从网页源文件中得到链接

文章作者 100test 发表时间 2007:11:14 12:48:46
来源 100Test.Com百考试题网

import Java.net.*.
import Java.io.*.
import Java.util.*.

class ScanPage{
private static String strPage.
private String strUrl.
private String fileName.
public void setURL(String strUrl){
this.strUrl=strUrl.
}
//从地址中得到文件名
public void setFileName(){
int i.
char ch.
i=strUrl.length().
ch=strUrl.charAt(--i).
while(ch!=’/’ &.&. ch>0)
ch=strUrl.charAt(--i).
fileName=strUrl.substring(i).
}
//下载网页
public void downFile()throws IOException{
URL url =new URL(strUrl).
InputStream is =url.openStream().
OutputStream os =new FileOutputStream(fileName).
byte[] buffer =new byte[512].
int len.
while((len =is.read(buffer))!=-1)
os.write(buffer,0,len).
is.close().
os.close().
}
//读文件
public void readFile() throws IOException {
StringBuffer sb = new StringBuffer().
BufferedReader in =new BufferedReader(new FileReader(fileName)).
String s.
while((s = in.readLine()) != null) {
sb.append(s).
sb.append("\n").
}
in.close().
strPage=sb.toString().
}
public String getTitle(){

return "".
}