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:integrator.Pdf.java

/**
 * Parses a PDF to a plain text file.//from  w  ww.  j a va 2 s .co m
 * @param pdf the original PDF
 * @param txt the resulting text
 * @throws IOException
 */
public void parsePdf(String pdf, String txt) 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());
        out.println(strategy.getResultantText());
    }
    out.flush();
    out.close();
    reader.close();
}

---

From source file:net.sf.regain.crawler.preparator.PdfItextPreparator.java

License:Open Source License

/**
 * Prpariert ein Dokument fr die Indizierung.
 *
 * @param rawDocument Das zu prpariernde Dokument.
 * @throws net.sf.regain.RegainException Wenn die Prparation fehl schlug.
 *//*w  w w . j a  va  2 s.c o m*/
@SuppressWarnings("unchecked")
public void prepare(RawDocument rawDocument) throws RegainException {
    String url = rawDocument.getUrl();

    InputStream stream = null;
    PdfReader reader = null;

    try {
        // Create a InputStream that reads the content.
        stream = rawDocument.getContentAsStream();

        // Parse the content
        reader = new PdfReader(stream);
        if (reader.isEncrypted()) {
            reader = new PdfReader(stream, OWNER_PASSWORD);
        }
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);

        TextExtractionStrategy strategy;
        StringBuilder stringBuilder = new StringBuilder();
        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            stringBuilder.append(strategy.getResultantText());

        }

        setCleanedContent(stringBuilder.toString());

        // Get metadata
        Map<String, String> info = reader.getInfo();

        StringBuilder metaData = new StringBuilder();
        metaData.append("p.");
        metaData.append(Integer.toString(reader.getNumberOfPages()));
        metaData.append(" ");

        // Check if fields are null
        String author = info.get("Author");
        String creator = info.get("Creator");
        String subject = info.get("Subject");
        String keywords = info.get("Keywords");
        String title = info.get("Title");

        if (author != null) {
            metaData.append(author);
            metaData.append(" ");
        }
        if (creator != null) {
            metaData.append(creator);
            metaData.append(" ");
        }
        if (subject != null) {
            metaData.append(subject);
            metaData.append(" ");
        }
        if (keywords != null) {
            metaData.append(keywords);
            metaData.append(" ");
        }

        if (title != null) {
            setTitle(title);
        }

        setCleanedMetaData(metaData.toString());
        if (log.isDebugEnabled()) {
            log.debug("Extracted meta data ::" + getCleanedMetaData() + ":: from " + rawDocument.getUrl());
        }

    } catch (IOException exc) {
        throw new RegainException("Error reading document: " + url, exc);
    } catch (Exception exc) {
        // They didn't supply a password and the default of "" was wrong.
        throw new RegainException("Unknown error parsing document: " + url, exc);

    } finally {
        if (stream != null) {
            try {
                stream.close();
            } catch (Exception exc) {
            }
        }
        if (reader != null) {
            try {
                reader.close();
            } catch (Exception exc) {
            }
        }
    }
}

---

From source file:org.archive.modules.extractor.ExtractorPDFContent.java

License:Apache License

public String extractPageText(PdfReader documentReader, int pageNum) {
    String content = "";
    PdfReaderContentParser parser = new PdfReaderContentParser(documentReader);
    TextExtractionStrategy strat;
    try {/*from   w  ww . j a va2  s.  com*/
        strat = parser.processContent(pageNum, new SimpleTextExtractionStrategy());
        content = strat.getResultantText();

    } catch (IOException e) {
        LOGGER.log(Level.WARNING, "Failed to parse pdf text in " + Thread.currentThread().getName(), e);
    }
    return content;
}

---

From source file:pdfextract.ControlPDF.java

public List<String> parsePdfToArrayList(String pdfPath) throws IOException {
    PdfReader reader = new PdfReader(pdfPath);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    List<String> arrayOftext = new ArrayList<String>();

    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        arrayOftext.add(strategy.getResultantText());
    }//w  w  w. jav  a2s . c  o  m
    reader.close();

    return arrayOftext;
}

---

From source file:pdfextract.ControlPDF.java

public String pdfToDIrAndimgToString(String pdfPath, File destnationPath)
        throws IOException, DocumentException, Exception {
    //boolean success;
    String kk = "";
    String desPath = null;/*from w  ww  .jav a2  s.  c  o  m*/
    PdfReader reader = new PdfReader(pdfPath);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    try {
        desPath = destnationPath.getName();

        new File(desPath.replace(".txt", "")).mkdir();
        PrintWriter out = new PrintWriter(
                new FileOutputStream(desPath.replace(".txt", "") + "/" + destnationPath.getName()));
        TextExtractionStrategy strategy;
        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            out.println(i + " " + strategy.getResultantText());
        }
        reader.close();
        out.flush();
        out.close();
        extractImagesFromPdf(pdfPath, desPath.replace(".txt", "") + "/" + desPath.replace(".txt", ""));
        File f = new File(desPath.replace(".txt", "") + "/" + desPath.replace(".txt", "") + "-16.null");
        kk = imageToBase64String(f);
        /*File deletedFolder = new File(destnationPath.getParent());
        System.out.println("here"+destnationPath.getParent());
        deletedFolder.delete();
        System.out.println("is delete+ " + deletedFolder.delete());*/
        //       FileUtils.deleteDirectory(new File(deletedFolder.getParent()));
        //success = true;
    } catch (Exception ex) {
        //success = false;

    }

    return kk;
}

---

From source file:pdfextract.ExtractInfo.java

public List<String> parsePdf(String pdfPath) throws IOException {
    PdfReader reader = new PdfReader(pdfPath);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    //String [] arrayOftext= new String[300];
    List<String> arrayOftext = new ArrayList<String>();

    // PrintWriter out = new PrintWriter(new FileOutputStream(destnationPath));
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        // out.println(i + " " + strategy.getResultantText());
        arrayOftext.add(strategy.getResultantText());
    }//from  ww w. j a v  a 2s. c o m
    reader.close();

    return arrayOftext;
}

---

From source file:textextractor.PDFManager.java

/**
 * Parses a PDF to a plain text file./*from ww  w.  j ava2s . c  o m*/
 *
 * @param pdf the original PDF
 * @throws IOException
 */
public ArrayList parsePdf(String pdf) throws IOException {
    PdfReader reader = new PdfReader(pdf);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        System.out.println(strategy.getResultantText());
        listPdf.add(strategy.getResultantText());
    }
    return listPdf;
}

---

From source file:tutorial.PDFtoText.java

public void convertPDFtoText() throws IOException {
    /*variabel "pdf" digunakan untuk menampung alamat direktori tempat file pdf disimpan.*/
    String pdf = txtDirektori.getText();
    StringBuilder text = new StringBuilder();
    String resultText;/*from w  w w  .jav  a  2s.c  om*/

    /*Buat file Text ".txt"*/
    File namaFile = new File(txtDirektori.getText().replace("pdf", "txt"));
    if (namaFile.createNewFile()) {
        System.out.println("File .txt berhasil dibuat.");
    }

    try {
        /*Panggil class yang ada pada library iText untuk membaca file PDF*/
        PdfReader reader = new PdfReader(pdf);
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        TextExtractionStrategy strategy;
        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
            text.append(strategy.getResultantText());
        }
        resultText = text.toString();

        /*Code untuk menuliskan hasil pembacaan file PDF ke file Text*/
        StringTokenizer stringTokenizer = new StringTokenizer(resultText, "\n");
        PrintWriter lineWriter = new PrintWriter(new FileOutputStream(namaFile));
        while (stringTokenizer.hasMoreTokens()) {
            String curToken = stringTokenizer.nextToken();
            lineWriter.println(curToken);
        }
        lineWriter.flush();
        lineWriter.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
}

---

From source file:uk.bl.dpt.qa.flint.wrappers.iTextWrapper.java

License:Apache License

/**
 * Extracts text from a PDF./*from   w  w w  . j ava 2  s  .  com*/
 * @param pFile input file
 * @param pOutput output file
 * @param pOverwrite whether or not to overwrite an existing output file
 * @return true if converted ok, otherwise false
 */
public boolean extractTextFromPDF(File pFile, File pOutput, boolean pOverwrite) {
    if (pOutput.exists() & (!pOverwrite))
        return false;

    boolean ret = true;

    PrintWriter pw = null;
    PdfReader reader = null;

    try {
        pw = new PrintWriter(new FileWriter(pOutput));
        reader = new PdfReader(pFile.getAbsolutePath());
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        TextExtractionStrategy strategy;
        for (int i = 0; i < reader.getNumberOfPages(); i++) {
            try {
                //page numbers start at 1
                strategy = parser.processContent((i + 1), new SimpleTextExtractionStrategy());
                //write text out to file
                pw.println(strategy.getResultantText());
            } catch (ExceptionConverter e) {
                e.printStackTrace();
                ret = false;
                pw.println("iText Exception: Page " + (i + 1) + ": " + e.getClass().getName() + ": "
                        + e.getMessage());
            }
        }
    } catch (IOException e) {
        ret = false;
        // TODO Auto-generated catch block
        e.printStackTrace();
    } finally {
        if (pw != null)
            pw.close();
        if (reader != null)
            reader.close();
    }

    return ret;
}

---

• «
• 1
• 2
• »