diff options
| author | tknall <tknall@7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c> | 2006-12-01 12:20:24 +0000 |
|---|---|---|
| committer | tknall <tknall@7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c> | 2006-12-01 12:20:24 +0000 |
| commit | 6025b6016517c6d898d8957d1d7e03ba71431912 (patch) | |
| tree | b15bd6fa5ffe9588a9bca3f2b8a7e358f83b6eba /src/main/java/org/pdfbox/examples/util/ExtractTextByArea.java | |
| parent | d2c77e820ab4aba8235d71275755021347b3ad10 (diff) | |
| download | pdf-as-3-6025b6016517c6d898d8957d1d7e03ba71431912.tar.gz pdf-as-3-6025b6016517c6d898d8957d1d7e03ba71431912.tar.bz2 pdf-as-3-6025b6016517c6d898d8957d1d7e03ba71431912.zip | |
Initial import of release 2.2.REL-2.2@923
git-svn-id: https://joinup.ec.europa.eu/svn/pdf-as/trunk@4 7b5415b0-85f9-ee4d-85bd-d5d0c3b42d1c
Diffstat (limited to 'src/main/java/org/pdfbox/examples/util/ExtractTextByArea.java')
| -rw-r--r-- | src/main/java/org/pdfbox/examples/util/ExtractTextByArea.java | 119 |
1 files changed, 119 insertions, 0 deletions
diff --git a/src/main/java/org/pdfbox/examples/util/ExtractTextByArea.java b/src/main/java/org/pdfbox/examples/util/ExtractTextByArea.java new file mode 100644 index 0000000..042e3e6 --- /dev/null +++ b/src/main/java/org/pdfbox/examples/util/ExtractTextByArea.java @@ -0,0 +1,119 @@ +/**
+ * Copyright (c) 2005, www.pdfbox.org
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice,
+ * this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright notice,
+ * this list of conditions and the following disclaimer in the documentation
+ * and/or other materials provided with the distribution.
+ * 3. Neither the name of pdfbox; nor the names of its
+ * contributors may be used to endorse or promote products derived from this
+ * software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * http://www.pdfbox.org
+ *
+ */
+package org.pdfbox.examples.util;
+
+import org.pdfbox.exceptions.InvalidPasswordException;
+
+import org.pdfbox.pdmodel.PDDocument;
+import org.pdfbox.pdmodel.PDPage;
+import org.pdfbox.util.PDFTextStripperByArea;
+
+import java.awt.Rectangle;
+
+import java.util.List;
+
+/**
+ * This is an example on how to extract text from a specific area on the PDF document.
+ *
+ * Usage: java org.pdfbox.examples.util.ExtractTextByArea <input-pdf>
+ *
+ * @author Ben Litchfield (ben@benlitchfield.com)
+ * @version $Revision: 1.1 $
+ */
+public class ExtractTextByArea
+{
+ private ExtractTextByArea()
+ {
+ //utility class and should not be constructed.
+ }
+
+
+ /**
+ * This will print the documents text in a certain area.
+ *
+ * @param args The command line arguments.
+ *
+ * @throws Exception If there is an error parsing the document.
+ */
+ public static void main( String[] args ) throws Exception
+ {
+ if( args.length != 1 )
+ {
+ usage();
+ }
+ else
+ {
+ PDDocument document = null;
+ try
+ {
+ document = PDDocument.load( args[0] );
+ if( document.isEncrypted() )
+ {
+ try
+ {
+ document.decrypt( "" );
+ }
+ catch( InvalidPasswordException e )
+ {
+ System.err.println( "Error: Document is encrypted with a password." );
+ System.exit( 1 );
+ }
+ }
+ PDFTextStripperByArea stripper = new PDFTextStripperByArea();
+ stripper.setSortByPosition( true );
+ Rectangle rect = new Rectangle( 10, 280, 275, 60 );
+ stripper.addRegion( "class1", rect );
+ List allPages = document.getDocumentCatalog().getAllPages();
+ PDPage firstPage = (PDPage)allPages.get( 0 );
+ stripper.extractRegions( firstPage );
+ System.out.println( "Text in the area:" + rect );
+ System.out.println( stripper.getTextForRegion( "class1" ) );
+
+ }
+ finally
+ {
+ if( document != null )
+ {
+ document.close();
+ }
+ }
+ }
+ }
+
+ /**
+ * This will print the usage for this document.
+ */
+ private static void usage()
+ {
+ System.err.println( "Usage: java org.pdfbox.examples.util.ExtractTextByArea <input-pdf>" );
+ }
+
+}
\ No newline at end of file |