Java Code Examples for org.apache.pdfbox.text.PDFTextStripper#writeText()

public static void main(String[] args) throws IOException {
	PDDocument document = null;
	try {
		document = PDDocument.load(new File("/home/lili/data/test.pdf"));

		PDFTextStripper stripper = new PrintTextLocations();
		stripper.setSortByPosition(true);
		stripper.setStartPage(0);
		stripper.setEndPage(document.getNumberOfPages());

		Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
		stripper.writeText(document, dummy);
	} finally {
		if (document != null) {
			document.close();
		}
	}
}
 

/**
 * @throws IOException If there is an error parsing the document.
 */
public static void main( String[] args ) throws IOException {
    PDDocument document = null;
    String fileName = "/home/lili/data/test.pdf";
    try {
        document = PDDocument.load( new File(fileName) );
        PDFTextStripper stripper = new GetLinesFromPDF();
        stripper.setSortByPosition( true );
        stripper.setStartPage( 0 );
        stripper.setEndPage( document.getNumberOfPages() );
        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        stripper.writeText(document, dummy);
        
        // print lines
        for(String line:lines){
            System.out.println(line); 
        }
    }
    finally {
        if( document != null ) {
            document.close();
        }
    }
}
 

private void transformTextAndCheck(String text, String encoding, String checkText)
        throws IOException
{
    // Get a reader for the text
    ContentReader reader = buildContentReader(text, Charset.forName(encoding));
    
    // And a temp writer
    File out = TempFileProvider.createTempFile("AlfrescoTest_", ".pdf");
    ContentWriter writer = new FileContentWriter(out);
    writer.setMimetype("application/pdf");
    
    // Transform to PDF
    transformer.transform(reader, writer);
    
    // Read back in the PDF and check it
    PDDocument doc = PDDocument.load(out);
    PDFTextStripper textStripper = new PDFTextStripper();
    StringWriter textWriter = new StringWriter();
    textStripper.writeText(doc, textWriter);
    doc.close();
    
    String roundTrip = clean(textWriter.toString());
    
    assertEquals(
            "Incorrect text in PDF when starting from text in " + encoding,
            checkText, roundTrip
    );
}
 

/**
 * <a href="https://stackoverflow.com/questions/50330484/could-someone-give-me-an-example-of-how-to-extract-coordinates-for-a-word-usin">
 * Could someone give me an example of how to extract coordinates for a 'word' using PDFBox
 * </a>
 * <br/>
 * <a href="https://www.tutorialkart.com/pdfbox/how-to-get-location-and-size-of-images-in-pdf/attachment/apache-pdf/">
 * apache.pdf
 * </a>
 * <p>
 * This test shows how to extract word coordinates combining the ideas of
 * the two tutorials referenced by the OP.
 * </p>
 */
@Test
public void testExtractWordsForGoodJuJu() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("apache.pdf")) {
        PDDocument document = Loader.loadPDF(resource);
        PDFTextStripper stripper = new GetWordLocationAndSize();
        stripper.setSortByPosition( true );
        stripper.setStartPage( 0 );
        stripper.setEndPage( document.getNumberOfPages() );
 
        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        stripper.writeText(document, dummy);
    }
}
 

public static String parsePdf2Text(InputStream input) throws Exception {
  PDDocument doc = PDDocument.load(input);
  ByteArrayOutputStream output = new ByteArrayOutputStream();
  OutputStreamWriter writer = new OutputStreamWriter(output);
  try {
    PDFTextStripper stripper = new PDFTextStripper();
    stripper.writeText(doc, writer);
  } finally {
    doc.close();
    input.close();
    output.close();
    writer.close();
  }
  return new String(output.toByteArray());
}
 

private String extractTextFromDocument(PDDocument document) throws IOException {
    Writer output = new StringWriter();
    PDFTextStripper stripper = new PDFTextStripper();
    stripper.writeText(document, output);
    return output.toString().trim();
}
 

/**
 * Get the text on a page in the PDF document.
 * @param document the document.
 * @param stripper the PDF stripper used to get the text.
 * @param page     the page number.
 * @return the text on the given page.
 * @throws IOException if something went wrong.
 */
private String getPageText(PDDocument document, PDFTextStripper stripper, int page) throws IOException {
    stripper.setStartPage(page);
    stripper.setEndPage(page);
    StringWriter textWriter = new StringWriter();
    stripper.writeText(document, textWriter);
    return textWriter.toString().replace("’", "'").replace("`", "'");
}