Package com.itextpdf.text.pdf

Examples of com.itextpdf.text.pdf.PdfReader

85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
      PdfCopy writer = new PdfCopy(document, outputStream);

      document.open();

      for (InputStream source : sources) {
        PdfReader reader = new PdfReader(source);
        int pageCount = reader.getNumberOfPages();
        for (int i = 1; i <= pageCount; i++) {
          PdfImportedPage page = writer.getImportedPage(reader, i);
          writer.addPage(page);
        }
        reader.close();
      }

      document.close();
      writer.close();
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
  public InputStream[] split(final InputStream source, final int size) throws IOException {
    try {
      Assert.notNull(source, "source");
      Assert.greaterThan(size, 0, "size");

      PdfReader reader = new PdfReader(source);
      int pageCount = reader.getNumberOfPages();
      List<InputStream> list = new LinkedList<InputStream>();

      Document document = null;
      InputOutputStream outputStream = null;
      PdfCopy writer = null;
      for (int i = 1; i <= pageCount; i++) {
        if ((document == null) || (i % size == 0)) {
          if (document != null) {
            document.close();
            writer.close();
            list.add(outputStream.getInputStream());
          }
          document = new Document(reader.getPageSizeWithRotation(1));
          outputStream = new InputOutputStream();
          writer = new PdfCopy(document, outputStream);
        }
        PdfImportedPage page = writer.getImportedPage(reader, i);
        writer.addPage(page);
      }

      if (document != null) {
        document.close();
        writer.close();
        list.add(outputStream.getInputStream());
      }

      reader.close();

      return list.toArray(new InputStream[list.size()]);
    } catch (DocumentException e) {
      throw new br.net.woodstock.rockframework.office.DocumentException(e);
    }
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
  @Override
  public String getText(final InputStream source) throws IOException {
    Assert.notNull(source, "source");

    PdfReader reader = new PdfReader(source);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    TextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
    int pageCount = reader.getNumberOfPages();
    ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
    PrintWriter writer = new PrintWriter(outputStream);

    for (int i = 1; i <= pageCount; i++) {
      TextExtractionStrategy result = parser.processContent(i, strategy);
      String pageText = result.getResultantText();
      writer.println(pageText);
    }

    reader.close();
    writer.close();

    String text = new String(outputStream.toByteArray());
    return text;
  }
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
          document.add(img);
          document.close();

          // Second - read the memory based PDF file and read the image. Write
          // this into PNG file.
          PdfReader reader = new PdfReader(baos.toByteArray());
          for (int j = 0; j < reader.getXrefSize(); j++) {
            PdfObject pdfobj = reader.getPdfObject(j);
            if (pdfobj != null) {
              if (pdfobj.isStream()) {
                PdfStream stream = (PdfStream) pdfobj;
                PdfObject pdfsubtype = stream.get(PdfName.SUBTYPE);
                if (pdfsubtype != null) {
                  if (pdfsubtype.toString().equals(PdfName.IMAGE.toString())) {
                    PdfImageObject image = new PdfImageObject((PRStream) stream);
                    BufferedImage bufferedImage = image.getBufferedImage();
                    if (bufferedImage != null) {
                      String pngName = IdUtils.getUniqueID() + ".png";
                      File pngFile = new File(tmpDirectory, pngName);
                      FileOutputStream out = new FileOutputStream(pngFile);
                      ImageIO.write(bufferedImage, "png", out);
                      out.close();
                      list.add(pngFile);
                    }
                  }
                }
              }
            }
          }
          reader.close();
        } catch (Exception exception) {
          // Ignore - the page may be corrupt.
        }
      }
    }
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
   * @param pdfFile File object with pdf file.
   * @return Text content of the pdf file.
   * @throws IOException
   */
  public static String getTextFromPdfFile(File pdfFile) throws IOException {
    PdfReader pdfReader = new PdfReader(pdfFile.getCanonicalPath());
    String content = "";
    for (int i = 0; i < pdfReader.getNumberOfPages(); i++) {
      String pageContent;
      try {
        pageContent = PdfTextExtractor.getTextFromPage(pdfReader, i + 1);
      }
      catch (Exception e) {
        // LogUtils.log(e);
        pageContent = null;
      }
      if (pageContent != null) {
        pageContent = pageContent.trim();
        if (pageContent.length() > 0) {
          if (i > 0) {
            content += "\r\n\r\n";
          }
          content += pageContent;
        }
      }
    }
    pdfReader.close();
    return content;
  }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
                InputStream is = resolveAndOpenStream(uriStr);
                if (is != null) {
                    try {
                        URI uri = new URI(uriStr);
                        if (uri.getPath() != null && uri.getPath().toLowerCase().endsWith(".pdf")) {
                            PdfReader reader = _outputDevice.getReader(uri);
                            PDFAsImage image = new PDFAsImage(uri);
                            Rectangle rect = reader.getPageSizeWithRotation(1);
                            image.setInitialWidth(rect.getWidth() * _outputDevice.getDotsPerPoint());
                            image.setInitialHeight(rect.getHeight() * _outputDevice.getDotsPerPoint());
                            resource = new ImageResource(uriStr, image);
                        } else {
                            Image image = Image.getInstance(readStream(is));
View Full Code Here
843
844
845
846
847
848
849
850
851
852
853
        }
    }

    private void drawPDFAsImage(PDFAsImage image, int x, int y) {
        URI uri = image.getURI();
        PdfReader reader = null;

        try {
            reader = getReader(uri);
        } catch (IOException e) {
            throw new XRRuntimeException("Could not load " + uri + ": " + e.getMessage(), e);
View Full Code Here
874
875
876
877
878
879
880
881
882
883
884
885
        _currentPage.addTemplate(page, (float) mx[0], (float) mx[1], (float) mx[2], (float) mx[3], (float) mx[4], (float) mx[5]);
        _currentPage.saveState();
    }

    public PdfReader getReader(URI uri) throws IOException {
        PdfReader result = (PdfReader) _readerCache.get(uri);
        if (result == null) {
            result = new PdfReader(getSharedContext().getUserAgentCallback().getBinaryResource(uri.toString()));
            _readerCache.put(uri, result);
        }
        return result;
    }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
   
    public ExtractorPDFContent() {
    }
   
    protected boolean innerExtract(CrawlURI curi){
        PdfReader documentReader;
        ArrayList<String> uris = new ArrayList<String>();
       
        try {
            documentReader = new PdfReader(curi.getRecorder().getContentReplayInputStream());

            for(int i=1; i<= documentReader.getNumberOfPages(); i++) { //Page numbers start at 1
                String pageParseText = extractPageText(documentReader,i);
                Matcher matcher = URLPattern.matcher(pageParseText);

                while(matcher.find()) {
                    String prospectiveURL = pageParseText.substring(matcher.start(),matcher.end()).trim();
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
38
39
40
    static int countPagesInPdf(String candidate) {

        // LOGGER.log(Level.INFO, System.getProperty("user.dir"));

        PdfReader reader = null;
        try {
            reader = new PdfReader(candidate);
        } catch (IOException e) {
            LOGGER.log(Level.SEVERE, "Exception: file not found - therefore I cannot count pages", e);
        }

        return reader.getNumberOfPages();
    }
View Full Code Here
TOP

Related Classes of com.itextpdf.text.pdf.PdfReader

  • aero.m_click.mcpdf.Main
  • at.fhj.itm.util.PDFUtil
  • br.com.objectos.way.boleto.PdfToText
  • br.net.woodstock.rockframework.document.pdf.itextpdf.CutProcessor
  • br.net.woodstock.rockframework.document.pdf.itextpdf.GetTextProcessor
  • br.net.woodstock.rockframework.document.pdf.itextpdf.IText
  • br.net.woodstock.rockframework.document.pdf.itextpdf.MergeProcessor
  • br.net.woodstock.rockframework.document.pdf.itextpdf.SplitProcessor
  • br.net.woodstock.rockframework.office.pdf.impl.ITextManager
  • br.net.woodstock.rockframework.security.sign.impl.PDFSigner
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.