##java 爬虫初体验 编译一个可以爬取网站首页html文件的小爬虫程序 并将爬取的文件保存到自定义路径中。
public class WebSpidTest { public static void main(String[] args) throws IOException { //获取URL URL url=new URL("https://music.163.com/"); //下载资源 //InputStream is =url.openStream(); HttpURLConnection conn=(HttpURLConnection) url.openConnection(); conn.setRequestMethod("GET"); conn.setRequestProperty("User-Agent","Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36"); BufferedReader br =new BufferedReader( new InputStreamReader(conn.getInputStream(),"UTF-8")); BufferedWriter bw=new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File("D:\\JavaWorld\\爬虫文件夹\\网易云首页"+new SimpleDateFormat("yyyy-MM-dd").format(new Date())+".html")))); String msg=null; while(null!=(msg=br.readLine())) { bw.write(msg); bw.newLine(); } br.close(); bw.close(); //分析 //处理 } }