使用 Java 解析 PDF 與 GroupDocs.Parser

<repositories>
   <repository>
      <id>repository.groupdocs.com</id>
      <name>GroupDocs Repository</name>
      <url>https://releases.groupdocs.com/parser/java/</url>
   </repository>
</repositories>

<dependencies>
   <dependency>
      <groupId>com.groupdocs</groupId>
      <artifactId>groupdocs-parser</artifactId>
      <version>25.5</version>
   </dependency>
</dependencies>

import com.groupdocs.parser.Parser;

public class PdfParserExample {
    public static void main(String[] args) {
        try (Parser parser = new Parser("path/to/your/document.pdf")) {
            // Your parsing logic here
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

import com.groupdocs.parser.templates.*;

private static Template getTemplate() {
    // Fixed position for "FromCompany"
    TemplateItem fromCompany = new TemplateField(
        new TemplateFixedPosition(new Rectangle(new Point(35, 135), new Size(100, 10))),
        "FromCompany");

    // Regex‑based field for "Invoice Number"
    TemplateItem invoiceNumber = new TemplateField(
        new TemplateRegexPosition("Invoice Number"),
        "InvoiceNumber");
    
    // Linked position for extracting the value next to the label
    TemplateItem invoiceNumberValue = new TemplateField(
        new TemplateLinkedPosition(invoiceNumber,
            new Size(200, 15),
            new TemplateLinkedPositionEdges(false, false, true, false)),
        "InvoiceNumberValue");

    // Define table parameters for line items
    TemplateTableParameters detailsTableParameters = new TemplateTableParameters(
        new Rectangle(new Point(35, 320), new Size(530, 55)), null);

    // Return the assembled template
    return new Template(java.util.Arrays.asList(
        fromCompany,
        invoiceNumber,
        invoiceNumberValue,
        new TemplateTable(detailsTableParameters, "details", null)));
}

import com.groupdocs.parser.Parser;
import com.groupdocs.parser.data.DocumentData;
import com.groupdocs.parser.data.PageTextArea;

public class PdfParserExample {
    public static void main(String[] args) {
        try (Parser parser = new Parser("path/to/your/document.pdf")) {
            Template template = getTemplate();
            DocumentData data = parser.parseByTemplate(template);

            if (data != null) {
                for (int i = 0; i < data.getCount(); i++) {
                    PageTextArea area = data.get(i).getPageArea() instanceof PageTextArea
                            ? (PageTextArea) data.get(i).getPageArea()
                            : null;
                    System.out.println(data.get(i).getName() + ": " +
                        (area == null ? "Not a template field" : area.getText()));
                }
            } else {
                System.out.println("Parse Document by Template isn't supported.");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}