1000字范文 > eclipse if代码折叠_仅需一页Java代码就能实现网页源码爬取

eclipse if代码折叠_仅需一页Java代码就能实现网页源码爬取

时间：2021-06-03 03:07:56

作者|小鱼儿. yanxiao|CSDN

Java代码基于Eclipse简单实现网页源码爬取

今天给大家分享我的最新java学习进程--java网页源码爬虫，废话不多说盘代码。

仅需一页代码:

package 网站爬虫2;/** * 爬取目标网页源代码示例 * @作者 YanXiaolxy * @版本 .03 * @时间 12月14日下午1:14:14 */import java.io.BufferedWriter;import java.io.ByteArrayOutputStream;import java.io.File;import java.io.FileWriter;import java.io.InputStream;import .HttpURLConnection;import .URL;public class webHtmlCrawer {public static void main(String[] args) {newFile();}public static String getConnection() {String path = "/";try {HttpURLConnection conn = (HttpURLConnection) new URL(path).openConnection();conn.setRequestMethod("GET"); conn.setConnectTimeout(5000); if (conn.getResponseCode() == 200) {InputStream xml = conn.getInputStream();byte[] data = read(xml);//System.out.println(xml);return new String(data); }else {System.out.println("连接失败！"); }} catch (Exception e) {e.printStackTrace();}return null;}//读取数据流,转换为字符串 public static byte[] read(InputStream xml) throws Exception { ByteArrayOutputStream outputStream = new ByteArrayOutputStream(); byte[] buffer = new byte[1024]; int len = 0; while ((len = xml.read(buffer)) != -1) { outputStream.write(buffer, 0, len); } xml.close(); return outputStream.toByteArray(); } public static void newFile() { String html = getConnection(); String dir = "D:/javafile/";//定义创建目录位置 File contents = new File(dir); contents.mkdirs();//创建文件目录 try { byte bytes[] = {1, 2, 3, 4}; File file = new File("D:/javafile/test.txt"); //判断文件是否存在，如果不存在就创建 if (!file.exists()) {file.createNewFile(); } FileWriter fw = new FileWriter(file.getAbsoluteFile()); BufferedWriter bw = new BufferedWriter(fw); System.out.println("正在写入....."); bw.write(html); bw.close(); System.out.println("录入完毕"); } catch (Exception e) { e.getStackTrace(); } } }