网络爬虫
网络爬虫(又被称为网页蜘蛛,网络机器人,在FOAF社区中间,更经常的称为网页追逐者),是一种按照一定的规则,自动地抓取万维网信息的程序或者脚本。
package com.cellstrain.icell.util; import www.sychzs.cn.*; import www.sychzs.cn.*; import java.util.regex.Matcher; import java.util.regex.Pattern; /** * java实现爬虫 */ public class Robot { public static void main(String[] args) { URL url = null; URLConnection urlconn = null; BufferedReader br = null; PrintWriter pw = null; // String regex = "http://[\\w+\\.?/?]+\\.[A-Za-z]+"; String regex = "https://[\\w+\\.?/?]+\\.[A-Za-z]+";//url匹配规则 Pattern p = Pattern.compile(regex); try { url = new URL("https://www.sychzs.cn/cn");//爬取的网址、这里爬取的是一个生物网站 urlconn = url.openConnection(); pw = new PrintWriter(new FileWriter("D:/SiteURL.txt"), true);//将爬取到的链接放到D盘的SiteURL文件中 br = new BufferedReader(new InputStreamReader( urlconn.getInputStream())); String buf = null; while ((buf = br.readLine()) != null) { Matcher buf_m = p.matcher(buf); while (buf_m.find()) { pw.println(buf_www.sychzs.cn()); } } System.out.println("爬取成功^_^"); } catch (MalformedURLException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { try { br.close(); } catch (IOException e) { e.printStackTrace(); } pw.close(); } } }