JAVA课程设计

基于学院网站的搜索引擎

对学院网站进行抓取、建索（需要中文分词）、排序（可选）、搜索、摘要显示。可以是GUI界面，也可以是Web界面。

一、团队介绍

二、项目git地址

码云地址

三、项目git提交记录截图

四、项目主要使用技术

Httplcient

Jsoup

多线程

数据库dao模式

IKAnanyzer

Lucene

Javascript /jQuery

Bootstrap

Web

五、项目其余特点

容错处理完善

界面美观

有配置文件

数据量大的时候查询速度依旧快

六、项目功能架构图与主要功能流程图

七、项目运行截图

八、项目关键代码

        try {
            Document doc=Jsoup.connect("http://cec.jmu.edu.cn/").get();
            Elements links = doc.select(".menu0_0_");  
            for (Element link : links) {  
                lis1.add(oriurl+link.attr("href"));
            }  
        } catch (IOException e1) {
            e1.printStackTrace();
        }

      try {
            CloseableHttpResponse response = httpClient.execute(httpget, context);
            try {
                HttpEntity entity = response.getEntity();
                Document doc=Jsoup.parse(EntityUtils.toString(entity,"utf8"));
                Elements links=doc.select(".c124907");    
                for (Element link : links) {  
                    lis1.add(url +link.attr("href"));
                }   
                String pattern ="\\?a2t=([0-9]{1,})&a2p=[0-9]{1,}&a2c=10&urltype=tree.TreeTempUrl&wbtreeid=([0-9]{1,})";  
                Elements links1=doc.select("a[href]"); 
                for (Element link1 : links1) {
                    String line=link1.attr("href");
                    Pattern r = Pattern.compile(pattern);
                    Matcher m = r.matcher(line);
                    int i=0;
                    if (m.find( )) {
//                       System.out.println("Found value: " + m.group(0) );
                        int j=Integer.parseInt(m.group(1));
                        if(j>7){
                            for(int k=1;k<j+1;k++){
                                lis.add("?a2t="+String.valueOf(j)+"&a2p="+String.valueOf(k)+"&a2c=10&urltype=tree.TreeTempUrl&wbtreeid="+m.group(2));
                                }
                            }
                        else{
                        lis.add(m.group(0));
                        }

       CloseableHttpResponse response = httpClient.execute(httpget, context);
            try {
                HttpEntity entity = response.getEntity();
                Document doc=Jsoup.parse(EntityUtils.toString(entity,"utf8"));
                Elements links=doc.select(".c124907");    
                for (Element link : links) {         
                    lis.add(link.attr("href"));
                    
                }  

            try {
                HttpEntity entity = response.getEntity();
                Document doc=Jsoup.parse(EntityUtils.toString(entity,"utf8"));
                String title = doc.select(".contentstyle124904").text(); 

 Crawl crawl=new Crawl(httpget.getURI().toString(),doc.title().toString(),title);
                CrawlDaoImpl test=new CrawlDaoImpl();
                try {
                    if(bool){
                    test.add(crawl);
                    System.out.println(httpget.toString()+"添加成功");
                    }
                    
                    else{
                        System.out.println("添加失败");

jdbc.url=jdbc:mysql://localhost:3306/test
jdbc.username=root
jdbc.password=root
jdbc.driver=com.mysql.jdbc.Driver

    @Override
    public Crawl findById(int id) throws SQLException {
        Connection conn = null;
        PreparedStatement ps = null;
        ResultSet rs = null;
        Crawl p = null;
        String sql = "select url,abs,description from crawl where id=?";
        try{
            conn = DBUtils.getConnection();
            ps = conn.prepareStatement(sql);
            ps.setInt(1, id);
            rs = ps.executeQuery();
            if(rs.next()){
                p = new Crawl();
                p.setId(id);
                p.setUrl(rs.getString(1));
                p.setAbs(rs.getString(2));
                p.setDescription(rs.getString(3));
            }
        }catch(SQLException e){
            e.printStackTrace();
            throw new SQLException("*");
        }finally{
            DBUtils.close(rs, ps, conn);
        }
        return p;
    }

public class IndexManager {
    @Test
    public void createIndex() throws Exception {
        // 采集数据
        CrawlDao dao = new CrawlDaoImpl();
        List<Crawl> list = dao.findAll();
        // 将采集到的数据封装到Document对象中
        List<Document> docList = new ArrayList();
        Document document;
        for (Crawl crawl : list) {
            document = new Document();
            // store:如果是yes，则说明存储到文档域中
            Field id = new IntField("id", crawl.getId(), Store.YES);
            Field url = new StoredField("url", crawl.getUrl());
            Field abs = new StoredField("abs", crawl.getAbs());
            Field description = new TextField("description",
                    crawl.getDescription(), Store.YES);
            document.add(id);
            document.add(url);
            document.add(abs);
            document.add(description);
            docList.add(document);
        }
        // 创建分词器，标准分词器
        // Analyzer analyzer = new StandardAnalyzer();
        // 使用ikanalyzer
        Analyzer analyzer = new IKAnalyzer();
        // 创建IndexWriter
        IndexWriterConfig cfg = new IndexWriterConfig(Version.LUCENE_4_10_3,
                analyzer);
        // 指定索引库的地址
        File indexFile = new File("C:\\test1\\aaa\\");
        Directory directory = FSDirectory.open(indexFile);
        IndexWriter writer = new IndexWriter(directory, cfg);
        // 通过IndexWriter对象将Document写入到索引库中
        for (Document doc : docList) {
            writer.addDocument(doc);
        }
        writer.close();
    }

public class IndexSearch {
    
    List<Crawl> lis1=new ArrayList();
    public List doSearch(Query query) throws InvalidTokenOffsetsException {
        // 创建IndexSearcher
        // 指定索引库的地址
        try {
            File indexFile = new File("C:\\test1\\aaa\\");
            Directory directory = FSDirectory.open(indexFile);
            IndexReader reader = DirectoryReader.open(directory);
            IndexSearcher searcher = new IndexSearcher(reader);
            // 通过searcher来搜索索引库
            // 第二个参数：指定需要显示的顶部记录的N条
            TopDocs topDocs = searcher.search(query, 20);
            // 根据查询条件匹配出的记录总数
            int count = topDocs.totalHits;
//          ScoreDoc[] scoreDocs = topDocs.scoreDocs;
            String filed="description";  
//          TopDocs top=searcher.search(query, 100);  
            QueryScorer score=new QueryScorer(query,filed);//传入评分  
            SimpleHTMLFormatter fors=new SimpleHTMLFormatter("<span style=\"color:red;\">", "</span>");//定制高亮标签  
            Highlighter  highlighter=new Highlighter(fors,score);//高亮分析器  
//           highlighter.setMaxDocCharsToAnalyze(10);//设置高亮处理的字符个数  
            for(ScoreDoc sd:topDocs.scoreDocs){  
                Document doc=searcher.doc(sd.doc);  
                String description=doc.get(filed);  
           //Lucene中分词的所有信息我们都可以从TokenStream流中获取.  
                TokenStream token=TokenSources.getAnyTokenStream(searcher.getIndexReader(), sd.doc, "description", new IKAnalyzer(true));//获取tokenstream  
                Fragmenter  fragment=new SimpleSpanFragmenter(score);  //根据这个评分新建一个对象     
                highlighter.setTextFragmenter(fragment);  //必须选取最合适的    
                highlighter.setTextFragmenter(new SimpleFragmenter());//设置每次返回的字符数 
                String str=highlighter.getBestFragment(token, description);//获取高亮的片段，可以对其数量进行限制  
                Crawl crawl = new Crawl();
                crawl.setDescription(str);
                crawl.setAbs(doc.get("abs"));
                crawl.setUrl(doc.get("url"));
                lis1.add(crawl);
            }       
            reader.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return lis1;
        
    }
    

<div id="test"> <img src="./img/logo.png" height="300" width="250"/></div>

    <form action="./query2.jsp" method="GET">
        <div class="search-wrapper">
            <div class="input-holder">
                <input type="text" class="search-input" placeholder="" name="name"/>
                <button class="search-icon" onclick="searchToggle(this, event);"><span></span></button>
            </div>
            <span class="close" onclick="searchToggle(this, event);"></span>
            <div class="result-container">

            </div>
        </div>
    </form>

<script src="js/jquery-1.11.0.min.js" type="text/javascript"></script>
<script type="text/javascript">
    function searchToggle(obj, evt){
        var container = $(obj).closest('.search-wrapper');

        if(!container.hasClass('active')){
              container.addClass('active');
              evt.preventDefault();
        }
        else if(container.hasClass('active') && $(obj).closest('.input-holder').length == 0){
              container.removeClass('active');
        
              container.find('.search-input').val('');
        
              container.find('.result-container').fadeOut(100, function(){$(this).empty();});
        }
    }

    function submitFn(obj, evt){
        value = $(obj).find('.search-input').val().trim();

        _html = "Yup yup! Your search text sounds like this: ";
        if(!value.length){
            _html = "Yup yup! Add some text friend :D";
        }
        else{
            _html += "<b>" + value + "</b>";
        }

        $(obj).find('.result-container').html('<span>' + _html + '</span>');
        $(obj).find('.result-container').fadeIn(100);

        evt.preventDefault();
    }
</script>

<script type="text/javascript">


$(function(){
    var Count = "<%=i %>";//记录条数
    var tmp = "<%=test %>";
    var PageSize=5;//设置每页示数目
    var PageCount=Math.ceil(Count/PageSize);//计算总页数
    var currentPage =1;//当前页，默认为1。
    //造个简单的分页按钮
    for(var i=1;i<=PageCount;i++){
        if(PageCount==1){
        }//如果页数为1的话，那么我们就是不分页

        else{
        var pageN='<li style=\"font-size:30px\"><a href="?name='+tmp+'&a='+i+'">'+i+'</a></li>';
        
        $('.pagination').append(pageN);
    }

    }
    
    //显示默认页（第一页）

});  
</script>

<%

String d =request.getParameter("a");    
//out.print(d+"<br>");
int b=0;
int k=0;
if(i!=0&&d==null){
    for(Crawl crawl: lis){
        if(5>k&&k>=0){
            out.print("<h3><p class=\"text-center\"><a href=\""+crawl.getUrl()+"\">"+crawl.getAbs()+"</a></p></h3>"); 
            out.print("<p class=\"text-center\">"+crawl.getDescription()+"<br>");  
            out.print("<br>");
        }
        k=k+1;
    }
    
    
}
else{
if(d!=null){
int c=Integer.valueOf(d);
//out.print(c);
for(Crawl crawl: lis){
    if(c*5>b&&b>=(c-1)*5){
        if(crawl.getDescription()==null){
            out.print("");
        }
        else{
            out.print("<h3><p class=\"text-center\"><a href=\""+crawl.getUrl()+"\">"+crawl.getAbs()+"</a></p></h3>"); 
            out.print("<p class=\"text-center\">"+crawl.getDescription()+"<br>"); 
        out.print("<br>");

        }
    }
    b=b+1;  
}
}
}
%>

尚待改进或者新的想法

变量的命名不太规范

可以尝试着去做一个只有修改部分参数，就可以去爬取别的网站的搜索引擎

团队成员任务分配