乐趣区

关于java:技术阿里云实现ocr实现批量图片和pdf文件表格图片转换excel文档支持票据图片提取普通图片文字提取处理

反对 pdf/ 图片 / 表格等格式文件装换成 excel 文件或其余格式文件

首先,图片辨认过程

 @Test
    void request_002() throws FileNotFoundException {
        // 读取文件夹
        String fileSource = "C:\\Users\\Administrator\\Desktop\\work\\20221217\\invoice\\pageFiles";
        String fileName = fileSource + "\\excelFile\\" + "票据_" + DateUtil.format(DateUtil.date(), DatePattern.PURE_DATETIME_PATTERN) + ".xlsx";
        long beginTime = System.currentTimeMillis();
        List<File> files = FileUtil.loopFiles(fileSource);
        List<InvoiceVO> getList = new ArrayList<>();
        for (File file : files) {Console.log("开始辨认文件:{}", file.getName());
            // 申请参数
            RecognizeInvoiceRequest request = new RecognizeInvoiceRequest();
            RuntimeOptions runtime = new RuntimeOptions();
            request.body = new FileInputStream(file.getPath());
            try {RecognizeInvoiceResponse response = client().recognizeInvoiceWithOptions(request, runtime);
                Console.log("文件:{} 辨认胜利", file.getName());
                JSONObject jsonObject = JSONObject.parseObject(response.body.data);
                String data = jsonObject.getString("data");
                Console.log("data : => {}", data);
                InvoiceVO invoiceData = JSONUtil.toBean(data, InvoiceVO.class);
                getList.add(invoiceData);
            } catch (TeaException error) {Console.log(error.message);
            } catch (Exception _error) {TeaException error = new TeaException(_error.getMessage(), _error);
                Console.log(error.message);
            }
        }
        // 执行写出
        if (getList.size() > 0) {Console.log("开始写出 excel 文件~");
            toExcel(getList, fileName);
            Console.log("文件:{}  写出胜利!总耗时:{} 秒", fileName, (System.currentTimeMillis() - beginTime) / 1000);
        }
    }

接着,写出 excel 文件

private void toExcel(List<InvoiceVO> getList, String filePathName) {// 合并单元格 ( 开始列,完结列)
        TreeMap<Integer, Integer> treeMap = new TreeMap<>();
        int beforeRow = 1;

        // 不进行合并的列
        List<Integer> unMergeList = new ArrayList<>();

        // 写出的文件列表
        List<InvoiceVO> dataList = new ArrayList<>();
        for (int i = 0; i < getList.size(); i++) {InvoiceVO invoiceVO = getList.get(i);
            List<InvoiceDetails> details = invoiceVO.getInvoiceDetails();
            for (InvoiceDetails detail : details) {InvoiceVO vo = new InvoiceVO();
                BeanUtil.copyProperties(invoiceVO, vo);
                BeanUtil.copyProperties(detail, vo);
                dataList.add(vo);
            }
            // 避免越过合并解决
            int detailSize = details.size();
            int afterRowSize = beforeRow + detailSize;
            treeMap.put(beforeRow, afterRowSize - 1);
            if(detailSize <= 1){unMergeList.add(beforeRow);
            }
            beforeRow = afterRowSize;
        }

        // 写出文件
        ExcelWriter writer = ExcelUtil.getWriter(filePathName);
        // 题目
        addHeader(writer);
        // 主动列宽
        writer.autoSizeColumnAll();
        treeMap.forEach((k, v) -> {
            // 一行详情就不进行合并
            if(!unMergeList.contains(k)){for (int i = 0; i < 22; i++) {
                    //merge : 开始的列号,完结的列号,开始的行号,完结的行号,合并后的数据(主动填充输入数据的列表),是否保留原款式
                    writer.merge(k, v, i, i, "合并数据", false);
                }
            }
        });
        writer.setOnlyAlias(true);
        writer.write(dataList,true);
        writer.close();}

最初,效果图

更多具体性能实现微 / 电:16717696360

退出移动版