�Q�d��创］java解析非结构化文本 doc xls pdf ppt xml html

Thu, 22 Oct 2009 02:55:00 GMT

在开��g��Q�經帔R��到需要用去解析各�c�非�l�构化文本，像doc,xls,pdf,ppt,xml,html.
本�h在开發站内搜索时�Q�需要加入对各类文�g�c�d��的支持，以方便徏立烦引。解析各�c�L��档调用了几個开源的包。像dom4j-1.6.1.jar�Q�FontBox-0.1.0-dev.jar�Q�htmllexer.jar�Q�htmlparser.jar�Q�PDFBox-0.7.3.jar�Q�poi-3.5-FINAL-20090928.jar�Q�poi-scratchpad-3.5-FINAL-20090928.jar。这些开源的包可以讓我們很方便去解析各�c�非�l�构化文本�?br />
jar包的下蝲地址�Q?nbsp;http://www.ziddu.com/download/7017588/devlib.rar.html

代码如下�Q?br />

package com.ducklyl;

import java.io.File;
import java.io.FileInputStream;
import java.util.Iterator;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.htmlparser.Parser;
import org.htmlparser.filters.*;

import org.htmlparser.*;
import org.htmlparser.nodes.TextNode;
import org.htmlparser.util.*;

import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.pdmodel.PDDocument;
import org.pdfbox.util.PDFTextStripper;

public class HandleFile {
    public static void main(String args[]){
        String str="e:\\test.HTML";
        System.out.println(handleFile(str));
    }

    public static String handleFile(String filename){
        String result="";
        String fileType=filename.substring(filename.lastIndexOf(".")+1, filename.length());
        if(fileType.equalsIgnoreCase("pdf"))
            result=handlePdf(filename);
        else if(fileType.equalsIgnoreCase("xls"))
            result=handleExcel(filename);
        else if(fileType.equalsIgnoreCase("doc"))
            result=handleDoc(filename);
        else if(fileType.equalsIgnoreCase("xml"))
            result=handleXml(filename);
        else if(fileType.equalsIgnoreCase("ppt"))
            result=handlePPT(filename);
        else if(fileType.equalsIgnoreCase("htm")||fileType.equalsIgnoreCase("html"))
            result=handleHtml(filename);
        return result;
    }
/**
* 解析HTML
* @param filename
* @return
*/
    public static String handleHtml(String filename){
        String content="";
        try{
            File file=new File(filename);
            if(!file.exists()) return content;

            Parser parser=new Parser(filename);
            parser.setEncoding("UTF-8");
            NodeFilter textFilter=new NodeClassFilter(TextNode.class);
            NodeList nodes=parser.extractAllNodesThatMatch(textFilter);
            for(int i=0;i<nodes.size();i++){
                TextNode textnode=(TextNode)nodes.elementAt(i);
                String line=textnode.toPlainTextString().trim();
                if(line.equals("")) continue;
                content=content+line;
            }
        }catch(Exception e){
            e.printStackTrace();
        }
        return content;
    }
    /**
     * 解析PPT
     * @param filename
     * @return
     */
    public static String handlePPT(String filename){
        StringBuffer content = new StringBuffer("");
        try{
            File file=new File(filename);
            if(!file.exists()) {
                return content.toString();
            }
            FileInputStream instream=new FileInputStream(file);
            SlideShow ppt = new SlideShow(instream);
            Slide[] slides = ppt.getSlides();
            for(int i=0;i<slides.length;i++){
                TextRun[] t = slides[i].getTextRuns();//��Z��取得�qȝ��片的文字内容�Q�徏立TextRun
                for(int j=0;j<t.length;j++){
                    content.append(t[j].getText());//�q�里会将文字内容加到content中去
                }
                content.append(slides[i].getTitle());
            }
        }catch(Exception e){
            e.printStackTrace();
        }
        return content.toString();
    }
    /**
     * 解析XML
     * @param filename
     * @return
     */
    public static String handleXml(String filename){
        String content="",value="",text="";
        try{
            File file=new File(filename);
            if(!file.exists()) {
                return content;
            }
              SAXReader saxReader = new SAXReader();
              Document document = saxReader.read(file);
              Element root = document.getRootElement() ;

              Iterator iter=root.elementIterator() ;
               while(iter.hasNext()){
                  Element element=(Element)iter.next();
                  value=element.getStringValue();
                  if(!value.trim().equals(""))    content=content+value;
               }
        }catch(Exception e){
                e.printStackTrace();
        }
        return content;
    }
    /**
     * 解析DOC
     * @param filename
     * @return
     */
    public static String handleDoc(String filename){
        String content="";
        try{
            File file=new File(filename);
            if(!file.exists()) {
                return content;
            }
            FileInputStream instream=new FileInputStream(file);
            HWPFDocument doc=new HWPFDocument(instream);
            Range range=doc.getRange();
            String text=range.text();
            for(int i=0;i<range.numParagraphs();i++){
                Paragraph p=range.getParagraph(i);
                content=content+p.text().trim()+"\n";
            }
        }catch(Exception e){
            e.printStackTrace();
        }
        return content;
    }
    /**
     * 解析PDF
     * @param filename
     * @return
     */
    public static String handlePdf(String filename){
        String contenttxt="";
        try{
            File file=new File(filename);
            if(!file.exists()){
                return contenttxt;
            }
            FileInputStream instream=new FileInputStream(file);
            PDFParser parser=new PDFParser(instream);
            parser.parse();
            PDDocument pdfdocument=parser.getPDDocument();
            PDFTextStripper pdfstripper=new PDFTextStripper();
            contenttxt=pdfstripper.getText(pdfdocument);
        }catch(Exception e){
            e.printStackTrace();
        }
        return contenttxt;
    }
    /**
     * 解析EXCEL
     * @param filename
     * @return
     */
    public static String handleExcel(String filename){
        String content="";
        try{
            File file=new File(filename);
            if(!file.exists()) {
                return content;
            }
            HSSFWorkbook workbook=new HSSFWorkbook(new FileInputStream(file));
            HSSFSheet sheet=workbook.getSheetAt(0);

            for(int i=0;i<workbook.getNumberOfSheets();i++){
                sheet=workbook.getSheetAt(i);
                if(sheet!=null){
                    for(int m=0;m<sheet.getLastRowNum();m++){
                        HSSFRow row=sheet.getRow(m);
                        if(row==null) break;

                        for(int n=0;n<row.getLastCellNum();n++){
                            HSSFCell cell=row.getCell(n);
                            if(cell==null) break;
                            int type=cell.getCellType();
                            switch(type){
                                case 0:
                                    content=content+cell.getNumericCellValue();
                                    break;
                                case 1:
                                    content=content+cell.getStringCellValue();
                                    break;
                                case 3:
                                    break;
                                default:
                                    ;
                            }
                        }
                        content=content+"\n";
                    }
                }
                content=content+"\n";
            }

        }catch(Exception e){
            e.printStackTrace();
        }
        return content;
    }
}

不想拯��的朋友可以直接下载源代码�Q?a class="normal12blue">http://www.ziddu.com/download/7017614/src.txt.html

以上代码比较��单，��׃��作说明，希望能幫到需要用的朋友。当然上面只是一個简单的例子�Q�如果要具体应用�Q�大家可以自己再改写。如果你有其它的��x��Q�欢�q�分享你的精彩想法�?br />

转蝲��h��?font size="3">出处

王生�?/a> 2009-10-22 10:55 发表评论

Mon, 12 Oct 2009 06:04:00 GMT

��单实现网��采集程序，�q�行�E�序后，把抓到的�|�页攑ֈ�目录下面

package com.ducklyl;

import java.net.*;
import java.io.*;

public class WebHttpClient {
    //�|�页保存路径
    private static String Text_File_Path="D:\\Test\\index.html";
    public static void main(String args[]){
        try{
            File file=new File(Text_File_Path);
            FileWriter fpWriter=new FileWriter(file);

            //生成下蝲对象
            String URL="www.bnu.edu.cn",Host="www.bnu.edu.cn";
            int Port=80;
            Socket webclient=new Socket(URL,Port);
            //输出��?br />             PrintWriter result=new PrintWriter(webclient.getOutputStream(),true);
            //��d��?br />             BufferedReader receiver=new BufferedReader(new InputStreamReader(webclient.getInputStream()));

            //发送http request
            result.println("GET / HTTP1.1");
            result.println("Host:"+Host);
            result.println("Connection:Close");
            result.println();

            //接收Http response
            boolean bRet=true;
            StringBuffer sb=new StringBuffer(8096);
            while(bRet){
                if(receiver.ready()){
                    int idx=0;
                    while(idx!=-1){
                        idx=receiver.read();
                        sb.append((char)idx);
                    }
                    bRet=false;
                }
            }
            //打印�l�果
            System.out.println(sb.toString());
            //寫到文�g里面
            fpWriter.write(sb.toString());
            webclient.close();
            fpWriter.close();
        }catch(UnknownHostException e){
            System.err.println("don't get the host");
            System.exit(1);
        }catch(IOException e){
            System.err.println("Download error,please check the URL.");
            System.exit(1);
        }
    }
}

王生�?/a> 2009-10-12 14:04 发表评论

(�?java的InputStream和OutputStream的理�?

Mon, 12 Oct 2009 05:28:00 GMT

摘要: Normal 0 7.8 pt 0 2 false false false MicrosoftInternetExplorer4 /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal";... 阅读全文

王生�?/a> 2009-10-12 13:28 发表评论

亚洲成a人片在线观看天堂无码 ,亚洲国产成人无码AV在线,亚洲阿v天堂在线2017免费

�Q�d��创］java解析非结构化文本 doc xls pdf ppt xml html

(�?java的InputStream和OutputStream的理�?