日期:2014-05-16 浏览次数:20395 次
package com.zwd.text; import java.io.BufferedReader; import java.io.File; import java.io.FileOutputStream; import java.io.InputStream; import java.io.InputStreamReader; import java.io.PrintWriter; import java.net.HttpURLConnection; import java.net.URL; import java.util.Date; public class Test { private static long star = 0; private static long end = 0; private static long ttime = 0; // 返回 html 代码 public static String getHtmlCode(String httpUrl) { Date before = new Date(); star = before.getTime(); StringBuffer htmlCode = new StringBuffer(); //这里我做了改动,原文是用String,这样内存消耗会太大,原因我就不说了 try { InputStream in; URL url = new java.net.URL(httpUrl); HttpURLConnection connection = (HttpURLConnection) url.openConnection(); //抽象连接 connection = (HttpURLConnection) url.openConnection(); connection.setRequestProperty("User-Agent", "Mozilla/ 4.0");//这句很重要,预防服务器拦截我们java程序的请求,如果少了就会被弹403等错误。 connection.connect(); //连接部分完成 //======================= 华丽分界线 ================= //io读写开始 in = connection.getInputStream(); java.io.BufferedReader breader = new BufferedReader(new InputStreamReader(in, "UTF-8")); String currentLine; while ((currentLine = breader.readLine()) != null) { //以行的方式读取 htmlCode.append(currentLine); } } catch (Exception e) { e.printStackTrace(); } finally { //计算时耗 Date after = new Date(); end = after.getTime(); ttime = end - star; System.out.println(" 执行时间 :" + ttime + " 毫秒 "); } return htmlCode.toString(); } // 存储文件 这里就做详细解释了,就是把上文获取的内容保存到指定文件而已 public static synchronized void writeHtml(String filePath, String info, String flag) { PrintWriter pw = null; try { File writeFile = new File(filePath); boolean isExit = writeFile.exists(); if (isExit != true) { writeFile.createNewFile(); } else { if (!flag.equals("NO")) { writeFile.delete(); writeFile.createNewFile(); } } pw = new PrintWriter(new FileOutputStream(filePath, true)); pw.println(info); pw.close(); } catch (Exception ex) { System.out.println(ex.getMessage()); } finally { pw.close(); } } public static void main(String[] args) { String url = "http://localhost:8080/online/index.do"; //目标网站 writeHtml("d:/demo.html", getHtmlCode(url), "NO"); //目标网站静态化 } }
这些代码是我从网上搜来的,其实网上材料很多,本人觉得这个写的是最好的,所以挑他来说下,其实静态化也不难,只是用最常见的方法,对把目标文件下载,或者应该说读取出来而已,
所以关键就在于io流的应用,从代码上看,其实也很简单,我也为大家一一注释下,希望对新手有点帮助,当然后事还没完成,列子只是给大家把怎么把一个页面静态化而已,如果大家想偷懒想容器自动静态化的话,只要配合写一个定时器就行了(定时器我别的文章页介绍了,这里就不多少)
核心部分也就是这样,如果等本人有时间,我再做一个实例,上传上来,提供大家参考吧.时间嘛,待定,呵呵