Package org.pdfbox.util

Examples of org.pdfbox.util.PDFTextStripper

79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
     */
    public void doTestFile(File file, boolean bLogResult)
        throws Exception
    {

        PDFTextStripper stripper = new PDFTextStripper();
        OutputStream os = null;
        Writer writer = null;
        PDDocument document = null;
        try
        {
            document = PDDocument.load(file);

            File outFile = new File(file.getParentFile().getParentFile(), "output/" + file.getName() + ".txt");
            os = new FileOutputStream(outFile);
            writer = new OutputStreamWriter(os);

            stripper.writeText(document, writer);
        }
        finally
        {
            if( writer != null )
            {
View Full Code Here
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
                        output = new OutputStreamWriter(
                            new FileOutputStream( textFile ) );
                    }
                }
   
                PDFTextStripper stripper = null;
                if(toHTML)
                {
                   stripper = new PDFText2HTML();
                }
                else
                {
                   stripper = new PDFTextStripper();
                }
                stripper.setSortByPosition( sort );
                stripper.setStartPage( startPage );
                stripper.setEndPage( endPage );
                stripper.writeText( document, output );
            }
            finally
            {
                if( output != null )
                {
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
                        PDDocument document = parser.getPDDocument();
                        try {
                            CharArrayWriter writer = new CharArrayWriter();

                            PDFTextStripper stripper = new PDFTextStripper();
                            stripper.setLineSeparator("\n");
                            stripper.writeText(document, writer);

                            delegate = new CharArrayReader(writer.toCharArray());
                        } finally {
                            document.close();
                        }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
                        PDDocument document = parser.getPDDocument();
                        try {
                            CharArrayWriter writer = new CharArrayWriter();

                            PDFTextStripper stripper = new PDFTextStripper();
                            stripper.setLineSeparator("\n");
                            stripper.writeText(document, writer);

                            delegate = new CharArrayReader(writer.toCharArray());
                        } finally {
                            document.close();
                        }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
        //Just try using the default password and move on
        pdf.openProtection(new StandardDecryptionMaterial(""));
      }

      // collect text
      PDFTextStripper stripper = new PDFTextStripper();
      text = stripper.getText(pdf);

      // collect title
      PDDocumentInformation info = pdf.getDocumentInformation();
      title = info.getTitle();
      // more useful info, currently not used. please keep them for future use.
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
   * @return Reader a reader that is fed to an indexer.
   */
  protected Reader getReader(InputStream docStream)
  {
   
    PDFParser parser = null; PDDocument document = null; PDFTextStripper stripper = null;
    CharArrayWriter writer = null;
    try{
      parser = new PDFParser(docStream);
      parser.parse();
      document = parser.getPDDocument();
      writer = new CharArrayWriter();
      stripper = new PDFTextStripper();
      stripper.setLineSeparator("\n");
      stripper.writeText(document, writer);
      document.close();
      writer.close();
      parser.getDocument().close();
      return new CharArrayReader(writer.toCharArray());
    }catch (Exception e){
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
        //Just try using the default password and move on
        decryptor.decryptDocument("");
      }

      // collect text
      PDFTextStripper stripper = new PDFTextStripper();
      text = stripper.getText(pdf);

      // collect title
      PDDocumentInformation info = pdf.getDocumentInformation();
      title = info.getTitle();
      // more useful info, currently not used. please keep them for future use.
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
103
104
         catch (IOException e)
         {
            return "";
         }

         PDFTextStripper stripper = new PDFTextStripper();
         stripper.setStartPage(1);
         stripper.setEndPage(Integer.MAX_VALUE);
         stripper.writeText(pdDocument, sw);
      }
      finally
      {
         if (pdDocument != null)
            try
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
   
                PDDocument document = parser.getPDDocument();
   
                CharArrayWriter writer = new CharArrayWriter();
   
                PDFTextStripper stripper = new PDFTextStripper();
                stripper.setLineSeparator("\n");
                stripper.writeText(document, writer);
   
                document.close();
                writer.close();
               
                Map result = new HashMap();
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
108
        //Just try using the default password and move on
        decryptor.decryptDocument("");
      }

      // collect text
      PDFTextStripper stripper = new PDFTextStripper();
      text = stripper.getText(pdf);

      // collect title
      PDDocumentInformation info = pdf.getDocumentInformation();
      title = info.getTitle();
      // more useful info, currently not used. please keep them for future use.
View Full Code Here
TOP

Related Classes of org.pdfbox.util.PDFTextStripper

  • br.com.caelum.stella.boleto.transformer.BoletoTransformerIntegrationTest
  • com.canoo.webtest.plugins.pdftest.htmlunit.pdfbox.PdfBoxPDFPage
  • com.stimulus.archiva.extraction.PDFExtractor
  • com.stimulus.archiva.persistence.textextraction.PDFExtractor
  • de.spotnik.mail.core.message.content.PDFHandler
  • edu.udo.cs.wvtool.generic.inputfilter.PDFInputFilter
  • eu.lsem.bakalarka.filetypeprocess.document.PdfDocumentParser
  • eu.planets_project.services.migration.pdfbox.TextExtractor
  • it.unimi.dsi.mg4j.document.PdfDocumentFactory
  • net.fp.rp.search.back.extractor.PdfDataExtractor
    • 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.