CVPR 2015 paper 下载

cvpr2015列表已经出来提供下载，文件太多可以用迅雷或者wget直接下载

http://www.cv-foundation.org/openaccess/CVPR2015.py

但是这样全部下载还得一个一个翻看，于是乎写了个小程序专门选则自己方向的论文。

需要htmlparser解析网页代码，下载地址http://sourceforge.net/projects/htmlparser/files/htmlparser/

还有为了方便，直接把paper网页保存在D盘了。

import java.io.BufferedReader;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.FileInputStream;
import java.io.File;
import java.net.URL;
import java.net.URLConnection;

import org.htmlparser.filters.TagNameFilter;
import org.htmlparser.nodes.TagNode;

import org.htmlparser.tags.LinkTag;
import org.htmlparser.util.NodeList;
import org.htmlparser.util.ParserException;

import org.htmlparser.Node;

import org.htmlparser.NodeFilter;
import org.htmlparser.Parser;
public class DownCVPR {

    /*
     * 建立个目录 D:/CVPR2015/Segmentation/
     * 页面保存位置
     *  String htmlName="D:\\CVPR 2015 Open Access Repository.htm";
     */
    static String saveDir="D:/CVPR2015/Segmentation/";
     public static String openFile( String szFileName ) {
            try {
                BufferedReader bis = new BufferedReader(new InputStreamReader(new FileInputStream( new File(szFileName))) );
                String szContent="";
                String szTemp;

                while ( (szTemp = bis.readLine()) != null) {
                    szContent+=szTemp+"\n";
                }
                bis.close();
                return szContent;
            }
            catch( Exception e ) {
                return "";
            }
        }

     static NodeFilter lnkFilter = new NodeFilter() {
          public boolean accept(Node node) {

           if(node instanceof LinkTag)
            return true;
           return false;
          }
         };
         private static void downloadNet(String urlString, String filename)
            {
                System.out.println("Begin to download " + urlString + "...");  

                int byteread = 0;
                try
                {
                    URL url = new URL(urlString);
                    URLConnection conn = url.openConnection();
                    InputStream inStream = conn.getInputStream();
                    FileOutputStream fs = new FileOutputStream(saveDir + filename);  

                    byte[] buffer = new byte[1204];
                    while ((byteread = inStream.read(buffer)) != -1)
                    {
                        fs.write(buffer, 0, byteread);
                    }
                    fs.flush();
                    fs.close();
                    System.out.println("Success to download file...");
                }
                catch (Exception e)
                {
                    e.printStackTrace();
                }
            }
    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub
        String htmlName="D:\\CVPR 2015 Open Access Repository.htm";
        String content=openFile(htmlName);
        String paperPath[];
        String paperName[];
        String papertype="Segmentation";
        int paperNum=0;
        try {
            Parser parser = new Parser(content);
//          AndFilter filter = new AndFilter(new TagNameFilter("div"),
//                  new HasAttributeFilter("id"));
            TagNameFilter filter=new TagNameFilter("dt");
            NodeList nodes = parser.parse(filter);
            System.out.println(nodes.size());
            paperNum=nodes.size();
            paperPath=new String[paperNum];
            paperName=new String[paperNum];
            for(int i=0;i<nodes.size();i++)
            {
                Node n=nodes.elementAt(i);
                Node cn=n.getLastChild();

                TagNode tn=new TagNode();
                tn.setText(cn.toHtml());

                //System.out.println(cn.getFirstChild().getText());
                paperName[i]=cn.getFirstChild().getText();
                paperPath[i]=tn.getAttribute("href").replaceAll(".html", ".pdf");
                paperPath[i]=paperPath[i].substring(paperPath[i].lastIndexOf("/")+1);

//              paperName[i]=path.substring(path.lastIndexOf("/")+1, path.indexOf(".html"));
//              System.out.println(paperName[i]);
            }

            String pre="http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/";
            for(int i=0;i<paperPath.length;i++){
                //String name=paperPath[i].substring(paperPath[i].lastIndexOf("/")+1, paperPath[i].indexOf(".html"));
                if(paperName[i].indexOf(papertype)>=0||paperName[i].indexOf(papertype.toLowerCase())>=0){
                    String name=name=paperPath[i].substring(paperPath[i].lastIndexOf("/")+1);
                    System.out.println(paperName[i]);
                    downloadNet(pre+paperPath[i], name) ;

                }
                else{
                    continue;
                }
                System.out.println(i);
            }

        } catch (ParserException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

    }

}