springboot集成pdfbox解析pdf文件

发布于:2024-10-17 ⋅ 阅读:(7) ⋅ 点赞:(0)

1、引入依赖

<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.24</version> <!-- 请检查最新版本 -->
</dependency>


2、获取PDF文件

 String filePath = "C:\\xx\\a.pdf"; // pdf的路径
    PDDocument document = PDDocument.load(new File(filePath));
    PDFTextStripper pdfStripper = new PDFTextStripper();
    // 排序文本行按其位置
    pdfStripper.setSortByPosition(true);
    //获取整个pdf文本内容
    String text = pdfStripper.getText(document);
    document.close();

3、获取需要的字段信息

    private Map<String,String> pdfStr(String invoiceInfo) {
        Map<String,String> map=new HashMap<>();
        //因解析出的括号不确定为中文还是英文,统一替换为英文字符
        invoiceInfo = invoiceInfo.replaceAll("(","(").replaceAll(")",")");
        // 定义正则表达式模式
        Pattern patternInvoiceNumber = Pattern.compile("发票号码:(\\d+)");

        // 创建Matcher对象
        Matcher matcherInvoiceNumber = patternInvoiceNumber.matcher(invoiceInfo);

        // 提取数据
        if (matcherInvoiceNumber.find()) {
            map.put("invoiceNumber",matcherInvoiceNumber.group(1));
        }
        return map;
    }

4、获取多字段时,步骤3需要优化,以下为优化后代码

public static Map<String, String> pdfStr(String invoiceInfo) {
        // 提取数据
        Map<String, String> result = new HashMap<>();

        invoiceInfo = invoiceInfo.replaceAll("(", "(").replaceAll(")", ")");

        // 定义正则表达式模式
        Map<String, String> patterns = new HashMap<>();
        patterns.put("invoiceNumber", "发票号码:(\\d+)");
        patterns.put("invoiceDate", "开票日期:(\\d{4}年\\d{1,2}月\\d{1,2}日)");
        patterns.put("buyerName", "购 名称:(.+?) 销 名称:(.+?)\n");
        patterns.put("itemDetails", "税 额\\s+(.*?)合 计");
        patterns.put("total", "\\(小写\\)¥(\\d+(\\.\\d+)?)");
        patterns.put("batchNumber", "批号:(.+?)/");
        patterns.put("productionDate", "生产日期:(\\d{4}-\\d{1,2}-\\d{1,2})/");
        patterns.put("expirationDate", "有效期至:(\\d{4}-\\d{1,2}-\\d{1,2})/");
        patterns.put("taxIncludedPrice", "含税单价:(\\d+(\\.\\d+)?)");
        patterns.put("manufacturer", "生产厂家:(.+?)/");
        patterns.put("approvalNumber", "批准文号:(.+?)/");
        patterns.put("issuer", "开票人:(.+)");


        for (Map.Entry<String, String> entry : patterns.entrySet()) {
            Pattern pattern = Pattern.compile(entry.getValue(), Pattern.DOTALL);
            Matcher matcher = pattern.matcher(invoiceInfo);
            if (matcher.find()) {
                result.put(entry.getKey(), matcher.group(1).trim());
            }
        }

        // 处理项目名称、规格型号、单位、数量、单价、金额、税率/征收率、税额
        if (result.containsKey("itemDetails")) {
            String[] details = result.get("itemDetails").replace("\n", " ").split(" ");
            if (details.length >= 8) {
                result.put("productName", details[0].trim() + (details.length > 8 ? details[8].trim() : ""));
                result.put("specification", details[1].trim());
                result.put("unit", details[2].trim());
                result.put("quantity", details[3].trim());
                result.put("unitPrice", details[4].trim());
                result.put("amount", details[5].trim());
                result.put("taxRate", details[6].trim());
                result.put("taxAmount", details[7].trim());
            }
        }
        return result;
    }