直接上代码，很简单，如果你是大神，请忽略本文章，这是给做web的新手!
//主函数
package com.yemian;
import java.io.IOException;
public class Xin {
public static void main(String[] args) throws IOException {
//两个文件，第一个是在网站上下载的页面，第二个保存的文件，注意这里用的是gbk，utf需要转码，或者将IO的读取设为utf-8
Element el = new Element("555.html", "zf1.html");
el.run();
}
}
//替换类
package com.yemian;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.Writer;
import java.nio.charset.Charset;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class Element {
private BufferedReader buf = null;
private Writer out = null;
private int n = 0;
public Element(String buf, String out) {
//super();
try {
this.buf = new BufferedReader(new InputStreamReader(new FileInputStream(new File(buf))));
this.out = new FileWriter(new File(out));
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void run() throws IOException {
String str = null;
StringBuffer sb = new StringBuffer();
Pattern p = Pattern.compile("(](.*)");
Matcher m =null;
while((str = buf.readLine()) != null) {
str = href("(.*)(href=\"([^\"]{2,})\")([\\s>]?)(.*)",str);
out.write(str);
out.write("\r\n");
}
buf.close();
out.close();
System.out.println(n);
}
public String href(String regex,String str) {
Pattern p = Pattern.compile(regex);//建立匹配起
Matcher m = p.matcher(str);//匹配
String fs = null;
while(str.matches(regex)){
if(m.find()) {
str = m.group(1)+" href=\"#\" "+m.group(4)+m.group(5);
m = p.matcher(str);
}else{
break;
}
n++;//统计替换了多少个
m = p.matcher(str);//查找下一个可能有很多
}
return str;
}
}
