<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.com/nexus/content/groups/public/</url>
    </repository>
</repositories>
<dependency>
    <groupId>e-iceblue</groupId>
    <artifactId>spire.pdf</artifactId>
    <version>11.11.11</version>
</dependency>

import com.spire.pdf.PdfDocument;

public class loadPDF {
    public static void main(String[] args) {

        // 創建 PdfDocument 實例
        PdfDocument pdf = new PdfDocument();
        // 加載 PDF 文件
        pdf.loadFromFile("sample.pdf");

        // 獲取頁面總數
        int pageCount = pdf.getPages().getCount();
        System.out.println("總頁數： " + pageCount);
    }
}

import com.spire.pdf.PdfDocument;
import com.spire.pdf.texts.PdfTextExtractOptions;
import com.spire.pdf.texts.PdfTextExtractor;

public class extractPdfText {
    public static void main(String[] args) {

        // 創建並加載 PDF 文檔
        PdfDocument pdf = new PdfDocument();
        pdf.loadFromFile("sample1.pdf");

        // 使用 StringBuilder 高效累積解析結果
        StringBuilder extractedText = new StringBuilder();

        // 配置文本解析選項
        PdfTextExtractOptions options = new PdfTextExtractOptions();

        // 啓用簡化解析模式，提高文本可讀性
        options.setSimpleExtraction(true);

        // 遍歷 PDF 中的每一頁
        for (int i = 0; i < pdf.getPages().getCount(); i++) {

            // 為當前頁面創建文本解析器
            PdfTextExtractor extractor =
                    new PdfTextExtractor(pdf.getPages().get(i));

            // 按配置選項解析當前頁面文本
            String pageText = extractor.extract(options);

            // 追加到結果緩衝區
            extractedText.append(pageText).append("\n");
        }

        // 此時 extractedText 已包含完整文本內容，
        // 可用於存儲、索引或後續處理
        System.out.println(extractedText.toString());
    }
}

import com.spire.pdf.PdfDocument;
import com.spire.pdf.utilities.PdfTable;
import com.spire.pdf.utilities.PdfTableExtractor;

public class extractPdfTable {
    public static void main(String[] args) {

        // 載入 PDF 文檔
        PdfDocument pdf = new PdfDocument();
        pdf.loadFromFile("sample1.pdf");

        // 創建 PdfTableExtractor 對象
        PdfTableExtractor extractor = new PdfTableExtractor(pdf);

        // 從第一頁解析表格（頁索引從 0 開始）
        PdfTable[] tables = extractor.extractTable(0);

        // 遍歷表格
        if (tables != null) {
            for (PdfTable table : tables) {

                // 獲取表格的行數和列數
                int rowCount = table.getRowCount();
                int columnCount = table.getColumnCount();

                System.out.println("Rows: " + rowCount +
                        ", Columns: " + columnCount);

                StringBuilder tableData = new StringBuilder();
                for (int i = 0; i < rowCount; i++) {
                    for (int j = 0; j < columnCount; j++) {

                        // 獲取單元格數據
                        tableData.append(table.getText(i, j));

                        if (j < columnCount - 1) {
                            tableData.append("\t");
                        }
                    }
                    if (i < rowCount - 1) {
                        tableData.append("\n");
                    }
                }

                System.out.println(tableData.toString());
            }
        }
    }
}

import com.spire.pdf.PdfDocument;
import com.spire.pdf.utilities.PdfImageHelper;
import com.spire.pdf.utilities.PdfImageInfo;

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;

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

        // 載入 PDF 文檔
        PdfDocument pdf = new PdfDocument();
        pdf.loadFromFile("sample1.pdf");

        // 創建 PdfImageHelper 對象
        PdfImageHelper imageHelper = new PdfImageHelper();

        // 遍歷每一頁
        for (int i = 0; i < pdf.getPages().getCount(); i++) {

            // 獲取當前頁的圖片信息
            PdfImageInfo[] imageInfos =
                    imageHelper.getImagesInfo(pdf.getPages().get(i));

            if (imageInfos != null) {
                for (int j = 0; j < imageInfos.length; j++) {

                    // 獲取指定圖片
                    BufferedImage image = imageInfos[j].getImage();

                    // 保存圖片為 PNG 文件
                    File output = new File(
                            "output/images/page_" + i + "_image_" + j + ".png"
                    );
                    ImageIO.write(image, "PNG", output);
                }
            }
        }
    }
}

import com.spire.pdf.PdfDocument;

public class parsePdfMetadata {
    public static void main(String[] args) {

        // 載入 PDF 文檔
        PdfDocument pdf = new PdfDocument();
        pdf.loadFromFile("sample1.pdf");

        // 獲取 PDF 文檔元數據信息
        String title = pdf.getDocumentInformation().getTitle();
        String author = pdf.getDocumentInformation().getAuthor();
        String subject = pdf.getDocumentInformation().getSubject();
        String keywords = pdf.getDocumentInformation().getKeywords();
        String creator = pdf.getDocumentInformation().getCreator();
        String producer = pdf.getDocumentInformation().getProducer();

        String creationDate = pdf.getDocumentInformation()
                .getCreationDate().toString();
        String modificationDate = pdf.getDocumentInformation()
                .getModificationDate().toString();

        System.out.println(
                "Title: " + title +
                        "\nAuthor: " + author +
                        "\nSubject: " + subject +
                        "\nKeywords: " + keywords +
                        "\nCreator: " + creator +
                        "\nProducer: " + producer +
                        "\nCreation Date: " + creationDate +
                        "\nModification Date: " + modificationDate
        );
    }
}