searchhttpfile.java

一个java的数据挖掘程序,实现关键字的搜索分类

package search;
import java.util.*;
import java.net.*;
import java.io.*;
import java.util.regex.*;

// 搜索Web爬行者
public class SearchHTTPFile implements Runnable{



  private HashMap disallowListCache = new HashMap();
  ArrayList errorList = new ArrayList();//错误信息
  ArrayList result=new ArrayList(); //搜索到的结果
  String startUrl;//开始搜索的起点
  int maxUrl;//最大处理的url数
  String searchString;//要搜索的字符串(英文)
  boolean caseSensitive=false;//是否区分大小写
  boolean limitHost=false;//是否在限制的主机内搜索

  public SearchHTTPFile(String startUrl,int maxUrl,String searchString){
   this.startUrl=startUrl;
   this.maxUrl=maxUrl;
   this.searchString=searchString;
  }

   public ArrayList getResult(){
       return result;
   }

  public void run(){//启动搜索线程
       crawl(startUrl,maxUrl, searchString,limitHost,caseSensitive);
       display();
  }


    //检测URL格式
  private URL verifyUrl(String url) {
    // 只处理HTTP URLs.
    if (!url.toLowerCase().startsWith("http://"))
      return null;

    URL verifiedUrl = null;
    try {
      verifiedUrl = new URL(url);
    } catch (Exception e) {
      return null;
    }

    return verifiedUrl;
  }

  // 检测robot是否允许访问给出的URL.
  private boolean isRobotAllowed(URL urlToCheck) {
    String host = urlToCheck.getHost().toLowerCase();//获取给出RUL的主机

    // 获取主机不允许搜索的URL缓存
    ArrayList disallowList =(ArrayList) disallowListCache.get(host);

    // 如果还没有缓存,下载并缓存。
    if (disallowList == null) {
      disallowList = new ArrayList();
      try {
        URL robotsFileUrl =new URL("http://" + host + "/robots.txt");
        MainFrame.display("正在连接请等待...\n") ;
        BufferedReader reader =new BufferedReader(new InputStreamReader(robotsFileUrl.openStream()));
        MainFrame.display("已连接到主机\n") ;
        // 读robot文件，创建不允许访问的路径列表。
        String line;
        while ((line = reader.readLine()) != null) {
          if (line.indexOf("Disallow:") == 0) {//是否包含"Disallow:"
            String disallowPath =line.substring("Disallow:".length());//获取不允许访问路径

            // 检查是否有注释。
            int commentIndex = disallowPath.indexOf("#");
            if (commentIndex != - 1) {
              disallowPath =disallowPath.substring(0, commentIndex);//去掉注释
            }

            disallowPath = disallowPath.trim();
            disallowList.add(disallowPath);
           }
         }

        // 缓存此主机不允许访问的路径。
        disallowListCache.put(host, disallowList);
      } catch (Exception e) {
        MainFrame.display("无法连接到主机："+host+"\n") ;
//              return true;
        return false;
      }
    }


    String file = urlToCheck.getFile();
    for (int i = 0; i < disallowList.size(); i++) {
      String disallow = (String) disallowList.get(i);
      if (file.startsWith(disallow)) {
        MainFrame.display("主机不允许访问\n") ;
        return false;
      }
    }

    return true;
  }


  private String downloadPage(URL pageUrl) {
     try {
        // Open connection to URL for reading.
        MainFrame.display("准备下载数据，请等待\n") ;
        BufferedReader reader =
          new BufferedReader(new InputStreamReader(pageUrl.openStream()));

        // Read page into buffer.
        String line;
        StringBuffer pageBuffer = new StringBuffer();
        while ((line = reader.readLine()) != null) {
          pageBuffer.append(line);
        }

        return pageBuffer.toString();
     } catch (Exception e) {
       MainFrame.display("失去连接\n") ;
//       System.out.println("无法连接") ;
     }

     return null;
  }

  // 从URL中去掉"www"
  private String removeWwwFromUrl(String url) {
    int index = url.indexOf("://www.");
    if (index != -1) {
      return url.substring(0, index + 3) +
        url.substring(index + 7);
    }

    return (url);
  }
  private void display(){
    if(errorList.size()>0){
      for(int i=0;i<errorList.size();i++){
        MainFrame.display(errorList.get(i).toString());
        MainFrame.display("\n");
      }
    }
    else if(result.isEmpty()){
      MainFrame.display("搜索结果：没有找到\n");
    }
    else {
      MainFrame.display("搜索结果为(URL)：\n");
      for(int i=0;i<result.size();i++){
        MainFrame.display(result.get(i).toString());
        MainFrame.display("\n");
      }
    }


  }

  // 解析页面并找出链接
  private ArrayList retrieveLinks(URL pageUrl, String pageContents, HashSet crawledList,
    boolean limitHost)
  {
    // 用正则表达式编译链接的匹配模式。
    Pattern p =Pattern.compile("<a\\s+href\\s*=\\s*\"?(.*?)[\"|>]",Pattern.CASE_INSENSITIVE);
    Matcher m = p.matcher(pageContents);


    ArrayList linkList = new ArrayList();
    while (m.find()) {
      String link = m.group(1).trim();

      if (link.length() < 1) {
        continue;
      }

      // 跳过链到本页面内链接。
      if (link.charAt(0) == '#') {
        continue;
      }


      if (link.indexOf("mailto:") != -1) {
        continue;
      }

      if (link.toLowerCase().indexOf("javascript") != -1) {
        continue;
      }

      if (link.indexOf("://") == -1){
        if (link.charAt(0) == '/') {//处理绝对地
          link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort()+ link;
        } else {
          String file = pageUrl.getFile();
          if (file.indexOf('/') == -1) {//处理相对地址
            link = "http://" + pageUrl.getHost()+":"+pageUrl.getPort() + "/" + link;
          } else {
            String path =file.substring(0, file.lastIndexOf('/') + 1);
            link = "http://" + pageUrl.getHost() +":"+pageUrl.getPort()+ path + link;
          }
        }
      }

      int index = link.indexOf('#');
      if (index != -1) {
        link = link.substring(0, index);
      }

      link = removeWwwFromUrl(link);

      URL verifiedLink = verifyUrl(link);
      if (verifiedLink == null) {
        continue;
      }

      /* 如果限定主机，排除那些不合条件的URL*/
      if (limitHost &&
          !pageUrl.getHost().toLowerCase().equals(
            verifiedLink.getHost().toLowerCase()))
      {
        continue;
      }

      // 跳过那些已经处理的链接.
      if (crawledList.contains(link)) {
        continue;
      }

       linkList.add(link);
    }

   return (linkList);
  }

 // 搜索下载Web页面的内容，判断在该页面内有没有指定的搜索字符串

  private boolean searchStringMatches(String pageContents, String searchString, boolean caseSensitive){
       String searchContents = pageContents;
       if (!caseSensitive) {//如果不区分大小写
          searchContents = pageContents.toLowerCase();
       }


    Pattern p = Pattern.compile("[\\s]+");
    String[] terms = p.split(searchString);
    for (int i = 0; i < terms.length; i++) {
      if (caseSensitive) {
        if (searchContents.indexOf(terms[i]) == -1) {
          return false;
        }
      } else {
        if (searchContents.indexOf(terms[i].toLowerCase()) == -1) {
          return false;
        }
      }

    }

    return true;
  }


  //执行实际的搜索操作
  public ArrayList crawl(String startUrl, int maxUrls, String searchString,boolean limithost,boolean caseSensitive )
  {

    System.out.println("searchString="+searchString);
    HashSet crawledList = new HashSet();
    LinkedHashSet toCrawlList = new LinkedHashSet();

     if (maxUrls < 1) {
        errorList.add("Invalid Max URLs value.");
        System.out.println("Invalid Max URLs value.");
      }


    if (searchString.length() < 1) {
      errorList.add("Missing Search String.");
      System.out.println("Missing search String");
    }


    if (errorList.size() > 0) {
      System.out.println("err!!!");
      return errorList;
      }


    // 从开始URL中移出www
    startUrl = removeWwwFromUrl(startUrl);


    toCrawlList.add(startUrl);
    while (toCrawlList.size() > 0) {

      if (maxUrls != -1) {
        if (crawledList.size() == maxUrls) {
          break;
        }
      }


      String url = (String) toCrawlList.iterator().next();


      toCrawlList.remove(url);


      URL verifiedUrl = verifyUrl(url);
      if (!isRobotAllowed(verifiedUrl)) {
        continue;
      }


      // 增加已处理的URL到crawledList
      crawledList.add(url);
      String pageContents = downloadPage(verifiedUrl);


      if (pageContents != null && pageContents.length() > 0){
        // 从页面中获取有效的链接
        ArrayList links =retrieveLinks(verifiedUrl, pageContents, crawledList,limitHost);

        toCrawlList.addAll(links);

        if (searchStringMatches(pageContents, searchString,caseSensitive))
        {
          result.add(url);
          System.out.println(url);
        }
     }
    }
   return result;
  }

  // 主函数
  public static void main(String[] args) {
     if(args.length!=3){
        System.out.println("Usage:java SearchFile startUrl maxUrl searchString");
        return;
     }
    int max=Integer.parseInt(args[1]);
    SearchHTTPFile crawler = new SearchHTTPFile(args[0],max,args[2]);
    Thread  search=new Thread(crawler);
    System.out.println("Start searching...");
    System.out.println("result:");
    search.start();

  }
}