java之爬虫

标签：爬虫

import java.io.BufferedReader;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import javax.swing.plaf.synth.SynthSpinnerUI;

public class study {
    private static List<String> waitforUrl=new ArrayList<>();//存储抓取出来的url,等待爬
    private static Set<String> goforUrl=new HashSet<>();//存储爬过的url
    private static Map<String,Integer> allUrldepth=new HashMap<>();//对所有url进行爬去深度判断
    private static int Maxdepth=2;
    public static void main(String[] args) {

        String urlstr="............";
        study.gourl(urlstr, 1);

    }

    public static void gourl(String urlstr,int depath) {
        if(!(goforUrl.contains(urlstr)||depath>Maxdepth)) {
            goforUrl.add(urlstr);
            try {
                URL url=new URL(urlstr);
                URLConnection urlConn=url.openConnection();//建立url链接
                InputStream is=urlConn.getInputStream();//通过链接获取页面内容，为字节流
                InputStreamReader isr=new InputStreamReader(is,"utf-8");//将字节流转化为字符流
                BufferedReader br=new BufferedReader(isr);//读取字节流

                StringBuffer sb=new StringBuffer();//实例化StringBuffer用来存储读取数据
                String line=null;

                while((line=br.readLine())!=null) {
                    sb.append(line);
                    //System.out.println(line);
                    Pattern p = Pattern.compile("<a .*href=.+</a>");
                    Matcher m=p.matcher(line);
                    while(m.find()) {
                        String href=m.group();
                        href=href.substring(href.indexOf("href="));
                        if(href.charAt(5)==‘\"‘||href.charAt(5)==‘\‘‘){
                            href=href.substring(6);
                          }else{
                            href=href.substring(5);
                          }
                        try {
                        href=href.substring(0,href.indexOf("\""));
                        }catch(Exception e) {
                            href=href.substring(0,href.indexOf("\‘"));
                        }
                        waitforUrl.add(href);
                        allUrldepth.put(href, depath+1);
                    }
                }

                is.close();//关闭输出流
                isr.close();//关闭字节流读取
                br.close();
                System.out.println(urlstr);
                System.out.println("链接总数："+waitforUrl.size()+",已爬去链接数："+goforUrl.size());

            }catch(Exception e){
                 e.printStackTrace();
            }
                    //用递归的方法继续爬取其他链接
            String nexturl=waitforUrl.get(0);
            waitforUrl.remove(0);
            gourl(nexturl,allUrldepth.get(nexturl));
        }//else是如果存在重复链接时继续爬
        else {
            String nexturl=waitforUrl.get(0);
            waitforUrl.remove(0);
            gourl(nexturl,allUrldepth.get(nexturl));
        }
    }

}

java之爬虫

标签：爬虫

原文地址：http://blog.51cto.com/12390959/2124580