Example usage for com.itextpdf.text.pdf.parser TextExtractionStrategy getResultantText

Introduction

In this page you can find the example usage for com.itextpdf.text.pdf.parser TextExtractionStrategy getResultantText.

Prototype

public String getResultantText();

Source Link

Document

Returns the result so far.

Usage

From source file:br.com.smarttaco.util.HelenaBarbosa.java

/**
 * pdf2txt/* ww  w .  j a va  2s  .com*/
 *
 * @param pdf
 * @param paginas se for <code>null</code> realiza leitura completa.
 * @param txt
 * @throws FileNotFoundException
 * @throws IOException
 */
private static void pdf2txt(final String pdf, List<Integer> paginas, final String txt)
        throws FileNotFoundException, IOException {
    PdfReader reader = new PdfReader(pdf);
    //System.out.println(reader.getInfo().toString());
    if (paginas != null) {
        reader.selectPages(paginas);
    }
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(txt, "UTF-8");
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        out.println(strategy.getResultantText());
    }
    out.flush();
    out.close();
    reader.close();
}

---

From source file:com.cloudhub.util.PDFToText.java

License:Apache License

/**
 * Parses a PDF to a plain text file./*from   w w w .  j ava  2 s.  c  o m*/
 *
 * @param source the original PDF
 * @param destination the resulting text
 * @throws IOException
 */
public static void parsePdf(String source, String destination) throws IOException {
    PdfReader reader = new PdfReader(source);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(new FileOutputStream(destination));
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        out.println(strategy.getResultantText());
    }
    out.flush();
    out.close();
}

---

From source file:com.erikHolz.vertretungsplan.Converter.java

License:Open Source License

public void parsePDF() throws IOException {

    PdfReader reader = new PdfReader(fileDest + ".pdf");
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(new FileOutputStream(fileDest + "__.txt"));

    TextExtractionStrategy strategy;
    for (int intI = 1; intI <= reader.getNumberOfPages(); intI++) {
        strategy = parser.processContent(intI, new LocationTextExtractionStrategy());
        out.println(strategy.getResultantText());
    }//w  w  w . jav  a2s  . co m

    out.flush();
    out.close();
    reader.close();

    // lschen der ursprnglichen pdf
    File f = new File(fileDest + ".pdf");
    if (f.exists())
        f.delete();
}

---

From source file:com.joanzapata.PDFViewActivity.java

License:Open Source License

public void parsePdf(String pdf2, String txt) throws IOException {
    // String//from ww  w.j  a  v  a  2 s.  c  o  m
    // pdf1=Environment.getExternalStoragePublicDirectory(Environment.DIRECTORY_DOWNLOADS)+
    // File.separator + "about.pdf";
    PdfReader reader = new PdfReader(pdf2);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);

    File file = getFileStreamPath("test.txt");

    if (!file.exists()) {
        file.createNewFile();
    }

    FileOutputStream writer = openFileOutput(file.getName(), Context.MODE_PRIVATE);

    // PrintWriter out = new PrintWriter(new FileOutputStream(txt));
    TextExtractionStrategy strategy;
    for (int i = 1; i <= pageNumber; i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        writer.write(strategy.getResultantText().getBytes());
        writer.flush();
    }
    writer.close();
    reader.close();
    String totalString = readFromFile();
    System.out.println(totalString);
    totalContent = totalString;
    String word = "Number of words  " + wordCount(totalString) + "\n";
    String averageWords = "Average length of words  " + " " + averageWords(totalString) + "\n";
    String sentenseCount = "Number of sentences  " + sentenseCount(totalString) + "\n";
    String averageSentenses = "Average length of sentences  " + averageSentense(totalString) + "\n";
    // String complexity=
    String readability = " Readability Index  " + getReadability(totalString) + "\n";

    String subject = "Subject Area  " + etSubject.getText().toString() + "\n";
    String article = "Type of the Article : " + etArticle.getText().toString() + "\n";
    String pages = " Pages  " + startPage + " to " + pageNumber + "\n";
    String book = "book name  " + etBookName.getText().toString() + "\n";
    String readername = "reader name  " + etReaderName.getText().toString() + "\n";
    totalInfo = readername + book + subject + "\n" + article + pages + word + averageWords + sentenseCount
            + averageSentenses + readability;
    displayMessage(totalInfo);

}

---

From source file:com.sustainalytics.crawlerfilter.PDFTitleGeneration.java

License:Apache License

public static String extractITextText(String pdf) {
    PdfReader reader = null;/*from   w  ww.  j  a  v  a2s.  c  om*/
    try {
        reader = new PdfReader(pdf);
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    TextExtractionStrategy strategy;
    String text = "";
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        try {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            text += strategy.getResultantText();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    reader.close();

    return text;
}

---

From source file:com.sustainalytics.crawlerfilter.PDFtoText.java

License:Apache License

public static String extractITextText(String pdf) {
    PdfReader reader = null;/*ww w.j a  v  a  2s  .c  om*/
    try {
        reader = new PdfReader(pdf);
    } catch (IOException e) {
        logger.info("Error in reading file with iText parser\n");
    }
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    TextExtractionStrategy strategy;
    String text = "";
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        try {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            text += strategy.getResultantText();
        } catch (IOException e) {
            logger.info("Error in parsing with iText parser\n");
        }
        logger.info("PDF text extracted from " + pdf + "\n");
    }
    reader.close();

    return text;
}

---

From source file:conversorpdf.Conversor.Conversor.java

/**
 * Parses a PDF to a plain text file.//from  w ww .  j  a  v  a  2 s  .  c  o  m
 * @param pdf the original PDF
 * @param txt the resulting text
 * @throws IOException
 */
public boolean parsePdf(String pdf, String txt, boolean removerAcento) throws IOException {
    PdfReader reader = new PdfReader(pdf);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(new FileOutputStream(txt));
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {

        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());

        if (removerAcento == false) {
            out.println(strategy.getResultantText());
        } else {
            out.println(this.removeAcentos(strategy.getResultantText()));
        }

    }
    out.flush();
    out.close();

    return true;
}

---

From source file:coviam.pdf.PdfParser.java

public void getText() {

    String pdf = "/home/amit/NetBeansProjects/ResumeParser/data/resumes/ejd1.pdf";
    String text = "/home/amit/NetBeansProjects/ResumeParser/data/resumes/edj1.txt";
    StringBuffer textBuffer = new StringBuffer();
    String resultText = "";
    PdfReader reader;//from w  ww  .  j a v  a2 s .c  o m
    try {
        reader = new PdfReader(pdf);
        PdfReaderContentParser contentParser = new PdfReaderContentParser(reader);
        PrintWriter printWriter = new PrintWriter(new FileOutputStream(text));
        TextExtractionStrategy strategy;
        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            strategy = contentParser.processContent(i, new SimpleTextExtractionStrategy());
            textBuffer.append(strategy.getResultantText());
        }
        resultText = textBuffer.toString();
        resultText = resultText.replaceAll("-\n", "");
        System.out.println("-->" + resultText);

        StringTokenizer stringTokenizer = new StringTokenizer(resultText, "\n");
        PrintWriter lineWriter = new PrintWriter(
                new FileOutputStream("/home/amit/NetBeansProjects/ResumeParser/data/resumes/edj1.txt"));
        while (stringTokenizer.hasMoreTokens()) {
            String curToken = stringTokenizer.nextToken();
            lineWriter.println("line-->" + curToken);
        }
        lineWriter.flush();
        lineWriter.close();
        System.out.flush();
        System.out.close();
    } catch (IOException ioe) {

    }

}

---

From source file:de.offis.health.icardea.cied.pdf.extractor.PDFiText5Extractor.java

License:GNU General Public License

public String getText(int pageNumber) throws IOException, Exception {
    String returnValue = null;//ww  w.  j  a  v a2  s  .c  o  m

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

        if (pageNumber > 0 && pageNumber <= numberOfPages) {
            TextExtractionStrategy strategy;
            PdfReaderContentParser parser = new PdfReaderContentParser(pdfReader);
            strategy = parser.processContent(pageNumber, new SimpleTextExtractionStrategy());

            if (strategy != null && strategy.getResultantText().trim().length() > 0) {
                returnValue = PAGE_START_MARKER + strategy.getResultantText();
            } // 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:helper.PdfText.java

License:Apache License

/**
 * @param pdfFile this file will be extracted.
 * @return the plain text of the pdf/*from  ww  w.  j a v  a 2s  .c  o m*/
 */
public String itext(File pdfFile) {

    PdfReader reader;
    try {
        reader = new PdfReader(pdfFile.getAbsolutePath());
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        StringBuffer buf = new StringBuffer();
        TextExtractionStrategy strategy;
        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            buf.append(strategy.getResultantText());
        }

        return buf.toString();
    } catch (IOException e) {
        throw new HttpArchiveException(500, e);
    }

}

---

• «
• 1
• 2
• »