Example usage for com.lowagie.text.pdf.parser PdfTextExtractor PdfTextExtractor

Introduction

In this page you can find the example usage for com.lowagie.text.pdf.parser PdfTextExtractor PdfTextExtractor.

Prototype

public PdfTextExtractor(PdfReader reader) 

Source Link

Document

Creates a new Text Extractor object.

Usage

From source file:de.offis.health.icardea.cied.pdf.extractor.PDFiText2Extractor.java

License:LGPL

public String getText(int pageNumber) throws IOException, Exception {
    String returnValue = null;/*from   w w w .  j  a  v  a 2s  .c om*/

    if (pdfReader != null) {
        int numberOfPages = getNumberOfPages();

        if (pageNumber > 0 && pageNumber <= numberOfPages) {
            PdfTextExtractor pdfTextExtractor = new PdfTextExtractor(pdfReader);
            String extractedText = pdfTextExtractor.getTextFromPage(pageNumber);
            if (extractedText != null && extractedText.trim().length() > 0) {
                returnValue = PAGE_START_MARKER + extractedText;
            } // end if
        } else {
            // TODO: Add own exception.
            throw new Exception("The given page number (" + pageNumber + ") "
                    + "is not in the range of valid pages (1.." + numberOfPages + ").");
        } // end if..else
    } else {
        // TODO: Add own exception.
        throw new Exception("There is no open PDF to work with.");
    } // end if..else
    return returnValue;
}

---

From source file:net.laubenberger.bogatyr.helper.HelperPdf.java

License:Open Source License

/**
 * Returns the text of a given PDF as {@link String}.
 * /*from  w  w w .  j  a v  a  2s  .c  om*/
 * @param file
 *           input as PDF
 * @return text of the given PDF
 * @throws IOException
 * @see File
 * @since 0.9.3
 */
public static String getText(final File file) throws IOException { // $JUnit$
    if (log.isDebugEnabled())
        log.debug(HelperLog.methodStart(file));
    if (null == file) {
        throw new RuntimeExceptionIsNull("file"); //$NON-NLS-1$
    }

    final PdfReader pdfReader = new PdfReader(file.getAbsolutePath());
    final PdfTextExtractor pdfExtractor = new PdfTextExtractor(pdfReader);

    final StringBuilder sb = new StringBuilder();

    for (int page = 1; page <= pdfReader.getNumberOfPages(); page++) {
        sb.append(pdfExtractor.getTextFromPage(page));
        sb.append(HelperString.NEW_LINE);
    }
    final String result = sb.toString();

    if (log.isDebugEnabled())
        log.debug(HelperLog.methodExit(result));
    return result;
}

---