java操作word,pdf的四種武器
阿新 • • 發佈:2018-12-29
下面是一個如何使用pdfbox抽取pdf檔案的例子:
import org.pdfbox.pdmodel.PDdocument.
import org.pdfbox.pdfparser.PDFParser;
import java.io.*;
import org.pdfbox.util.PDFTextStripper;
import java.util.Date;
/**
* <p>Title: pdf extraction</p>
* <p>Description: email:[email protected]</p>
* <p>Copyright: Matrix Copyright (c) 2003</p>
* <p>Company: Matrix.org.cn</p>
* @author chris
* @version 1.0,who use this example pls remain the declare
*/
public class PdfExtracter{
public PdfExtracter(){
}
public String GetTextFromPdf(String filename) throws Exception
{
String temp=null;
PDdocument.nbsppdfdocument.null;
FileInputStream is=new FileInputStream(filename);
PDFParser parser = new PDFParser( is );
parser.parse();
pdfdocument.nbsp= parser.getPDdocument.);
ByteArrayOutputStream out = new ByteArrayOutputStream();
OutputStreamWriter writer = new OutputStreamWriter( out );
PDFTextStripper stripper = new PDFTextStripper();
stripper.writeText(pdfdocument.getdocument.), writer );
writer.close();
byte[] contents = out.toByteArray();
String ts=new String(contents);
System.out.println("the string length is"+contents.length+"");
return ts;
}
public static void main(String args[])
{
PdfExtracter pf=new PdfExtracter();
PDdocument.nbsppdfdocument.nbsp= null;
try{
String ts=pf.GetTextFromPdf("c://a.pdf");
System.out.println(ts);
}
catch(Exception e)
{
e.printStackTrace();
}
}
}
4.抽取支援中文的pdf檔案-xpdf
xpdf是一個開源專案,我們可以呼叫他的本地方法來實現抽取中文pdf檔案。
下載xpdf函式包:
import org.pdfbox.pdmodel.PDdocument.
import org.pdfbox.pdfparser.PDFParser;
import java.io.*;
import org.pdfbox.util.PDFTextStripper;
import java.util.Date;
/**
* <p>Title: pdf extraction</p>
* <p>Description: email:[email protected]</p>
* <p>Copyright: Matrix Copyright (c) 2003</p>
* <p>Company: Matrix.org.cn</p>
* @author chris
* @version 1.0,who use this example pls remain the declare
*/
public class PdfExtracter{
public PdfExtracter(){
}
public String GetTextFromPdf(String filename) throws Exception
{
String temp=null;
PDdocument.nbsppdfdocument.null;
FileInputStream is=new FileInputStream(filename);
PDFParser parser = new PDFParser( is );
parser.parse();
pdfdocument.nbsp= parser.getPDdocument.);
ByteArrayOutputStream out = new ByteArrayOutputStream();
OutputStreamWriter writer = new OutputStreamWriter( out );
PDFTextStripper stripper = new PDFTextStripper();
stripper.writeText(pdfdocument.getdocument.), writer );
writer.close();
byte[] contents = out.toByteArray();
String ts=new String(contents);
System.out.println("the string length is"+contents.length+"");
return ts;
}
public static void main(String args[])
{
PdfExtracter pf=new PdfExtracter();
PDdocument.nbsppdfdocument.nbsp= null;
try{
String ts=pf.GetTextFromPdf("c://a.pdf");
System.out.println(ts);
}
catch(Exception e)
{
e.printStackTrace();
}
}
}
4.抽取支援中文的pdf檔案-xpdf
xpdf是一個開源專案,我們可以呼叫他的本地方法來實現抽取中文pdf檔案。
下載xpdf函式包: