public class LinkQueue {
 // 已訪問(wèn)的 url 集合
 private static Set visitedUrl = new HashSet();
 // 待訪問(wèn)的 url 集合
 private static Queue unVisitedUrl = new PriorityQueue();

 // 獲得URL隊(duì)列
 public static Queue getUnVisitedUrl() {
  return unVisitedUrl;
 }

 // 添加到訪問(wèn)過(guò)的URL隊(duì)列中
 public static void addVisitedUrl(String url) {
  visitedUrl.add(url);
 }

 // 移除訪問(wèn)過(guò)的URL
 public static void removeVisitedUrl(String url) {
  visitedUrl.remove(url);
 }

 // 未訪問(wèn)的URL出隊(duì)列
 public static Object unVisitedUrlDeQueue() {
  return unVisitedUrl.poll();
 }

 // 保證每個(gè) url 只被訪問(wèn)一次
 public static void addUnvisitedUrl(String url) {
  if (url != null && !url.trim().equals("") && !visitedUrl.contains(url)
    && !unVisitedUrl.contains(url))
   unVisitedUrl.add(url);
 }

 // 獲得已經(jīng)訪問(wèn)的URL數(shù)目
 public static int getVisitedUrlNum() {
  return visitedUrl.size();
 }

 // 判斷未訪問(wèn)的URL隊(duì)列中是否為空
 public static boolean unVisitedUrlsEmpty() {
  return unVisitedUrl.isEmpty();
 }

}

import java.io.DataOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import org.apache.commons.httpclient.DefaultHttpMethodRetryHandler;
import org.apache.commons.httpclient.HttpClient;
import org.apache.commons.httpclient.HttpException;
import org.apache.commons.httpclient.HttpStatus;
import org.apache.commons.httpclient.methods.GetMethod;
import org.apache.commons.httpclient.params.HttpMethodParams;

public class DownLoadFile {
 /**
  * 根據(jù) url 和網(wǎng)頁(yè)類型生成需要保存的網(wǎng)頁(yè)的文件名 去除掉 url 中非文件名字符
  */
 public String getFileNameByUrl(String url, String contentType) {
  // remove http://
  url = url.substring(7);
  // text/html類型
  if (contentType.indexOf("html") != -1) {
   url = url.replaceAll("[\\?/:*|<>\"]", "_") + ".html";
   return url;
  }
  // 如application/pdf類型
  else {
   return url.replaceAll("[\\?/:*|<>\"]", "_") + "."
     + contentType.substring(contentType.lastIndexOf("/") + 1);
  }
 }

 /**
  * 保存網(wǎng)頁(yè)字節(jié)數(shù)組到本地文件 filePath 為要保存的文件的相對(duì)地址
  */
 private void saveToLocal(byte[] data, String filePath) {
  try {
   DataOutputStream out = new DataOutputStream(new FileOutputStream(
     new File(filePath)));
   for (int i = 0; i < data.length; i++)
    out.write(data[i]);
   out.flush();
   out.close();
  } catch (IOException e) {
   e.printStackTrace();
  }
 }

 /* 下載 url 指向的網(wǎng)頁(yè) */
 public String downloadFile(String url) {
  String filePath = null;
  /* 1.生成 HttpClinet 對(duì)象并設(shè)置參數(shù) */
  HttpClient httpClient = new HttpClient();
  // 設(shè)置 Http 連接超時(shí) 5s
  httpClient.getHttpConnectionManager().getParams()
    .setConnectionTimeout(5000);

  /* 2.生成 GetMethod 對(duì)象并設(shè)置參數(shù) */
  GetMethod getMethod = new GetMethod(url);
  // 設(shè)置 get 請(qǐng)求超時(shí) 5s
  getMethod.getParams().setParameter(HttpMethodParams.SO_TIMEOUT, 5000);
  // 設(shè)置請(qǐng)求重試處理
  getMethod.getParams().setParameter(HttpMethodParams.RETRY_HANDLER,
    new DefaultHttpMethodRetryHandler());

  /* 3.執(zhí)行 HTTP GET 請(qǐng)求 */
  try {
   int statusCode = httpClient.executeMethod(getMethod);
   // 判斷訪問(wèn)的狀態(tài)碼
   if (statusCode != HttpStatus.SC_OK) {
    System.err.println("Method failed: "
      + getMethod.getStatusLine());
    filePath = null;
   }

   /* 4.處理 HTTP 響應(yīng)內(nèi)容 */
   byte[] responseBody = getMethod.getResponseBody();// 讀取為字節(jié)數(shù)組
   // 根據(jù)網(wǎng)頁(yè) url 生成保存時(shí)的文件名
   filePath = "f:\\spider\\"
     + getFileNameByUrl(url,
       getMethod.getResponseHeader("Content-Type")
         .getValue());
   saveToLocal(responseBody, filePath);
  } catch (HttpException e) {
   // 發(fā)生致命的異常，可能是協(xié)議不對(duì)或者返回的內(nèi)容有問(wèn)題
   System.out.println("Please check your provided http address!");
   e.printStackTrace();
  } catch (IOException e) {
   // 發(fā)生網(wǎng)絡(luò)異常
   e.printStackTrace();
  } finally {
   // 釋放連接
   getMethod.releaseConnection();
  }
  return filePath;
 }
}

import java.util.HashSet;
import java.util.Set;
import org.htmlparser.Node;
import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
import org.htmlparser.filters.NodeClassFilter;
import org.htmlparser.filters.OrFilter;
import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

public class HtmlParserTool {
 // 獲取一個(gè)網(wǎng)站上的鏈接,filter 用來(lái)過(guò)濾鏈接
 public static Set<String> extracLinks(String url, LinkFilter filter) {

  Set<String> links = new HashSet<String>();
  try {
   Parser parser = new Parser(url);
   //parser.setEncoding("utf-8");
   // 過(guò)濾 <frame >標(biāo)簽的 filter，用來(lái)提取 frame 標(biāo)簽里的 src 屬性所表示的鏈接
   NodeFilter frameFilter = new NodeFilter() {
    public boolean accept(Node node) {
     if (node.getText().startsWith("frame src=")) {
      return true;
     } else {
      return false;
     }
    }
   };
   // OrFilter 來(lái)設(shè)置過(guò)濾 <a> 標(biāo)簽，和 <frame> 標(biāo)簽
   OrFilter linkFilter = new OrFilter(new NodeClassFilter(
     LinkTag.class), frameFilter);
   // 得到所有經(jīng)過(guò)過(guò)濾的標(biāo)簽
   NodeList list = parser.extractAllNodesThatMatch(linkFilter);
   for (int i = 0; i < list.size(); i++) {
    Node tag = list.elementAt(i);
    if (tag instanceof LinkTag)// <a> 標(biāo)簽
    {
     LinkTag link = (LinkTag) tag;
     String linkUrl = link.getLink();// url
     if (filter.accept(linkUrl))
      links.add(linkUrl);
    } else// <frame> 標(biāo)簽
    {
     // 提取 frame 里 src 屬性的鏈接如 <frame src="test.html"/>
     String frame = tag.getText();
     int start = frame.indexOf("src=");
     frame = frame.substring(start);
     int end = frame.indexOf(" ");
     if (end == -1)
      end = frame.indexOf(">");
     String frameUrl = frame.substring(5, end - 1);
     if (filter.accept(frameUrl))
      links.add(frameUrl);
    }
   }
  } catch (ParserException e) {
   e.printStackTrace();
  }
  return links;
 }
}

import java.util.Set;

public class MyCrawler {
 /**
  * 使用種子初始化 URL 隊(duì)列
  *
  * @return
  * @param seeds
  *            種子URL
  */
 private void initCrawlerWithSeeds(String[] seeds) {
  for (int i = 0; i < seeds.length; i++)
   LinkQueue.addUnvisitedUrl(seeds[i]);
 }

 /**
  * 抓取過(guò)程
  *
  * @return
  * @param seeds
  */
 public void crawling(String[] seeds) { // 定義過(guò)濾器，提取以http://www.lietu.com開(kāi)頭的鏈接
  LinkFilter filter = new LinkFilter() {
   public boolean accept(String url) {
    if (url.startsWith("http://www.baidu.com"))
     return true;
    else
     return false;
   }
  };
  // 初始化 URL 隊(duì)列
  initCrawlerWithSeeds(seeds);
  // 循環(huán)條件：待抓取的鏈接不空且抓取的網(wǎng)頁(yè)不多于1000
  while (!LinkQueue.unVisitedUrlsEmpty()
    && LinkQueue.getVisitedUrlNum() <= 1000) {
   // 隊(duì)頭URL出隊(duì)列
   String visitUrl = (String) LinkQueue.unVisitedUrlDeQueue();
   if (visitUrl == null)
    continue;
   DownLoadFile downLoader = new DownLoadFile();
   // 下載網(wǎng)頁(yè)
   downLoader.downloadFile(visitUrl);
   // 該 url 放入到已訪問(wèn)的 URL 中
   LinkQueue.addVisitedUrl(visitUrl);
   // 提取出下載網(wǎng)頁(yè)中的 URL
   Set<String> links = HtmlParserTool.extracLinks(visitUrl, filter);
   // 新的未訪問(wèn)的 URL 入隊(duì)
   for (String link : links) {
    LinkQueue.addUnvisitedUrl(link);
   }
  }
 }

 // main 方法入口
 public static void main(String[] args) {
  MyCrawler crawler = new MyCrawler();
  crawler.crawling(new String[] { "http://www.baidu.com" });
 }

}