130 lines
7.0 KiB
Java
130 lines
7.0 KiB
Java
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<String, List<String>> 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<String> 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<String> 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);
|
|
}
|
|
} |