PDFBOX can onley select text from pdf?
Java
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:chris@matrix.org.cn</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+"\n");
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();
}
}
}
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:chris@matrix.org.cn</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+"\n");
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();
}
}
}
同时CSHARP如下
引用一些类
PDDocument doc = PDDocument.load("4.pdf");
//doc.getDocument();
PDFTextStripper pdfStripper = new PDFTextStripper();
PDFTextStripper stripper = new PDFTextStripper();
stripper.getText(doc);
doc.close();
最新版本省去了一下数据流的操作
参考:http://pdfhome.hope.com.cn/
作者:拒绝潜水的鱼
出处:http://slave2.cnblogs.com/
本文版权归作者和博客园共有,欢迎转载,但未经作者同意必须保留此段声明,且在文章页面明显位置给出原文连接,否则保留追究法律责任的权利。
出处:http://slave2.cnblogs.com/
本文版权归作者和博客园共有,欢迎转载,但未经作者同意必须保留此段声明,且在文章页面明显位置给出原文连接,否则保留追究法律责任的权利。