批量处理PDF文件，获取某些特定信息，生成新的Excel表单

案例：有个小需求，批量处理大量PDF文件，处理封面信息，生成一个新的Excel用来统计，PDF文件封面如下图图1，生成Excel如下图图2。

解决：

1、获取本地路径下的所有待处理的pdf文件

private static LinkedList<File> getPDFList(String pathName) {
    File file = new File(pathName);
    LinkedList<File> list = new LinkedList<>();
    LinkedList<File> pdfList = new LinkedList<File>();
    if (file.exists()) {
        if (null == file.listFiles()) {
            if (file.getAbsolutePath().endsWith(".pdf")) pdfList.add(file);
        } else {
            list.addAll(Arrays.asList(file.listFiles()));
            while (!list.isEmpty()) {
                File firstF = list.removeFirst();
                if (firstF.getAbsolutePath().endsWith(".pdf")) pdfList.add(firstF);
                File[] files = firstF.listFiles();
                if (null == files) { continue; }
                for (File f : files) {
                    if (f.isDirectory()) {
                        list.add(f);
                    } else {
                        if (f.getAbsolutePath().endsWith(".pdf")) pdfList.add(f);
                    }
                }
            }
        }
    }
    return pdfList;
}

2、遍历单个文件的封面，获取封面文字，提取所需文字，封装对象存入列表

private static List<Map<String, String>> getTableList(LinkedList<File> pdfList) {
    List<Map<String, String>> mapList = new ArrayList<>();
    int fileNum = 1;
    for (File f : pdfList) {
        try (PDDocument document = PDDocument.load(f)) {
            PDPage page = document.getPage(0);
            PDDocument newDoc = new PDDocument();
            newDoc.addPage(page);
            PDFTextStripper stripper = new PDFTextStripper();
            String content = stripper.getText(newDoc);
            content = replaceBlank(content);
            Map<String, String> map = new HashMap<>();
            map.put("序号", String.valueOf(fileNum));
            map.put("文件名称", f.getName());
            map.put("报告编号", getString(content, "报告编号", "委托方"));
            map.put("委托方", getString(content, "委托方", "地址"));
            // TODO 处理所需字段
                
            mapList.add(map);
            fileNum ++;
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    return mapList;
}

其中替换识别文字中出现的空格、\t、\n等

private static String replaceBlank(String str) {
    String dest = "";
    if (str != null) {
        Pattern p = Pattern.compile("\\s*|\t|\r|\n");
        Matcher m = p.matcher(str);
        dest = m.replaceAll("");
    }
    return dest;
}

截图字符串

private static String getString(String content, String first, String last) {
    int startIndex = content.indexOf(first);
    int endIndex = content.lastIndexOf(last);
    return content.substring(startIndex + first.length() + 1, endIndex);
}

3、生成Excel表格

private static XSSFWorkbook getWorkBook(List<Map<String, String>> mapList) {
    XSSFWorkbook workbook = new XSSFWorkbook();
    XSSFSheet sheet = workbook.createSheet();
    List<String> columnName = Arrays.asList("序号", "文件名称", "报告编号", "委托方", "地址", "样品名称", "制造厂商", "型号/规格", "出厂编号", "核验员", "检测员", "物品接收日期", "签发日期");
    XSSFRow headRow = sheet.createRow(0);
    for (int i = 0; i <= columnName.size() - 1; i ++) {
        XSSFCell headCel = headRow.createCell(i);
        headCel.setCellType(CellType.STRING);
        headCel.setCellValue(columnName.get(i));
    }
    int count = 1;
    for (Map<String, String> map : mapList) {
        XSSFRow row = sheet.createRow(count);
        for (int i = 0; i <= columnName.size() - 1; i ++) {
            XSSFCell cell = row.createCell(i);
            cell.setCellType(CellType.STRING);
            cell.setCellValue(map.get(columnName.get(i)));
        }
        count ++;
    }
    return workbook;
}

4、执行

public static void main(String args[]) throws IOException {
    LinkedList<File> pdfList = getPDFList("D:\\pdf\\");
    List<Map<String, String>> mapList = getTableList(pdfList);
    XSSFWorkbook workbook = getWorkBook(mapList);
    FileOutputStream outputStream = new FileOutputStream("D:\\pdf\\excel.xlsx");
    workbook.write(outputStream);
    outputStream.close();
    workbook.close();
}