>
		<option value="3/1/2008" >2008-3</option>
		<option value="4/1/2008" >2008-4</option>
		<option value="5/1/2008" >2008-5</option>
		<option value="6/1/2008" >2008-6</option>
		<option value="7/1/2008" >2008-7</option>
		<option value="8/1/2008" >2008-8</option>
		<option value="9/1/2008" >2008-9</option>
		<option value="10/1/2008" >2008-10</option>
		<option value="11/1/2008" >2008-11</option>
		<option value="12/1/2008" >2008-12</option>
		<option value="1/1/2009" >2009-1</option>
		<option value="2/1/2009" >2009-2</option>
		<option value="3/1/2009" >2009-3</option>
		<option value="4/1/2009" >2009-4</option>
		<option value="5/1/2009" selected>2009-5</option>
		</select>
		<select name="selectday">
		<option value="1" >1</option>
		<option value="2" >2</option>
		<option value="3" >3</option>
		<option value="4" >4</option>
		<option value="5" >5</option>
		<option value="6" >6</option>
		<option value="7" >7</option>
		<option value="8" >8</option>
		<option value="9" >9</option>
		<option value="10" >10</option>
		<option value="11" >11</option>
		<option value="12" >12</option>
		<option value="13" >13</option>
		<option value="14" >14</option>
		<option value="15" >15</option>
		<option value="16" >16</option>
		<option value="17" >17</option>
		<option value="18" >18</option>