从网页源文件中得到链接

 

1. import java.net.*;
2. import java.io.*;
3. import java.util.*;
5. class ScanPage{
6.     private static String strPage;
7.     private String strUrl;
8.     private String fileName;
9.     public void setURL(String strUrl){
10.         this.strUrl=strUrl;
11.     }
12.     //从地址中得到文件名
13.     public void setFileName(){
14.         int i;
15.         char ch;
16.         i=strUrl.length();
17.         ch=strUrl.charAt(--i);
18.         while(ch!='/' && ch>0)
19.             ch=strUrl.charAt(--i);
20.         fileName=strUrl.substring(i);
21.     }
22.     //下载网页
23.     public void downFile()throws IOException{ 
24.         URL url =new URL(strUrl);
25.         InputStream is =url.openStream();
26.         OutputStream os =new FileOutputStream(fileName);
27.         byte[] buffer =new byte[512];
28.         int len;
29.         while((len =is.read(buffer))!=-1) 
30.             os.write(buffer,0,len);
31.         is.close();
32.         os.close();
33.     }
34.     //读文件
35.     public void readFile() throws IOException {
36.         StringBuffer sb = new StringBuffer();
37.         BufferedReader in =new BufferedReader(new FileReader(fileName));
38.         String s;
39.         while((s = in.readLine()) != null) {
40.             sb.append(s);
41.             sb.append("/n");
42.         }
43.         in.close();
44.         strPage=sb.toString();
45.     }
46.     public String getTitle(){
47.         
48.         return "";
49.     }
50.     //扫描标签，得到资源
51.     public void scanLabel(ArrayList al,String strLabel,String strType){
52.         int idx;   //返回下标
53.         String strTmp;
54.         strPage=strPage.toLowerCase();  //转换为小写,以便后面比较
55.         idx = strPage.indexOf("<body");
56.         while(idx!=-1){
57.             idx=strPage.indexOf(strLabel,idx);
58.             if (idx==-1)
59.                 break;
60.             else{
61.                 int i=0;
62.                 idx=idx+strLabel.length();
63.                 for(;strPage.charAt(idx+i)!='>' && strPage.charAt(idx+i)!=32;++i);
64.                 strTmp=strPage.substring(idx,idx+i);
65.                 idx=idx+i;
66.                 //去掉首尾引号
67.                 if (strTmp.charAt(0)=='/"')
68.                     strTmp=strTmp.substring(1);
69.                 if (strTmp.charAt(strTmp.length()-1)=='/"')
70.                     strTmp=strTmp.substring(0,strTmp.length()-1);
71.             //判断是否是用户需要的类型
72.                 if (strType.equals("*"))
73.                     al.add(strTmp);
74.                 else{
75.                     String right;
76.                     if (strTmp.length()>=strType.length()){
77.                         right=strTmp.substring(strTmp.length()-strType.length());
78.                         right=right.toLowerCase();
79.                         if (right.equals(strType))
80.                             al.add(strTmp);
81.                     }
82.                 }
83.             }
84.         }
85.     }
86. }
88. class ScanApp{
89.     public static void main(String[] args){
90.         ArrayList al=new ArrayList();
91.         ScanPage sp=new ScanPage();
92.         sp.setURL(args[0]);
93.         sp.setFileName();
94.         try{
95.             sp.downFile();
96.             sp.readFile();
97.         }catch(IOException ie){System.out.println("文件操作出错");};
98.         sp.scanLabel(al,"<a href=",".html");
99.         for(int i=0;i<al.size();i++){
100.             System.out.println(al.get(i));
101.         }
102.     }
103. }
105. E:/javawork>java ScanApp http://www.17kyk.com/Html/Book/16/2431/list.html
106. list.html
107. 429400.html
108. 429401.html
109. 439789.html
110. 429403.html
111. 429404.html
112. 429405.html
113. 429406.html
114. 429407.html
115. 429408.html
116. 429409.html
117. 429411.html
118. 429412.html
119. 说明:
120. scanLabel针对<a href和<img src这2个标签进行扫描.
121. 得到所有链接存储在ArrayList中
124. scanLabel(al,"<a href=","*");
125. scanLabel(al,"<img src=","*");
126. 得到特定的链接
127. scanLabel(al,"<a href=",".html");
128. scanLabel(al,"<a href=",".asp");
129. scanLabel(al,"<img src=",".gif");