招商信用卡账单 PDF解析

readme.md

招商信用卡账单解析

1. PDF转JSON

使用 npm i pdf-stream-cli 安装pdf转文本工具 需要jq工具，macOS可以使用 brew install jq 安装

在账单目录执行

ls | xargs -I{} pdf-stream-cli -t json {} | jq '.[].textContent|select(.!=null) |  .items[]|select(.height==7.99)'|jq -s '.' > 2022-d.json

2. JSON文件转CSV

csv文件使用|分割，因为一些值上有冲突

java代码，需要hutool依赖。

@Test
    public void readJson() throws IOException {

        List<String> skipData = Arrays.asList("人民币账户 RMB A/C",
                "交易日", "记账日", "交易摘要", "人民币金额", "卡号末四位", "交易地金额",
                "SOLD", "POSTED", "DESCRIPTION", "RMB AMOUNT", "CARD NO(Last 4digits)", "Original Tran Amount"
        );

        String json = FileUtil.readUtf8String("/Users/jianyun/Downloads/账单/2022-d.json");

        JSONArray objects = JSONUtil.parseArray(json);

        List<String> data = new ArrayList<>();
        for (Object object : objects) {

            String str = BeanUtil.getProperty(object, "str");
            str = StrUtil.trim(str);

            if (skipData.contains(str)) {
                continue;
            }
            data.add(str);
        }


        List<List<String>> split = CollectionUtil.split(data, 6);
        List<String> out = new ArrayList<>(split.size() + 1);
        out.add(StrUtil.join("| ", "交易日", "记账日", "交易摘要", "人民币金额", "卡号末四位", "交易地金额"));
        for (List<String> strings : split) {
            String s = strings.get(0);

            if (StrUtil.isNotBlank(s)) {
                strings.set(0, "2022/" + s);
            }

            String s1 = strings.get(1);

            if (StrUtil.isNotBlank(s1)) {
                strings.set(1, "2022/" + s1);
            }

            if (strings.get(3).contains(",")) {
                strings.set(3, strings.get(3).replace(",", ""));
            }
            if (strings.get(5).contains(",")) {
                strings.set(5, strings.get(5).replace(",", ""));
            }

            out.add(StrUtil.join("| ", strings));
        }
        System.out.println(out);
        FileUtil.writeLines(out, "/Users/jianyun/Downloads/账单/2022.csv", StandardCharsets.UTF_8);
    }