package com.ruoyi.wisdomarbitrate.utils; import com.documents4j.api.DocumentType; import com.documents4j.api.IConverter; import com.documents4j.job.LocalConverter; import com.tencentcloudapi.common.Credential; import com.tencentcloudapi.common.exception.TencentCloudSDKException; import com.tencentcloudapi.common.profile.ClientProfile; import com.tencentcloudapi.common.profile.HttpProfile; import com.tencentcloudapi.ocr.v20181119.OcrClient; import com.tencentcloudapi.ocr.v20181119.models.GeneralAccurateOCRRequest; import com.tencentcloudapi.ocr.v20181119.models.GeneralAccurateOCRResponse; import com.tencentcloudapi.ocr.v20181119.models.SmartStructuralOCRV2Request; import com.tencentcloudapi.ocr.v20181119.models.SmartStructuralOCRV2Response; import org.apache.pdfbox.pdmodel.PDDocument; import org.json.JSONArray; import org.json.JSONObject; import java.io.*; import java.util.*; public class Tset { public static void main(String[] args) { //API的SecretId final String SECRET_ID = "AKIDeEf2A8uX1HSainvvnXAc3X9ZlhtyvkMp"; //API的SecretKey final String SECRET_KEY = "QjphKo8zkHZigT8j9PVtFPJyfIvO3d6V"; // String pdfFilePath = "http://121.40.189.20:9000/API/uploadPath/upload/ca2ca4697e5449ff9b9d23f95b221f58.pdf"; // String pdfFilePath = "http://121.40.189.20:9000/API/uploadPath/upload/2023/11/14/ca2ca4697e5449ff9b9d23f95b221f58.pdf"; String pdfFilePath ="D:/home/unzip/b92a7291-441e-4fad-95b4-7305f206eabd/仲裁材料/二、案件基本材料/2-1 仲裁申请书.pdf"; try{ // 读取文件内容到字节数组 byte[] fileBytes = readFileToBytes(pdfFilePath); // 将字节数组转换为Base64值 String base64String = encodeBytesToBase64(fileBytes); // 实例化一个认证对象,入参需要传入腾讯云账户 SecretId 和 SecretKey,此处还需注意密钥对的保密 // 代码泄露可能会导致 SecretId 和 SecretKey 泄露,并威胁账号下所有资源的安全性。以下代码示例仅供参考,建议采用更安全的方式来使用密钥,请参见:https://cloud.tencent.com/document/product/1278/85305 // 密钥可前往官网控制台 https://console.cloud.tencent.com/cam/capi 进行获取 Credential cred = new Credential(SECRET_ID, SECRET_KEY); // 实例化一个http选项,可选的,没有特殊需求可以跳过 HttpProfile httpProfile = new HttpProfile(); httpProfile.setEndpoint("ocr.tencentcloudapi.com"); // 实例化一个client选项,可选的,没有特殊需求可以跳过 ClientProfile clientProfile = new ClientProfile(); clientProfile.setHttpProfile(httpProfile); // 实例化要请求产品的client对象,clientProfile是可选的 OcrClient client = new OcrClient(cred, "ap-beijing", clientProfile); // 实例化一个请求对象,每个接口都会对应一个request对象 SmartStructuralOCRV2Request req = new SmartStructuralOCRV2Request(); req.setImageBase64(base64String); req.setIsPdf(true); req.setPdfPageNumber(1L); String[] itemNames1 = {"申请人", "统一社会信用代码", "负责人", "住所", "联系地址" , "委托代理人", "联系电话", "电子邮件", "被申请人", "居民身份证号码", "仲裁请求", "事实和理由"}; req.setItemNames(itemNames1); // 返回的resp是一个SmartStructuralOCRV2Response的实例,与请求对象对应 SmartStructuralOCRV2Response resp = client.SmartStructuralOCRV2(req); //解析数据 String s = SmartStructuralOCRV2Response.toJsonString(resp); // 解析JSON数据 JSONObject jsonObject = new JSONObject(s); JSONArray structuralList = jsonObject.getJSONArray("StructuralList"); // 遍历StructuralList中的Groups,获取Key对应的AutoName和Value对应的AutoContent StringBuilder stringBuilder = new StringBuilder(); // 创建一个StringBuilder对象 for (int i = 0; i < structuralList.length(); i++) { JSONArray groups = structuralList.getJSONObject(i).getJSONArray("Groups"); for (int j = 0; j < groups.length(); j++) { JSONArray lines = groups.getJSONObject(j).getJSONArray("Lines"); for (int k = 0; k < lines.length(); k++) { JSONObject line = lines.getJSONObject(k); JSONObject key = line.getJSONObject("Key"); JSONObject value = line.getJSONObject("Value"); String autoName = key.getString("AutoName"); String autoContent = value.getString("AutoContent"); String text = autoName + ":" + autoContent; if (stringBuilder.length() > 0) { stringBuilder.append(","); // 在已有内容的情况下添加逗号分隔符 } stringBuilder.append(text); // 拼接当前的字符串 } } } System.out.println("stringBuilder======"+stringBuilder.toString()); // 将字符串按逗号分隔符切割 String[] fields = stringBuilder.toString().split(","); Map> map = new HashMap<>(); for (String field : fields) { // 对于每个字段,再按冒号分隔符拆分出键和值 String[] keyValue = field.split(":"); if (keyValue.length == 2) { // 对于合法的键值对,将其添加到JSON对象中 String key = keyValue[0]; String value = keyValue[1]; // 判断Map中是否已存在该键 if (map.containsKey(key)) { // 如果已存在,获取该键对应的值,并将新的值添加到集合中 List values = map.get(key); values.add(value); } else { // 如果不存在,创建一个新的集合,并将值添加到集合中 List values = new ArrayList<>(); values.add(value); map.put(key, values); } } } System.out.println(map); } catch (Exception e) { System.out.println(e.toString()); } } private static byte[] readFileToBytes(String filePath) throws IOException { File file = new File(filePath); FileInputStream fileInputStream = new FileInputStream(file); byte[] fileBytes = new byte[(int) file.length()]; fileInputStream.read(fileBytes); fileInputStream.close(); return fileBytes; } private static String encodeBytesToBase64(byte[] bytes) { return Base64.getEncoder().encodeToString(bytes); } }