用HTML Parser抓取HTML文法中的TABLE表資料

因為之前工作需要，老闆叫我分析Html中的table資料，我也有找資料，只是有些看不太懂，也有發問
也被一些人打了回票，所以我就自己研究，算是小有成就，但比起論壇中的大師們，我只是小螞蟻，
我今天要發表出來，或許下個人有個參考方向，這程式改進地方有很多，各位先進大師們，小弟不才
我只學了2個月的Java，往後路很長，希望各位指導小弟一下，感激！！！
小弟用的工具是Jericho HTML Parser，Google一下應該可以找到。
程式很鳥，笑笑就好～

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32

"content-type" content="text/html; charset=big5">

"generator" content="Namo WebEditor">





"2" face="Arial,Verdana">Test Name

"2" face="Arial,Verdana">Result

"2" face="Arial,Verdana">Time

"2" face="Arial,Verdana">Synopsis



"1" face="Arial,Verdana">9   cdrouter_dhcp_20

"1" face="Arial,Verdana">+FAIL "v4_wireless_802.1x_full/cdrouter_dhcp_20.txt">[log]
 
"1" face="Arial,Verdana">12:31

"1" face="Arial,Verdana">DHCP client ignores DHCP packets with corrupt UDP checksum



"1" face="Arial,Verdana">1   cdrouter_basic_1

"1" face="Arial,Verdana">Pass "v4_wireless_802.1x_full/cdrouter_basic_1.txt">[log]
 
"1" face="Arial,Verdana">00:00

"1" face="Arial,Verdana">Router responds to ARP Request on LAN interface

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71

import au.id.jericho.lib.html.*; import java.util.*; import java.io.*; import java.net.*;   public class HtmlParser { public static void main(String[] args) throws Exception { String sourceUrlString="v4_wireless_wpa_dhcp_full.html"; if(sourceUrlString.indexOf(':') == -1) sourceUrlString ="file:"+sourceUrlString; Source source=new Source(new URL(sourceUrlString)); List Elements_TABLE=source.findAllElements(HTMLElementName.TABLE); Elements_TABLE.remove(0); Iterator it_TABLE = Elements_TABLE.iterator(); while(it_TABLE.hasNext()) { Element Element_TABLE = (Element)it_TABLE.next(); Segment getContent_TABLE = (Segment)Element_TABLE.getContent(); List Elements_TR = getContent_TABLE.findAllElements(HTMLElementName.TR); Elements_TR.remove(0); Iterator it_TR = Elements_TR.iterator(); while(it_TR.hasNext()) { Element Element_TR = (Element)it_TR.next(); Segment getContent_TR = (Segment)Element_TR.getContent(); List Elements_FONT = getContent_TR.findAllElements(HTMLElementName.FONT); Iterator it_FONT = Elements_FONT.iterator(); int i = 1; while(it_FONT.hasNext()) { Element Element_FONT = (Element)it_FONT.next(); Segment getContent_FONT = (Segment)Element_FONT.getContent(); String a1 = getContent_FONT.toString(); if ( i == 1 ) { int x = a1.lastIndexOf(';'); System.out.print(a1.substring( (a1.lastIndexOf(';'))+1 , a1.length() )+"," ); } if ( i == 2 || i == 3) { String y = a1.substring(0,5); if( y.equals("Pass ")) { System.out.print(a1.substring(0,4)+","); } else if ( y.equals("+FAIL")) { System.out.print(a1.substring(1,5)+","); } } if (!it_FONT.hasNext()) { System.out.print(a1); } //System.out.println(i + " = " + Element_FONT.getContent()); i++; } System.out.println(); } } } }

本程式就是用下面的Java Code去抓取上面Html文法中的TABLE中的資料。