maven导入包
org.apache.pdfbox pdfbox 2.0.8 com.sleepycat je 5.0.73 com.github.jai-imageio jai-imageio-jpeg2000 1.3.0
PdfUtil.java
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import javax.imageio.ImageIO;
import lombok.extern.slf4j.Slf4j;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.text.PDFTextStripper;
@Slf4j
public class PdfUtil {
public static int getNumberOfPages(String filePath) throws IOException, InterruptedException {
File file = new File(filePath);
PDDocument pdDocument = PDDocument.load(new File(filePath));
int pages = pdDocument.getNumberOfPages();
pdDocument.close();
return pages;
}
public static String getContent(String filePath) throws IOException {
PDFParser pdfParser =
new PDFParser(new org.apache.pdfbox.io.RandomAccessFile(new File(filePath), "rw"));
pdfParser.parse();
PDDocument pdDocument = pdfParser.getPDDocument();
String text = new PDFTextStripper().getText(pdDocument);
pdDocument.close();
return text;
}
public static void getPdfImage(String filePath, String outPath) throws IOException {
// 利用PdfBox生成图像
List list = new ArrayList<>();
PDDocument pdDocument = PDDocument.load(new File(filePath));
PDFRenderer renderer = new PDFRenderer(pdDocument);
int pages = pdDocument.getNumberOfPages();
for (int i = 0; i < pages; i++) {
// 构造图片
File file = new File(outPath);
if (!file.exists()) {
file.mkdirs();
}
String fileName = outPath + "/" + (i + 1) + ".png";
BufferedImage image = renderer.renderImageWithDPI(i, 96); // Windows native DPI
ImageIO.write(image, "PNG", new File(fileName));
list.add(fileName);
}
// Warning: You did not close a PDF Document
pdDocument.close();
}
}
测试代码
import java.io.IOException;
public class PdfTest {
public static void main(String[] args) throws IOException, InterruptedException {
int numberOfPages =
PdfUtil.getNumberOfPages("D:\workspace\service-api\xyd-client\data1.pdf");
System.out.println(numberOfPages);
String content = PdfUtil.getContent("D:\workspace\service-api\xyd-client\data1.pdf");
System.out.println(content);
PdfUtil.getPdfImage(
"D:\workspace\service-api\xyd-client\data1.pdf",
"D:\workspace\service-api\xyd-client\data1.pdf.png");
}
}



