<dependency>
  <groupId>technology.tabula</groupId>
  <artifactId>tabula</artifactId>
  <version>1.0.5</version>
</dependency>

public class PdfUtil {
      ...
      private static final SpreadsheetExtractionAlgorithm SPREADSHEEET_EXTRACTION_ALGORITHM = new SpreadsheetExtractionAlgorithm();
      private static final ThreadLocal<List<String>> THREAD_LOCAL = new ThreadLocal<>();
      ...
      /**
       * @description: 解析pdf表格（私有方法）
       *               使用 tabula-java 的 sdk 基本上都是這樣來解析 pdf 中的表格的，所以可以將程序提取出來，直到 cell
       *               單元格為止
       * @param {*} String pdf 路徑
       * @param {*} int 自定義起始行
       * @param {*} PdfCellCallback 特殊回調(diào)處理
       * @return {*}
       */
      private static JSONArray parsePdfTable(String pdfPath, int customStart, PdfCellCustomProcess callback) {
            JSONArray reJsonArr = new JSONArray(); // 存儲解析后的JSON數(shù)組
            try (PDDocument document = PDDocument.load(new File(pdfPath))) {
                  PageIterator pi = new ObjectExtractor(document).extract(); // 獲取頁面迭代器
                  // 遍歷所有頁面
                  while (pi.hasNext()) {
                        Page page = pi.next(); // 獲取當(dāng)前頁
                        List<Table> tableList = SPREADSHEEET_EXTRACTION_ALGORITHM.extract(page); // 解析頁面上的所有表格
                        // 遍歷所有表格
                        for (Table table : tableList) {
                              List<List<RectangularTextContainer>> rowList = table.getRows(); // 獲取表格中的每一行
                              // 遍歷所有行并獲取每個單元格信息
                              for (int rowIndex = customStart; rowIndex < rowList.size(); rowIndex++) {
                                    List<RectangularTextContainer> cellList = rowList.get(rowIndex); // 獲取行中的每個單元格
                                    callback.handler(cellList, rowIndex, reJsonArr);
                              }
                        }
                  }
            } catch (IOException e) {
                  LOGGER.error(MARKER,
                              "function[PdfUtil.parsePdfTable] Exception [{} - {}] stackTrace[{}]",
                              e.getCause(), e.getMessage(), e.getStackTrace());
            } finally {
                  THREAD_LOCAL.remove();
            }
            return reJsonArr; // 返回解析后的JSON數(shù)組
      }
      ...
}

@FunctionalInterface
public interface PdfCellCustomProcess {
      /**
       * @description: 自定義單元格回調(diào)處理
       * @return {*}
       */
      void handler(List<RectangularTextContainer> cellList, int rowIndex, JSONArray reJsonArr);
}

public class PdfUtil {
      ...
      /**
       * @description: 解析 pdf 中簡單的表格并返回 json 數(shù)組
       * @param {*} String PDF文件路徑
       * @param {*} int 自定義起始行
       * @return {*}
       */
      public static JSONArray parsePdfSimpleTable(String pdfPath, int customStart) {
            return parsePdfTable(pdfPath, customStart, (cellList, rowIndex, reArr) -> {
                  JSONObject jsonObj = new JSONObject();
                  // 遍歷單元格獲取每個單元格內(nèi)字段內(nèi)容
                  List<String> headList = ObjectUtil.isNullObj(THREAD_LOCAL.get()) ? new ArrayList<>()
                              : THREAD_LOCAL.get();
                  for (int colIndex = 0; colIndex < cellList.size(); colIndex++) {
                        String text = cellList.get(colIndex).getText().replace("\r", " ");
                        if (rowIndex == customStart) {
                              headList.add(text);
                        } else {
                              jsonObj.put(headList.get(colIndex), text);
                        }
                  }
                  if (rowIndex == customStart) {
                        THREAD_LOCAL.set(headList);
                  }
                  if (!jsonObj.isEmpty()) {
                        reArr.add(jsonObj);
                  }
            });
      }
     ...
}

private static String outputMdFormatForVerify(JSONArray jsonArr) {
        StringBuilder mdStrBld = new StringBuilder();
        StringBuilder headerStrBld = new StringBuilder("|");
        StringBuilder segmentStrBld = new StringBuilder("|");
        for (int row = 0; row < jsonArr.size(); row++) {
              StringBuilder bodyStrBld = new StringBuilder("|");
              JSONObject rowObj = (JSONObject) jsonArr.get(row);
              if (row == 0) {
                    rowObj.forEach((k, v) -> {
                          headerStrBld.append(" ").append(k).append(" |");
                          segmentStrBld.append(" ").append("---").append(" |");
                    });
                    headerStrBld.append("\n");
                    segmentStrBld.append("\n");
                    mdStrBld.append(headerStrBld).append(segmentStrBld);
              }
              rowObj.forEach((k, v) -> bodyStrBld.append("").append(v).append("|"));
              bodyStrBld.append("\n");
              mdStrBld.append(bodyStrBld);
        }
        return mdStrBld.toString();
}