Reading data in PDF using Java

Using Java to read data in PDF files: Step 1: Download The PDFBox-0.7.2.jar. Provide one: http://pdfhome.hope.com.cn/Resource.aspx? Cid = 63844604-5253-4ae1-b023-258c9e324061 & rid = 20cd8f94-1cee-40b6-a3df-0ef024f8e0d2 unzip the Lib file under the PDFBox-0.7.2.jar, PDFBox-0.7.2-log4j.jar put your classpath path. (I put the source code and jar package in the attachment below for your use .) Step 2: write a simple program for reading PDF files. (Pdfreader. Java) Import java. Io. file;
Import java. Io. fileoutputstream;
Import java. Io. outputstreamwriter;
Import java. Io. Writer;
Import java.net. malformedurlexception;
Import java.net. url;
Import orgdomainbox. pdmodel. pddocument;
Import orgshortbox. util. writable textstripper; public class pdfreader {public void readfdf (string file) throws exception {
// Sort or not
Boolean sort = false;
// PDF file name
String pdffile = file;
// Enter the text file name
String textfile = NULL;
// Encoding method
String encoding = "UTF-8 ";
// Start page Extraction
Int startpage = 1;
// End number of extracted pages
Int endpage = integer. max_value;
// File input stream to generate a text file
Writer output = NULL;
// PDF document stored in memory
Pddocument document = NULL;
Try {
Try {
// First load the file as a URL, and then load the file from the local file system if an exception occurs. //
URL url = new URL (pdffile); // note that the parameter is not a previous version of URL. But a file.
Document = pddocument. Load (pdffile );
// Obtain the PDF file name
String filename = URL. GetFile ();
// Name the generated TXT file with the original PDF name
If (filename. Length ()> 4 ){
File outputfile = new file (filename. substring (0, filename
. Length ()-4)
+ ". Txt ");
Textfile = outputfile. getname ();
}
} Catch (malformedurlexception e ){
// If an exception occurs when loading as a URL, load the file from the file system. // note that the parameter is not a URL. But a file in a previous version.
Document = pddocument. Load (pdffile );
If (pdffile. Length ()> 4) {textfile = pdffile. substring (0, pdffile. Length ()-4)
+ ". Txt ";
}
}
// File input stream, which is written into the file inverted textfile
Output = new outputstreamwriter (New fileoutputstream (textfile ),
Encoding );
// Extract textstripper to extract text
Optional textstripper stripper = NULL;
Stripper = new jsontextstripper ();
// Set whether to sort
Stripper. setsortbyposition (SORT );
// Set the start page
Stripper. setstartpage (startpage );
// Set the end page
Stripper. setendpage (endpage );
// Call javastextstripper's writetext to extract and output the text
Stripper. writetext (document, output );
} Finally {
If (output! = NULL ){
// Close the output stream
Output. Close ();
}
If (document! = NULL ){
// Close the PDF document
Document. Close ();
}
}
}/**
* @ Param ARGs
*/
Public static void main (string [] ARGs ){
// Todo auto-generated method stub
Pdfreader = new pdfreader ();
Try {
// Obtain the springguide.pdf content from the edrive
Pdfreader. readfdf ("E: // springguide.pdf ");
} Catch (exception e ){
E. printstacktrace ();
}
} This completes reading data from PDF. Generate a TXT file with the same name in the directory where your PDF file is located.