项目用打印出来的pdf需要电子化处理。就用到了读取pdf内容，合并pdf文件，以及拆分pdf的处理。

废话不多说，直接上代码。

import java.io.File;
import java.io.IOException;
import java.util.List;

import org.apache.pdfbox.multipdf.Splitter;
import org.apache.pdfbox.pdmodel.PDDocument;

public class PdfSplit {

public static void main(String[] args) throws IOException {
try {
Splitter splitter = new Splitter();
PDDocument source = PDDocument.load(new File(“C:/temp/combine.pdf”));

List<PDDocument> documents = splitter.split(source);

int i = 0;
for (PDDocument document : documents) {
i++;
document.save(“C:/temp/split/” + “out” + i + “.pdf”);
}
} finally {

}
}
}

========================================

合并多个pdf 为1个pdf文件

import java.io.File;
import java.io.IOException;

import org.apache.pdfbox.io.MemoryUsageSetting;
import org.apache.pdfbox.multipdf.PDFMergerUtility;

public class PdfCombining {

public static void main(String[] args) throws IOException {
try {
PDFMergerUtility merger = new PDFMergerUtility();
merger.addSource(new File(“C:/temp/test_excel.pdf”));
merger.addSource(new File(“C:/temp/test_word.pdf”));
merger.addSource(new File(“C:/temp/test_ppt.pdf”));
merger.setDestinationFileName(“C:/temp/office3page.pdf”);
merger.mergeDocuments(MemoryUsageSetting.setupTempFileOnly());
}finally {
System.out.println(“combining end”);
}
}
}

========================================

读取pdf上面的内容

import java.io.File;
import java.io.IOException;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

public class PdfGetStr {

public static final void main(String[] args) throws IOException {

File file = new File(“C:/temp/office3page.pdf”);

PDDocument document = PDDocument.load(file);
int lastPage = document.getNumberOfPages();
System.out.println(“pageNum：” + document.getNumberOfPages());

PDFTextStripper stripper = new PDFTextStripper();
stripper.setStartPage(0);
stripper.setEndPage(3);
String text = stripper.getText(document);

System.out.println(text);
}

}