java 读取PDF文本，获取CA签章信息并定位页面索引

本文链接：https://blog.csdn.net/qq_45503106/article/details/114628785

1、介绍
使用Spire组件，参考：Spire帮助文档；分为免费版和付费版，根据自己需求而定
2、依赖

	<repositories>
        <repository>
            <id>com.e-iceblue</id>
            <url>http://repo.e-iceblue.cn/repository/maven-public/</url>
        </repository>
    </repositories>
    
	<dependency>
            <groupId>e-iceblue</groupId>
            <artifactId>spire.pdf</artifactId>
            <version>3.11.6</version>
    </dependency>

3、获取CA签章信息

	PdfDocument pdf = new PdfDocument();
    pdf.loadFromFile("PDF Path");//加载PDF文件
    //获取域集合
    PdfFormWidget widgets = (PdfFormWidget) pdf.getForm();
    PdfFormFieldWidgetCollection fieldWidgetCollection = widgets.getFieldsWidget();
   	for (int i = 0; i < fieldWidgetCollection.getCount(); i++) {
         PdfFieldWidget widget = (PdfFieldWidget) fieldWidgetCollection.get(i);
         if (widget instanceof PdfSignatureFieldWidget) {
             PdfSignatureFieldWidget signatureFieldWidget = (PdfSignatureFieldWidget) widget;
             //获取签名
             PdfSignature signature = signatureFieldWidget.getSignature();
             String location = signature.getLocationInfo();
             String reason = signature.getReason();
             String data = signature.getDate().toString();
             String name = signature.getSignatureName();
             PdfPageBase page = signatureFieldWidget.getPage();
             System.out.println("签名位置信息：" + location + "\n" +
                     "签名原因：" + reason + "\n" +
                     "签名日期：" + data + "\n" +
                     "签名人：" + name + "\n" +
                     "文档中的签名坐标：X = " + signatureFieldWidget.getLocation().getX() + "  Y = " + signatureFieldWidget.getLocation().getY()
             );

             //获取页面索引
             int pageIndex = pdf.getPages().indexOf(page) + 1;
             System.out.println("签名所在页：" + pageIndex);
          }
    }

4.获取PDF文本

		//创建PdfDocument实例
        PdfDocument doc = new PdfDocument();
        //加载PDF文件
        doc.loadFromFile("PDF Path");
        StringBuilder sb = new StringBuilder();
        PdfPageBase page;
        //遍历PDF页面，获取每个页面的文本并添加到StringBuilder对象
        for (int i = 0; i < doc.getPages().getCount(); i++) {
            page = doc.getPages().get(i);
            sb.append(page.extractText(true));
        }
        System.out.println(sb);