Eason: PDF_Extractor

2008年5月24日

PDF_Extractor

http://eason982.blogspot.com/2008/05/pdfextractor.html

API:
http://www.pdfbox.org/userguide/text_extraction.html




public class PDF_Reader {
   //讀pdf
   File f = new File("src\\Test\\test.pdf");
   PDDocument document = PDDocument.load(f);
   PDFTextStripper stripper = new PDFTextStripper();
   //設定從pdf的幾頁開始
    stripper.setStartPage(1);
   //設定從pdf的幾頁結束
    stripper.setEndPage(2);
   String mytext =  stripper.getText(document);
   System.out.println(mytext);
   document.close();

}