org.apache.pdfbox.util.PDFTextStripper Java Examples

private boolean getFile(String url)
{
    try
    {
        URL u = new URL(url);
        URLConnection con = u.openConnection();
        InputStream in = con.getInputStream();
        PDFParser p = new PDFParser(in);
        p.parse();
        PDDocument pdoc = new PDDocument(p.getDocument());
        PDFTextStripper pts = new PDFTextStripper();
        text = pts.getText(pdoc);
        pdoc.close();

        return true;
    }
    catch (Exception e)
    {
        e.printStackTrace();
        return false;
    }
}
 

public static String extractTextOutOfPDF(String url) {
    PDDocument doc = null;
    try {
        if(url.startsWith("file:")) {
            doc = PDDocument.load(new File(url));
        }
        else {
            doc = PDDocument.load(new URL(url));
        }
        PDFTextStripper stripper = new PDFTextStripper();
        String content = stripper.getText(doc);
        doc.close();
        return content;
    }
    catch(Exception e) {
        e.printStackTrace();
    }
    return null;
}
 

private static void usingPDFBox() {
    try {
        File file = new File("TestDocument.pdf");
        PDDocument pdDocument = PDDocument.load(file);
        PDFTextStripper stripper = new PDFTextStripper();
        String text = stripper.getText(pdDocument);
        System.out.println(text);
        pdDocument.close();
    } catch (IOException ex) {
        ex.printStackTrace();
    }
}
 

private String extractText(final VFSLeaf leaf) throws IOException, DocumentAccessException {
    if (log.isDebugEnabled()) {
        log.debug("readContent from pdf starts...");
    }
    PDDocument document = null;
    InputStream is = null;
    try {
        is = leaf.getInputStream();
        document = PDDocument.load(is);
        if (document.isEncrypted()) {
            try {
                document.decrypt("");
            } catch (final Exception e) {
                throw new DocumentAccessException("PDF is encrypted. Can not read content file=" + leaf.getName());
            }
        }
        if (log.isDebugEnabled()) {
            log.debug("readContent PDDocument loaded");
        }
        final PDFTextStripper stripper = new PDFTextStripper();
        return stripper.getText(document);
    } finally {
        if (document != null) {
            document.close();
        }
        if (is != null) {
            is.close();
        }
        // needed to prevent potential OutOfMemoryError
        // https://issues.apache.org/jira/browse/PDFBOX-1009
        PDFont.clearResources();
    }
}
 

@Test
public void testShouldReturnIndexedDocumentWhenParameterCorrect() throws IOException {
    String mediaType = "application/pdf+test";
    final String MEDIA_TYPE = "mediaType";
    PDFParser parser = Mockito.mock(PDFParser.class);
    COSDocument cosDoc = Mockito.mock(COSDocument.class);
    PDFTextStripper pdfTextStripper = Mockito.mock(PDFTextStripper.class);
    Mockito.doThrow(IOException.class).when(cosDoc).close();
    Mockito.when(parser.getDocument()).thenReturn(new COSDocument()).thenReturn(cosDoc);
    Mockito.when(pdfTextStripper.getText(new PDDocument())).thenReturn("");
    PDFIndexer pdfIndexer = new PDFIndexerWrapper(parser, pdfTextStripper);

    // should return the default media type when media type is not defined in file2Index
    IndexDocument pdf = pdfIndexer.getIndexedDocument(file2Index);
    if (!"application/pdf".equals(pdf.getFields().get(MEDIA_TYPE).get(0))) {
        Assert.fail();
    }

    // should return the media type we have set in the file2Index even if error occurs in finally block
    file2Index.mediaType = mediaType;
    pdf = pdfIndexer.getIndexedDocument(file2Index);
    if (!mediaType.equals(pdf.getFields().get(MEDIA_TYPE).get(0))) {
        Assert.fail();
    }

}
 

private String getPdfText() {
    try {
        return new PDFTextStripper().getText(actual);
    } catch (IOException shouldNotHappen) {
        throw new RuntimeException(shouldNotHappen);
    } finally {
        try {
            actual.close();
        } catch (IOException e) {
            // we don't care
        }
    }
}
 

public void process(File pdf, File output){
    PDDocument pdDoc;
    try {//Kudos for closing: http://stackoverflow.com/questions/156508/closing-a-java-fileinputstream
        File tmpfile = File.createTempFile(String.format("txttmp-%s", UUID.randomUUID().toString()), null);
        RandomAccessFile raf = new RandomAccessFile(tmpfile, "rw");
        pdDoc = PDDocument.loadNonSeq(pdf, raf);
        FileWriter writer = new FileWriter(output);
        try {
            PDFTextStripper stripper = new PDFTextStripper();
            int numberOfPages = pdDoc.getNumberOfPages();

            for (int j = 1; j < numberOfPages+1; j++) {
                stripper.setStartPage(j);
                stripper.setEndPage(j);
                writer.write(stripper.getText(pdDoc));
                writer.flush();
            }
        } finally {
            pdDoc.close();
            raf.close();
            tmpfile.delete();
            writer.close();
        }
    } catch (IOException ioe) {
        log.warn(String.format("Failed to create txt for file: %s", pdf.getName()), ioe);
    }
}
 

protected PDFTextStripper getPdfTextStripper() throws IOException {
	return new PDFTextStripper();
}
 

public PDFIndexerWrapper(PDFParser pdfParser, PDFTextStripper stripper) {
    this.pdfParser = pdfParser;
    this.pdfTextStripper = stripper;
}
 

@Override
protected PDFTextStripper getPdfTextStripper() throws IOException {
    return this.pdfTextStripper;
}