資源簡介
實驗課的項目,爬蟲爬取網站內容,lucene實現索引和搜索功能,界面也很美觀。爬取的是重慶大學新聞網的內容。
代碼片段和文件信息
package?com.eguil.model;
public?class?Constant
{
public?static?int?NEWS_TYPE_CDKY?=?0;
public?static?int?NEWS_TYPE_CDXS?=?1;
public?static?int?NEWS_TYPE_CDJX?=?2;
public?static?int?NEWS_TYPE_ZSJY?=?3;
public?static?int?NEWS_TYPE_OTHERS?=?4;
public?static?String?NEWS_URL_CDKY?=?“http://news.cqu.edu.cn/news/article/list.php?catid=46“;
public?static?String?NEWS_URL_CDXS?=?“http://news.cqu.edu.cn/news/article/list.php?catid=47“;
public?static?String?NEWS_URL_CDJX?=?“http://news.cqu.edu.cn/news/article/list.php?catid=48“;
public?static?String?NEWS_URL_ZSJY?=?“http://news.cqu.edu.cn/news/article/list.php?catid=53“;
public?static?String?typeToString(int?type)
{
switch?(type)
{
case?0:
return?“重大科研“;
case?1:
return?“重大學術“;
case?2:
return?“重大教學“;
case?3:
return?“招生就業“;
default:
return?“其他“;
}
}
public?static?int?stringToType(String?type)
{
switch?(type)
{
case??“重大科研“:
return?0;
case?“重大學術“:
return?1;
case?“重大教學“:
return?2;
case?“招生就業“:
return?3;
default:
return?4;
}
}
public?static?String?getUrlOfType(int?type)
{
switch?(type)
{
case?0:
return?Constant.NEWS_URL_CDKY;
case?1:
return?Constant.NEWS_URL_CDXS;
case?2:
return?Constant.NEWS_URL_CDJX;
case?3:
return?Constant.NEWS_URL_ZSJY;
default:
return?““;
}
}
public?static?int?getTypeOfUrl(String?url)
{
if(url.equals(Constant.NEWS_URL_CDKY))
return?0;
else?if(url.equals(Constant.NEWS_URL_CDXS))
return?1;
else?if(url.equals(Constant.NEWS_URL_CDJX))
return?2;
else?if(url.equals(Constant.NEWS_URL_ZSJY))
return?3;
else?
return?-1;
}
}
?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----
?????文件???????1251??2015-11-26?22:30??CquNews\.classpath
?????文件???????1040??2015-11-22?12:02??CquNews\.project
?????文件????????567??2015-11-22?12:02??CquNews\.settings\.jsdtscope
?????文件????????116??2015-11-26?22:19??CquNews\.settings\org.eclipse.core.resources.prefs
?????文件????????364??2015-11-22?12:02??CquNews\.settings\org.eclipse.jdt.core.prefs
?????文件????????473??2015-11-22?12:02??CquNews\.settings\org.eclipse.wst.common.component
?????文件????????305??2015-11-22?12:02??CquNews\.settings\org.eclipse.wst.common.project.facet.core.xm
?????文件?????????49??2015-11-22?12:02??CquNews\.settings\org.eclipse.wst.jsdt.ui.superType.container
?????文件??????????6??2015-11-22?12:02??CquNews\.settings\org.eclipse.wst.jsdt.ui.superType.name
?????文件???????1934??2015-12-12?10:45??CquNews\build\classes\com\eguil\model\Constant.class
?????文件???????2149??2015-12-12?10:45??CquNews\build\classes\com\eguil\model\NewsItem.class
?????文件???????5574??2015-12-12?10:45??CquNews\build\classes\com\eguil\myspider\MySpider.class
?????文件???????5207??2015-12-12?11:21??CquNews\build\classes\com\gnoroul\lucenehelper\LuceneHelper.class
?????文件???????1783??2015-11-25?20:39??CquNews\src\com\eguil\model\Constant.java
?????文件???????1483??2015-11-25?20:39??CquNews\src\com\eguil\model\NewsItem.java
?????文件???????5339??2015-11-30?12:48??CquNews\src\com\eguil\myspider\MySpider.java
?????文件???????4234??2015-12-12?11:21??CquNews\src\com\gnoroul\lucenehelper\LuceneHelper.java
?????文件?????117305??2015-11-26?19:24??CquNews\WebContent\css\bootstrap.min.css
?????文件??????23739??2015-11-26?19:24??CquNews\WebContent\css\font-awesome.min.css
?????文件??????16904??2015-11-26?20:57??CquNews\WebContent\css\templatemo-st
?????文件????????322??2015-11-30?13:47??CquNews\WebContent\data\segments_d
?????文件??????????0??2015-11-29?18:47??CquNews\WebContent\data\write.lock
?????文件????1860946??2015-11-30?05:41??CquNews\WebContent\data\_a.fdt
?????文件????????962??2015-11-30?05:41??CquNews\WebContent\data\_a.fdx
?????文件????????327??2015-11-30?05:41??CquNews\WebContent\data\_a.fnm
?????文件??????40667??2015-11-30?05:41??CquNews\WebContent\data\_a.nvd
?????文件?????????88??2015-11-30?05:41??CquNews\WebContent\data\_a.nvm
?????文件????????490??2015-11-30?05:41??CquNews\WebContent\data\_a.si
?????文件?????624033??2015-11-30?05:41??CquNews\WebContent\data\_a_Lucene50_0.doc
?????文件?????320767??2015-11-30?05:41??CquNews\WebContent\data\_a_Lucene50_0.pos
............此處省略57個文件信息
- 上一篇:DLOG4J JAVAEE多用戶博客
- 下一篇:java做的個人記帳本
評論
共有 條評論