pdfbox转换html,PDF格式转换为HTML页面明智使用PDFBOX库

/**

* private constructor.

*/

private ExtractText()

{

//static class

}

public static void main(String[] args) throws Exception

{

if(l!=null)

{

System.out.println("HERE"+l.length);

deleteSubs(op);

System.out.println("Then"+l.length);

}

else

{

System.out.println("WHERE");

}

File y=new File(imgDes);

if(!y.exists())

{

y.mkdirs();

}

File z=new File(imgDestination);

if(!z.exists())

{

z.mkdirs();

}

File fr=new File(outputFile);

if(!fr.isDirectory())

{

fr.delete();

}

// Defaults to text files

String ext = ".txt";

int startPage = 1;

int endPage = Integer.MAX_VALUE;

Writer output = null;

PDDocument document =null;

try

{

try

{

URL url = new URL(pdfFile);

document = PDDocument.load(url, force);

String fileName = url.getFile();

if(outputFile == null && fileName.length() >4)

{

outputFile = new File(fileName.substring(0, fileName.length() -4) + ext).getName();

}

}