.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

						<tr>
							<td>05-19 20:00</td>

							<td align="center">申花</td>
							<td align="center"><a href="http://sports.tom.com/2009-05-19/07M9/46332849.html" target="_blank"><u><font color=blue>1-1</font></u></a></td>
							<td align="center">鹿岛</td>
							<td align="center"><a href="http://post.sports.tom.com/s/3B00091B798.html" target="_blank"><u><font color=blue>数据</font></u></a></td>
						</tr>
						<tr>
							<td>05-20 19:00</td>

							<td align="center">国安</td>
							<td align="center"><a href="http://sports.tom.com/2009-05-20/07MD/42823868.html" target="_blank"><u><font color=blue>1-1</font></u></a></td>
							<td align="center">鲸八</td>
							<td align="center"><a href="http://post.sports.tom.com/s/30000AB4304.html" target="_blank"><u><font color=blue>数据</font></u></a></td>
						</tr>
						<tr>
							<td>05-20 21:00</td>

							<td align="center">斯里</td>
							<td align="center"><a href="http://sports.tom.com/2009-05-20/07MF/53751999.html" target="_blank"><u><font color=blue>4-2</font></u></a></td>
							<td align="center">鲁能</td>
							<td align="center"><a href="http://post.sports.tom.com/s/EC00091E513.html" target="_blank"><u><font color=blue>数据</font></u></a></td>
						</tr>
					</table>
				</div>

				<div id="cont0" class="tabcont">
					<table border="0" cellspacing="0" cellpadding="0">
						<tr>
							<th>日期</th>
							<th>球队</th>
							<th>比分</th>
							<th>球队</th>

							<th class="bdr">数据</th>
						</tr>
						<tr>
							<td>05-23 15:30</td>
							<td align="center">深圳</td>
							<td align="center">VS</td>
							<td align="center">长沙</td>

							<td align="center">焦点</td>
						</tr>
						<tr>
							<td>05-23 15:30</td>
							<td align="center">成都</td>
							<td align="center">VS</td>
							<td align="center">杭州</td>

							<td align="center">焦点</td>
						</tr>
						<tr>
							<td>05-23 19:30</td>
							<td align="center">长春</td>
							<td align="center">VS</td>
							<td align="center">天津</td>

							<td align="center">焦点</td>
						</tr>
						<tr>
							<td>05-24 15:30</td>
							<td align="center">陕西</td>
							<td align="center">VS</td>
							<td align="center">广药</td>

							<td align="center">焦点</td>
						</tr>
												<tr>



							<td>05-24 16:00</td>
							<td align="center">江苏</td>

							<td align="center">VS</td>
							<td align="center">重庆</td>

							<td align="center">焦点</td>
						</tr>
						<tr>
							<td height="14">05-24 19:30</td>
							<td align="center">北京</td>
							<td align="center">VS</td>
							<td align="center">青岛</td>

							<td align="center">焦点</td>
						</tr>

						<tr>
							<td>05-24 19:30</td>
							<td align="center">山东</td>
							<td align="center">VS</td>
							<td align="center">大连</td>

							<td align="center">焦点</td>
						</tr>
						<tr>
							<td>05-24 19:45</td>
							<td align="center">上海</td>
							<td align="center">VS</td>
							<td align="center">河南</td>

							<td align="center">焦点</td>
						</tr>
					</table>
				</div>
			</div>
			<script type="text/javascript">show(tabDiv(2,'tab','cont','curr'),0);</script>
			<div class="mr">
				<h2>看点</h2>

				<a href="http://sports.tom.com/2009-05-21/07ME/76604439.html" target="_blank"><img src='http://sports.tom.com/uldf/2009/0521/zhuyun/soccer09052102x.jpg' /></a>

			  <p><a href="/2009-05-20/07MF/55471840.html" target="_blank">鲁能520溃败惨案怎能让球迷爱中超?</a><br>
			    　　<a href="http://post.sports.tom.com/s/14000913268.html" target="_blank">几失全部尊严 双线突破一夜成泡影</a><br>
			  　　<a href="http://post.sports.tom.com/s/FA0008B9868.html" target="_blank">过亿投资却换垫底 黄金甲变青铜器</a></p>
			  <h2>活动专区</h2>
				<a href="http://post.sports.tom.com/s/6B000A93290.html" target="_blank"><img src='http://sports.tom.com/uldf/2009/0430/zhuyun/soccer09043007.jpg' /></a>
			  <p>　
		    <a href="http://sports.tom.com/2009-03-16/0KQ2/12467122.html" target="_blank"><b><font color=blue>亚冠有奖寻宝第一期获奖名单</font></b></a><br>　　
		      <a href="http://sports.tom.com/2009-03-24/0KQ2/19481787.html" target="_blank"><b><font color=blue>亚冠有奖寻宝第二期获奖名单</font></b></a></p>
			</div>
<!-- 赛程与活动 -->
			
		</td>

	</tr>
</table>
<!-- 16强列表 -->
<!-- 足彩首屏下方宣传通栏 -->
<html>
<head>
<title>Untitled Document</title>
<meta http-equiv="Content-Type" content="text/html; charset=gb2312">
<style type="text/css">
<!--
body,td {font-size: 12px;line-height:18px}
a:link,a:visited {color: #000; text-decoration:none}
a:hover {color: #000; text-decoration:underline}
.t01 {line-height:14px;width:20px;height:70px}
.t02 {line-height:14px;width:36px;height:70px}
.t03 {line-height:14px;width:24px;height:70px}
.s01 {color:#134CA2; line-height:18px}
.s02 {color:#F05500; line-height:18px}
.yt_01 {color:#6E6E6E}
.yt_01 a:link,.yt_01 a:visited {color: #6E6E6E; text-decoration:none}
.yt_01 a:hover {color: #6E6E6E; text-decoration:underline}

.tb21_on {background-image: url(/caipiao/center/y_06.gif);font-weight:bold;color:#134CA2;width:64px;padding-top:2px;cursor:pointer}
.tb21_off {background-image: url(/caipiao/center/y_07.gif);font-weight:bold;color:#134CA2;width:59px;padding-top:4px;cursor:pointer}
.tb22_on {background-image: url(/caipiao/center/y_08.gif);font-weight:bold;color:#4F9800;width:64px;padding-top:2px;cursor:pointer}
.tb22_off {background-image: url(/caipiao/center/y_09.gif);font-weight:bold;color:#4F9800;width:58px;padding-top:4px;cursor:pointer}
.tb23_on {background-image: url(/caipiao/center/y_10.gif);font-weight:bold;color:#F05500;width:64px;padding-top:2px;cursor:pointer}
.tb23_off {background-image: url(/caipiao/center/y_11.gif);font-weight:bold;color:#F05500;width:58px;padding-top:4px;cursor:pointer}
.tb31_on,.tb41_on {background-image: url(/caipiao/center/x_01.jpg);font-weight:bold;color:#134CA2;width:104px;padding-top:2px;cursor:pointer}
.tb31_off,.tb41_off {background-image: url(/caipiao/center/x_03.jpg);font-weight:bold;color:#134CA2;width:99px;padding-top:4px;cursor:pointer}
.tb32_on,.tb42_on {background-image: url(/caipiao/center/x_05.jpg);font-weight:bold;color:#4F9800;width:104px;padding-top:2px;cursor:pointer}
.tb32_off,.tb42_off {background-image: url(/caipiao/center/x_07.jpg);font-weight:bold;color:#4F9800;width:99px;padding-top:4px;cursor:pointer}
.tb33_on,.tb43_on {background-image: url(/caipiao/center/x_09.jpg);font-weight:bold;color:#F05500;width:104px;padding-top:2px;cursor:pointer}
.tb33_off,.tb43_off {background-image: url(/caipiao/center/x_11.jpg);font-weight:bold;color:#F05500;width:99px;padding-top:4px;cursor:pointer}
//-->
</style>
<script >
<!-- 
	var debug = false ;
	function switchTab (tab)
	{	
		var tabName = getTabGroupName (tab.id) ;
		if (tabName == '')
		{	alert ("No tabName for tab [" + tab.id + "]") ;
			return ;
		}
		var index = 1 ;
		while (true)
		{	var tabTitle = eval ("document.all ('" + tabName + '_' + index + "')") ;
			if (tabTitle == undefined)
				break ;
			deactiveTabTitle (tabTitle , tabName) ;
			var tabContent = eval ("document.all ('" + tabName + '_' + index + '_content' + "')") ;
			if (tabContent != undefined)
				tabContent.style.display = "NONE" ;
			index ++ ;
		}
		if (debug)
			alert ("Find " + (index - 1) + " tab title(s) for TabName [" + tabName + "]") ;
		activeTabTitle (tab , tabName) ;
		var tabContent = eval ("document.all ('" + tab.id + '_content' + "')") ;
		if (tabContent != undefined)
			tabContent.style.display = "BLOCK" ;
	}	
	function getTabGroupName (tabId)
	{
		if (tabId == '' || tabId == undefined)