Java自动化提取PDF表格的全场景实现

<repositories>
    <repository>
        <id>com.e-iceblue</id>
        <name>e-iceblue</name>
        <url>https://repo.e-iceblue.cn/repository/maven-public/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>e-iceblue</groupId>
        <artifactId>spire.pdf</artifactId>
        <version>11.12.16</version>
    </dependency>
</dependencies>

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

import java.io.FileWriter;
import java.io.IOException;

public class ExtractTable {
    public static void main(String[] args)throws IOException {
        // 实例化PdfDocument类的对象
        PdfDocument pdf = new PdfDocument();

        // 加载PDF文档
        pdf.loadFromFile("E:/Administrator/Python1/input/项目进度.pdf");

        // 创建StringBuilder类的实例
        StringBuilder builder = new StringBuilder();

        // 创建PdfTableExtractor类的对象
        PdfTableExtractor extractor = new PdfTableExtractor(pdf);

        // 遍历每一页
        for (int page = 0; page < pdf.getPages().getCount(); page++)
        {
            // 提取页面中的表格存入PdfTable[]数组
            PdfTable[] tableLists = extractor.extractTable(page);
            if (tableLists != null && tableLists.length > 0)
            {
                //遍历表格
                for (PdfTable table : tableLists)
                {
                    int row = table.getRowCount();//获取表格行
                    int column = table.getColumnCount();//获取表格列
                    for (int i = 0; i < row; i++)
                    {
                        for (int j = 0; j < column; j++)
                        {
                            // 获取表格中的文本内容
                            String text = table.getText(i, j);

                            // 将获取的text写入StringBuilder容器
                            builder.append(text+" ");
                        }
                        builder.append("\r\n");
                    }
                }
            }
        }

        // 保存为txt文档
        FileWriter fileWriter = new FileWriter("E:/Administrator/Python1/output/提取表格为文本.txt");
        fileWriter.write(builder.toString());
        fileWriter.flush();
        fileWriter.close();
    }
}

import com.spire.pdf.*;  
import com.spire.pdf.utilities.*;  
  
import java.io.*;  
  
public class ExtractTable {  
    public static void main(String[] args) throws Exception {  
        // 1. 加载 PDF 文档  
        PdfDocument pdf = new PdfDocument();  
        // 请确保路径正确  
        pdf.loadFromFile("E:/Administrator/Python1/input/项目进度.pdf");  
  
        // 用于存储提取文本的 StringBuilder        StringBuilder sb = new StringBuilder();  
  
        // 2. 遍历每一页并提取表格  
        for (int i = 0; i < pdf.getPages().getCount(); i++) {  
            PdfTableExtractor extractor = new PdfTableExtractor(pdf);  
            PdfTable[] tableLists = extractor.extractTable(i);  
  
            if (tableLists != null) {  
                for (PdfTable table : tableLists) {  
                    for (int row = 0; row < table.getRowCount(); row++) {  
                        for (int col = 0; col < table.getColumnCount(); col++) {  
                            // 使用工具方法处理 CSV 特殊字符和换行  
                            String cellText = escapeCsvField(table.getText(row, col));  
                            sb.append(cellText);  
  
                            // 列之间用逗号分隔  
                            if (col < table.getColumnCount() - 1) {  
                                sb.append(",");  
                            }  
                        }  
                        // 行之间用换行符分隔  
                        sb.append("\n");  
                    }  
                }  
            }  
        }  
  
        // 3. 写入带 BOM 的 CSV 文件  
        File outFile = new File("E:/Administrator/Python1/output/提取表格为csv.csv");  
  
        // 确保输出目录存在  
        if (!outFile.getParentFile().exists()) {  
            outFile.getParentFile().mkdirs();  
        }  
  
        try (FileOutputStream fos = new FileOutputStream(outFile)) {  
            // 【核心修复】写入 UTF-8 BOM 字节，防止 Excel 打开乱码  
            fos.write(0xEF);  
            fos.write(0xBB);  
            fos.write(0xBF);  
  
            // 使用 UTF-8 编码包装输出流  
            try (Writer writer = new OutputStreamWriter(fos, "UTF-8")) {  
                writer.write(sb.toString());  
            }  
        }  
  
        pdf.close();  
        System.out.println("PDF 表格已成功导出为 CSV 文件。");  
    }  
  
    /**  
     * 处理 CSV 字段的工具方法：  
     * 1. 去除单元格内的换行符  
     * 2. 转义双引号  
     * 3. 对包含特殊字符的字段添加双引号包裹  
     */  
    private static String escapeCsvField(String text) {  
        if (text == null) return "";  
  
        // 去掉单元格内的换行符（防止破坏 CSV 行结构）  
        text = text.replaceAll("[\\n\\r]", " ");  
  
        // 处理特殊字符  
        boolean containsSpecialChar = text.contains(",") || text.contains(";") ||  
                text.contains("\"") || text.contains("\n");  
  
        if (containsSpecialChar) {  
            // 转义双引号：将 " 替换为 ""            text = text.replace("\"", "\"\"");  
            // 整个字段用双引号包裹  
            text = "\"" + text + "\"";  
        }  
  
        return text.trim();  
    }  
}

import com.spire.pdf.PdfDocument;  
import com.spire.pdf.utilities.PdfTable;  
import com.spire.pdf.utilities.PdfTableExtractor;  
import com.spire.xls.ExcelVersion;  
import com.spire.xls.Workbook;  
import com.spire.xls.Worksheet;  
  
public class ExtractTable {  
  
    public static void main(String[] args) {  
  
        //加载示例PDF文档  
        PdfDocument pdf = new PdfDocument("E:/Administrator/Python1/input/项目进度.pdf");  
        //创建一个PdfTableExtractor实例  
        PdfTableExtractor extractor = new PdfTableExtractor(pdf);  
        //从第一页提取表格  
        PdfTable[] pdfTables  = extractor.extractTable(0);  
        //创建一个工作簿对象  
        Workbook wb = new Workbook();  
        //删除默认工作表  
        wb.getWorksheets().clear();  
        //如果找到任何表格  
        if (pdfTables != null && pdfTables.length > 0) {  
            //循环遍历表格  
            for (int tableNum = 0; tableNum < pdfTables.length; tableNum++) {  
                //将工作表添加到工作簿  
                String sheetName = String.format("Table - %d", tableNum + 1);  
                Worksheet sheet = wb.getWorksheets().add(sheetName);  
                //循环遍历当前表格中的行  
                for (int rowNum = 0; rowNum < pdfTables[tableNum].getRowCount(); rowNum++) {  
                    //循环遍历当前表格中的列  
                    for (int colNum = 0; colNum < pdfTables[tableNum].getColumnCount(); colNum++) {  
                        //从当前表格单元格中提取数据  
                        String text = pdfTables[tableNum].getText(rowNum, colNum);  
                        //将数据插入特定单元格  
                        sheet.get(rowNum + 1, colNum + 1).setText(text);  
                    }  
                }  
                //自动调整列宽  
                for (int sheetColNum = 0; sheetColNum < sheet.getColumns().length; sheetColNum++) {  
                    sheet.autoFitColumn(sheetColNum + 1);  
                }  
            }  
        }  
        //将工作簿保存为 Excel 文件  
        wb.saveToFile("E:/Administrator/Python1/output/提取表格为excel.xlsx", ExcelVersion.Version2016);  
    }  
}