用Java在网页上保存小说

技术点：
	文件存储
	http访问
	正则表达式匹配
	当前系统时间
文件结构：
	File		--appeendFile.java
	Http		--HttpRequest.java
	Matches 	--RegexMatches.java
	Time	 	--currentTime.java
	test.java
	run.bat

appeendFile.java

package File;

import java.io.File;
import java.io.FileWriter;
import java.io.BufferedWriter;
import java.io.IOException;

public class appeendFile {
    public static void fw(String fileName,String data) { 
     try{
      File file =new File(fileName);
      if(!file.exists()){
       file.createNewFile();
      }
      FileWriter fileWritter = new FileWriter(file.getName(),true);
			BufferedWriter bufferWritter = new BufferedWriter(fileWritter);
			bufferWritter.write(data);
			bufferWritter.close();
			System.out.println("fileWritter Done!");
     }catch(IOException e){
      e.printStackTrace();
     }
    }
}

HttpRequest.java

package	Http;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.PrintWriter;
import java.net.URL;
import java.net.URLConnection;
import java.util.List;
import java.util.Map;

public class HttpRequest {
    /**
     * 向指定URL发送GET方法的请求
     * 
     * @param url
     *            发送请求的URL
     * @param param
     *            请求参数，请求参数应该是 name1=value1&name2=value2 的形式。
     * @return URL 所代表远程资源的响应结果
     */
    public static String sendGet(String url, String param) {
        String result = "";
        BufferedReader in = null;
        try {
            String urlNameString = url + "?" + param;
            URL realUrl = new URL(urlNameString);
            // 打开和URL之间的连接
            URLConnection connection = realUrl.openConnection();
            // 设置通用的请求属性
            connection.setRequestProperty("accept", "*/*");
            connection.setRequestProperty("connection", "Keep-Alive");
            connection.setRequestProperty("user-agent",
                    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
            // 建立实际的连接
            connection.connect();
            // 获取所有响应头字段
            Map<String, List<string>> map = connection.getHeaderFields();
            // 遍历所有的响应头字段
            for (String key : map.keySet()) {
                System.out.println(key + "--->" + map.get(key));
            }
            // 定义 BufferedReader输入流来读取URL的响应
            in = new BufferedReader(new InputStreamReader(
                    connection.getInputStream()));
            String line;
            while ((line = in.readLine()) != null) {
                result += line;
            }
        } catch (Exception e) {
            System.out.println("发送GET请求出现异常！" + e);
            e.printStackTrace();
        }
        // 使用finally块来关闭输入流
        finally {
            try {
                if (in != null) {
                    in.close();
                }
            } catch (Exception e2) {
                e2.printStackTrace();
            }
        }
        return result;
    }

    /**
     * 向指定 URL 发送POST方法的请求
     * 
     * @param url
     *            发送请求的 URL
     * @param param
     *            请求参数，请求参数应该是 name1=value1&name2=value2 的形式。
     * @return 所代表远程资源的响应结果
     */
    public static String sendPost(String url, String param) {
        PrintWriter out = null;
        BufferedReader in = null;
        String result = "";
        try {
            URL realUrl = new URL(url);
            // 打开和URL之间的连接
            URLConnection conn = realUrl.openConnection();
            // 设置通用的请求属性
            conn.setRequestProperty("accept", "*/*");
            conn.setRequestProperty("connection", "Keep-Alive");
            conn.setRequestProperty("user-agent",
                    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1;SV1)");
            // 发送POST请求必须设置如下两行
            conn.setDoOutput(true);
            conn.setDoInput(true);
            // 获取URLConnection对象对应的输出流
            out = new PrintWriter(conn.getOutputStream());
            // 发送请求参数
            out.print(param);
            // flush输出流的缓冲
            out.flush();
            // 定义BufferedReader输入流来读取URL的响应
            in = new BufferedReader(
                    new InputStreamReader(conn.getInputStream()));
            String line;
            while ((line = in.readLine()) != null) {
                result += line;
            }
        } catch (Exception e) {
            System.out.println("发送 POST 请求出现异常！"+e);
            e.printStackTrace();
        }
        //使用finally块来关闭输出流、输入流
        finally{
            try{
                if(out!=null){
                    out.close();
                }
                if(in!=null){
                    in.close();
                }
            }
            catch(IOException ex){
                ex.printStackTrace();
            }
        }
        return result;
    }    
}</string>

RegexMatches.java

package Matches;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class RegexMatches{
    public static String rm (String line, String pattern){
    	String sum = "";
      Pattern r = Pattern.compile(pattern);
      Matcher m = r.matcher(line);
      while (m.find()) {
      	sum += m.group();
      } 
			return sum;
   }
}

currentTime.java

package Time;
import java.util.Date;
import java.text.SimpleDateFormat;
public class currentTime{
	public static String ct() { 
	SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd-HH-mm-ss");//设置日期格式
	return df.format(new Date());// new Date()为获取当前系统时间
	}
}

test.java

import  Http.HttpRequest;
import	File.appeendFile;
import	Matches.RegexMatches;
import	Time.currentTime;
public class test{
		public static void main(String[] args){
				String httpStr = HttpRequest.sendPost(args[0],"");
				String pattern = "<div id="\'content\'">(.*)</div>";
				httpStr = (new RegexMatches()).rm(httpStr,pattern);
				pattern = "[^\\x00-\\xff]";
				httpStr = (new RegexMatches()).rm(httpStr,pattern);
				appeendFile.fw(currentTime.ct()+".txt",httpStr);
			}
	}

run.bat

java test http://www.zhuaji.org/read/2471/985093.html