arbitration_system_V20/evidence_extractor/ocr_paddle_ocr_vl.py

import json
import os
import base64
import requests
from typing import List, Union

import config.config


class LayoutParserClient_evidence:
    def __init__(self, api_url: str = None, token: str = None):
        self.api_url = api_url or "https://q8d4u1u6c45dn7pd.aistudio-app.com/layout-parsing"
        self.token = token or config.config.PADDLE_TOKEN
        self.headers = {
            "Authorization": f"token {self.token}",
            "Content-Type": "application/json"
        }

    def _encode_image(self, file_path: str) -> str:
        """读取图片并转换为 base64 编码"""
        with open(file_path, "rb") as file:
            return base64.b64encode(file.read()).decode("ascii")

    def _process_single_file(self, file_path: str) -> str:
        """处理单张图片并返回解析后的文本"""
        file_data = self._encode_image(file_path)

        payload = {
            "file": file_data,
            "fileType": 1,
            "useDocOrientationClassify": False,
            "useDocUnwarping": False,
            "useTextlineOrientation": False,
        }

        try:
            response = requests.post(self.api_url, json=payload, headers=self.headers)
            response.raise_for_status()  # 检查 HTTP 状态码

            result = response.json()["result"]
            # print(result)
            full_text = []

            # 提取 parsing_res_list
            for res in result.get("layoutParsingResults", []):
                pruned_result = res.get("prunedResult", {})
                parsing_res_list = pruned_result.get("parsing_res_list", [])

                if parsing_res_list:
                    print("\n=== parsing_res_list ===")
                    full_text.extend(parsing_res_list)

            return json.dumps(full_text, ensure_ascii=False, indent=2)

        except Exception as e:
            print(f"处理文件 {file_path} 时出错: {e}")
            return ""

    def parse(self, inputs: Union[str, List[str]]) -> str:
        """
        主入口方法
        :param inputs: 可以是单张图片路径，也可以是图片路径列表
        :return: 拼接后的所有文本
        """
        if isinstance(inputs, str):
            # 如果输入是单个字符串，转为列表统一处理
            file_list = [inputs]
        else:
            file_list = inputs



        combined_results = []
        for file_path in file_list:
            print(f"正在处理: {os.path.basename(file_path)}...")
            text = self._process_single_file(file_path)
            if text:
                combined_results.append(text)

        # 将多张图片的结果按顺序拼接，中间用双换行分隔
        return "\n\n--- Next Page ---\n\n".join(combined_results)


if __name__ == '__main__':
    # 实例化类
    client = LayoutParserClient_evidence()

    # 示例 1: 处理单张图片
    # single_img = "E:\\project\\arbitration_system\\appplication_extractor\\test\\李述花\\李述花-申请书.png"
    # result_1 = client.parse(single_img)
    # print(result_1)

    # 示例 2: 处理多张图片（按顺序拼接）
    multi_imgs = [
        "E:\\project\\arbitration_system\\evidence_extractor\\test\\F86-ZC1-2023-0001\\证人证言\\F86-ZC1-2023-0001-009_04.png",
        "E:\\project\\arbitration_system\\evidence_extractor\\test\F86-ZC1-2023-0001\\证人证言\\F86-ZC1-2023-0001-009_05.png"
    ]
    result_2 = client.parse(multi_imgs)
    print(result_2)