解析pdf

最新推荐文章于 2024-02-28 19:54:04 发布

千硕

最新推荐文章于 2024-02-28 19:54:04 发布

阅读量174

点赞数

文章标签： java

本文链接：https://blog.csdn.net/weixin_42469936/article/details/121128335

版权

1、maven

		<repositories>
			<repository>
				<id>com.e-iceblue</id>
				<name>e-iceblue</name>
				<url>http://repo.e-iceblue.com/nexus/content/groups/public/</url>
				</repository>
			</repositories>
		<dependency>
            <groupId> e-iceblue </groupId>
            <artifactId>spire.pdf</artifactId>
            <version>2.2.0</version>
        </dependency>
        <dependency>
            <groupId>e-iceblue</groupId>
            <artifactId>spire.pdf.free</artifactId>
            <version>2.2.2</version>
        </dependency>

2、代码

public static void main(String[] args)  {
        try {
            PdfDocument doc = new PdfDocument();
            doc.loadFromFile("C:\\Users\\EDZ\\Desktop\\测试.pdf");
            StringBuilder sb = new StringBuilder();
            PdfPageBase page;
            for (int i = 0; i < doc.getPages().getCount(); i++) {
                //获取每一行的page对象
                page = doc.getPages().get(i);
                sb.append(page.extractText(true));
                //这个if中是图片的解析输出
                if (page.extractImages() != null) {
                    for (BufferedImage image : page.extractImages()) {
                        if (image != null) {
                            //指定输出图片名，指定图片格式,后缀自己换
                            File output = new File("D:\\pdf\\img.png");
                            ImageIO.write(image, "PNG", output);
                        }
                    }
                }
            }
            System.out.println(sb);
            doc.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }