[url]http://www.klstudio.com/post/103.html[/url]
[code]
package com.klstudio.util;
import java.io.*;
import java.net.*;
public class Tools {
final static Object lock = new Object();
public static void makeHtml(String page, String filePath){
makeHtml(page,filePath,"UTF-8");
}
public static void makeHtml(String page, String filePath,String chartset) {
synchronized (lock) {
HttpURLConnection huc = null;
BufferedReader br = null;
BufferedWriter bw = null;
try {
huc = (HttpURLConnection)new URL(page).openConnection();
System.setProperty("sun.net.client.defaultConnectTimeout", "30000");
System.setProperty("sun.net.client.defaultReadTimeout", "30000");
huc.connect();
InputStream stream = huc.getInputStream();
bw = new BufferedWriter(new OutputStreamWriter (new FileOutputStream(filePath),chartset));
br = new BufferedReader(new InputStreamReader(stream, chartset));
String line;
while((line = br.readLine())!= null){
if(line.trim().length() > 0){
bw.write(line);
bw.newLine();
}
}
}catch (Exception e) {
e.printStackTrace();
}finally {
try {
br.close();
bw.close();
huc.disconnect();
}catch (Exception e) {
e.printStackTrace();
}
}
}
}
[/code]
[url=http://www.chinab2c.net/content/71.html]网上超市平台系统技术解决方案[/url]
[code]
package com.klstudio.util;
import java.io.*;
import java.net.*;
public class Tools {
final static Object lock = new Object();
public static void makeHtml(String page, String filePath){
makeHtml(page,filePath,"UTF-8");
}
public static void makeHtml(String page, String filePath,String chartset) {
synchronized (lock) {
HttpURLConnection huc = null;
BufferedReader br = null;
BufferedWriter bw = null;
try {
huc = (HttpURLConnection)new URL(page).openConnection();
System.setProperty("sun.net.client.defaultConnectTimeout", "30000");
System.setProperty("sun.net.client.defaultReadTimeout", "30000");
huc.connect();
InputStream stream = huc.getInputStream();
bw = new BufferedWriter(new OutputStreamWriter (new FileOutputStream(filePath),chartset));
br = new BufferedReader(new InputStreamReader(stream, chartset));
String line;
while((line = br.readLine())!= null){
if(line.trim().length() > 0){
bw.write(line);
bw.newLine();
}
}
}catch (Exception e) {
e.printStackTrace();
}finally {
try {
br.close();
bw.close();
huc.disconnect();
}catch (Exception e) {
e.printStackTrace();
}
}
}
}
[/code]
[url=http://www.chinab2c.net/content/71.html]网上超市平台系统技术解决方案[/url]
本文介绍了一个使用Java编写的网页抓取工具,该工具通过HttpURLConnection获取网页内容,并将其保存到指定文件路径下。支持设置连接及读取超时时间,并能够指定字符集。
248

被折叠的 条评论
为什么被折叠?



