试试PDFBOX
public class PDFTextReader{ static String pdftoText(String fileName) { PDFParser parser; String parsedText = null; PDFTextStripper pdfStripper = null; PDdocument pdDoc = null; COSdocument cosDoc = null; File file = new File(fileName); if (!file.isFile()) { System.err.println("File " + fileName + " does not exist."); return null; } try { parser = new PDFParser(new FileInputStream(file)); } catch (IOException e) { System.err.println("Unable to open PDF Parser. " + e.getMessage()); return null; } try { parser.parse(); cosDoc = parser.getdocument(); pdfStripper = new PDFTextStripper(); pdDoc = new PDdocument(cosDoc); parsedText = pdfStripper.getText(pdDoc); } catch (Exception e) { System.err .println("An exception occured in parsing the PDF document." + e.getMessage()); } finally { try { if (cosDoc != null) cosDoc.close(); if (pdDoc != null) pdDoc.close(); } catch (Exception e) { e.printStackTrace(); } } return parsedText; } public static void main(String args[]){ try { String content = pdftoText(PDF_FILE_PATH); File file = new File("/sample/filename.txt"); // if file doesnt exists, then create it if (!file.exists()) { file.createNewFile(); } FileWriter fw = new FileWriter(file.getAbsoluteFile()); BufferedWriter bw = new BufferedWriter(fw); bw.write(content); bw.close(); System.out.println("Done"); } catch (IOException e) { e.printStackTrace(); } } }


