Java PDFTextStripper类代码示例

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
private boolean process() throws IOException {
    boolean toReturn = false;
    PDFTextStripper stripper = new TitleExtractor();
    PDDocument document = null;

    try {
        document = PDDocument.load(new File(this.getFileNamePathWithExtension()));

        //((TitleExtractor) stripper).setFileNamePathWithExtension(this.getFileNamePathWithExtension());
        stripper.setSortByPosition(true);
        stripper.setStartPage(0);
        stripper.setEndPage(1);

        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        stripper.writeText(document, dummy);
        
        setTitle(((TitleExtractor) stripper).getTitle());

        toReturn = true;
    } finally {
        if (document != null) {
            document.close();
        }
    }
    return toReturn;
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
/**
 * <a href="https://stackoverflow.com/questions/45895768/pdfbox-2-0-7-extracttext-not-working-but-1-8-13-does-and-pdfreader-as-well">
 * PDFBox 2.0.7 ExtractText not working but 1.8.13 does and PDFReader as well
 * </a>
 * <br/>
 * <a href="https://wetransfer.com/downloads/214674449c23713ee481c5a8f529418320170827201941/b2bea6">
 * test-2.pdf
 * </a>
 * <p>
 * Due to the broken <b>ToUnicode</b> maps the output of immediate text
 * extraction from this document is unsatisfying, cf. {@link #testTest2()}.
 * It can be improved by removing these <b>ToUnicode</b> maps as this test
 * shows.
 * </p>
 */
@Test
public void testNoToUnicodeTest2() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("test-2.pdf")    )
    {
        PDDocument document = PDDocument.load(resource);

        for (int pageNr = 0; pageNr < document.getNumberOfPages(); pageNr++)
        {
            PDPage page = document.getPage(pageNr);
            PDResources resources = page.getResources();
            removeToUnicodeMaps(resources);
        }

        PDFTextStripper stripper = new PDFTextStripper();
        String text = stripper.getText(document);

        System.out.printf("\n*\n* test-2.pdf without ToUnicode\n*\n%s\n", text);
        Files.write(new File(RESULT_FOLDER, "test-2_NoToUnicode.txt").toPath(), Collections.singleton(text));
    }
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
public static void main(String[] args) {
    try {
        PDDocument document = PDDocument.load(new File("PDF File.pdf"));
            PDFTextStripper Tstripper = new PDFTextStripper();
            String documentText = Tstripper.getText(document);
            System.out.println(documentText);
    } catch (Exception e) {
        e.printStackTrace();
    }
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
/**
 * Extracts all the Text inside a Pdf
 */
private static String extractPdfText(byte[] pdfData) throws IOException {
    PDDocument pdfDocument = PDDocument.load(new ByteArrayInputStream(pdfData));
    try {
        return new PDFTextStripper().getText(pdfDocument);
    } finally {
        pdfDocument.close();
    }
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
private static String readPdf(InputStream is) throws Exception {
    String result;
    PDDocument doc = PDDocument.load(is);
    PDFTextStripper stripper = new PDFTextStripper();
    result = stripper.getText(doc);
    if(doc!= null) {
        doc.close();
    }
    if (is != null) {
        is.close();
    }
    return result;
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
private boolean process() throws IOException {
    boolean toReturn = false;
    PDFTextStripper stripper = new AuthorExtractor();
    PDDocument document = null;

    try {
        document = PDDocument.load(new File(this.getFileNamePathWithExtension()));

        //((TitleExtractor) stripper).setFileNamePathWithExtension(this.getFileNamePathWithExtension());
        stripper.setSortByPosition(true);
        stripper.setStartPage(0);
        stripper.setEndPage(1);

        Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
        stripper.writeText(document, dummy);

        setAuthorNames(((AuthorExtractor) stripper).getAuthorNames());
        setAuthorAffiliations(((AuthorExtractor) stripper).getAuthorAffiliations());
        setAuthorContacts(((AuthorExtractor) stripper).getAuthorContacts());

        toReturn = true;
    } finally {
        if (document != null) {
            document.close();
        }
    }
    return toReturn;
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
@Test
public void createTitleBlockForPartIterationTest() throws Exception {
    PartTitleBlockData partTitleBlockData = new PartTitleBlockData(partIteration, new Locale("en"));
    byte[] titleBlock = new TitleBlockWriter(partTitleBlockData).createTitleBlock();
    PDDocument loadedDocument = PDDocument.load(titleBlock);

    Assert.assertNotNull(loadedDocument);
    String text = new PDFTextStripper().getText(loadedDocument);

    loadedDocument.close();

    Assert.assertFalse(text.isEmpty());
    Assert.assertTrue(text.contains(user.getLogin()));
    Assert.assertTrue(text.contains(partIteration.getNumber()));
    Assert.assertTrue(text.contains(partIteration.getPartRevision().getDescription()));

}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
@Test
public void testPdfFromStringTo() throws Exception {

    // GIVEN an html template containing special characters that java stores in utf-16 internally
    Pdf pdf = pdfBuilder.build();
    pdf.addPage("<html><head><meta charset=\"utf-8\"></head><h1>Müller</h1></html>", PageType.htmlAsString);

    String tempFolder = temporaryFolder.newFolder().getPath();
    pdf.saveAs(tempFolder+"/output.pdf");

    // WHEN
    byte[] pdfBytes = pdf.getPDF();

    PDFParser parser = new PDFParser(new RandomAccessBufferedFileInputStream(new ByteArrayInputStream(pdfBytes)));

    // that is a valid PDF (otherwise an IOException occurs)
    parser.parse();
    PDFTextStripper pdfTextStripper = new PDFTextStripper();
    String pdfText = pdfTextStripper.getText(new PDDocument(parser.getDocument()));

    assertThat("document should contain the creditorName", pdfText, containsString("Müller"));
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
/**
 * Reads the PDF file and extracts the content and table of contents to text files.
 */
public static void extractFromPDF() throws IOException {

	PDDocument document = PDDocument.load(new File(MCV_PDF));
	PDFTextStripper stripper = new PDFTextStripper();

	// Extract the main contents
	stripper.setStartPage(15);
	String text = stripper.getText(document);
	Files.write(Paths.get(MCV_TXT), text.getBytes());

	// Extract the table of contents
	stripper.setStartPage(3);
	stripper.setEndPage(14);
	text = stripper.getText(document);
	Files.write(Paths.get(MCV_TXT_TOC), text.getBytes());

	document.close();
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
private PDF(String name, byte[] content) {
  this.content = content;

  try (InputStream inputStream = new ByteArrayInputStream(content)) {
    try (PDDocument pdf = PDDocument.load(inputStream)) {
      this.text = new PDFTextStripper().getText(pdf);
      this.numberOfPages = pdf.getNumberOfPages();
      this.author = pdf.getDocumentInformation().getAuthor();
      this.creationDate = pdf.getDocumentInformation().getCreationDate();
      this.creator = pdf.getDocumentInformation().getCreator();
      this.keywords = pdf.getDocumentInformation().getKeywords();
      this.producer = pdf.getDocumentInformation().getProducer();
      this.subject = pdf.getDocumentInformation().getSubject();
      this.title = pdf.getDocumentInformation().getTitle();
      this.encrypted = pdf.isEncrypted();
      
      PDSignature signature = pdf.getLastSignatureDictionary();
      this.signed = signature != null;
      this.signerName = signature == null ? null : signature.getName();
      this.signatureTime = signature == null ? null : signature.getSignDate();
    }
  }
  catch (Exception e) {
    throw new IllegalArgumentException("Invalid PDF file: " + name, e);
  }
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
public static String readPdf(InputStream is) throws Exception {
	PDDocument document = PDDocument.load(is);
	PDFTextStripper textStripper = new PDFTextStripper(); 
	return textStripper.getText(document);
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
public static String extractPdf(String path) throws IOException {
	// Loading an existing document

	File file = new File(path);
	PDDocument document = PDDocument.load(file);

	// Instantiate PDFTextStripper class
	PDFTextStripper pdfStripper = new PDFTextStripper();

	// Retrieving text from PDF document
	String text = pdfStripper.getText(document);
	document.close();
	return text;
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
@Test
public void createTitleBlockForDocumentIterationTest() throws Exception {
    DocumentTitleBlockData documentTitleData = new DocumentTitleBlockData(documentIteration, new Locale("en"));
    byte[] titleBlock = new TitleBlockWriter(documentTitleData).createTitleBlock();
    PDDocument loadedDocument = PDDocument.load(titleBlock);
    Assert.assertNotNull(loadedDocument);
    String text = new PDFTextStripper().getText(loadedDocument);
    loadedDocument.close();
    Assert.assertFalse(text.isEmpty());
    Assert.assertTrue(text.contains(user.getLogin()));
    Assert.assertTrue(text.contains(documentIteration.getId()));
    Assert.assertTrue(text.contains(documentIteration.getDocumentRevision().getDescription()));
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
List<TextPositionSequence> findSubwords(PDDocument document, int page, String searchTerm) throws IOException
{
    final List<TextPositionSequence> hits = new ArrayList<TextPositionSequence>();
    PDFTextStripper stripper = new PDFTextStripper()
    {
        @Override
        protected void writeString(String text, List<TextPosition> textPositions) throws IOException
        {
            System.out.printf("  -- %s\n", text);

            TextPositionSequence word = new TextPositionSequence(textPositions);
            String string = word.toString();

            int fromIndex = 0;
            int index;
            while ((index = string.indexOf(searchTerm, fromIndex)) > -1)
            {
                hits.add(word.subSequence(index, index + searchTerm.length()));
                fromIndex = index + 1;
            }
            super.writeString(text, textPositions);
        }
    };
    
    stripper.setSortByPosition(true);
    stripper.setStartPage(page);
    stripper.setEndPage(page);
    stripper.getText(document);
    return hits;
}
 

import org.apache.pdfbox.text.PDFTextStripper; //导入依赖的package包/类
/**
 * <a href="http://stackoverflow.com/questions/37862159/pdf-reading-via-pdfbox-in-java">
 * pdf reading via pdfbox in java 
 * </a>
 * <br/>
 * <a href="https://drive.google.com/file/d/0B_Ke2amBgdpedUNwVTR3RVlRTFE/view?usp=sharing">
 * PnL_500010_0314.pdf
 * </a>
 * <p>
 * Indeed, the <code>PDFTextStripper</code> is not even informed about those undecipherable
 * text sections. Essentially the underlying method `PDFTextStreamEngine.showGlyph` filters
 * all unmappable glyphs from composite fonts. 
 * </p>
 */
@Test
public void testPnL_500010_0314() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("PnL_500010_0314.pdf")    )
    {
        PDDocument document = PDDocument.load(resource);
        PDFTextStripper stripper = new PDFTextStripper();
        //stripper.setSortByPosition(true);
        String text = stripper.getText(document);

        System.out.printf("\n*\n* PnL_500010_0314.pdf\n*\n%s\n", text);
        Files.write(new File(RESULT_FOLDER, "PnL_500010_0314.txt").toPath(), Collections.singleton(text));
    }
}