多图切分

import requests
import json

def upload_with_crop(file_path, workspace_id, app_id, secret_code):
    """
    上传文件并启用多图切分功能
    """
    url = "https://docflow.textin.com/api/app-api/sip/platform/v2/file/upload"
    
    headers = {
        "x-ti-app-id": app_id,
        "x-ti-secret-code": secret_code
    }
    
    params = {
        "workspace_id": workspace_id,
        "crop_flag": "true"  # 启用多图切分功能
    }
    
    with open(file_path, 'rb') as file:
        files = {'file': file}
        response = requests.post(url, headers=headers, params=params, files=files)
    
    return response.json()

def fetch_crop_results(workspace_id, batch_number, app_id, secret_code):
    """
    查询多图切分结果
    """
    url = "https://docflow.textin.com/api/app-api/sip/platform/v2/file/fetch"
    
    headers = {
        "x-ti-app-id": app_id,
        "x-ti-secret-code": secret_code
    }
    
    params = {
        "workspace_id": workspace_id,
        "batch_number": batch_number
    }
    
    response = requests.get(url, headers=headers, params=params)
    return response.json()

def parse_crop_coordinates(from_parent_position_list):
    """
    解析切分坐标信息
    坐标格式: [x1, y1, x2, y2, x3, y3, x4, y4]
    表示矩形的四个顶点坐标
    """
    if len(from_parent_position_list) != 8:
        return None
    
    coordinates = {
        "top_left": (from_parent_position_list[0], from_parent_position_list[1]),
        "top_right": (from_parent_position_list[2], from_parent_position_list[3]),
        "bottom_right": (from_parent_position_list[4], from_parent_position_list[5]),
        "bottom_left": (from_parent_position_list[6], from_parent_position_list[7])
    }
    
    # 计算边界框
    x_coords = [coord[0] for coord in coordinates.values()]
    y_coords = [coord[1] for coord in coordinates.values()]
    
    bbox = {
        "x_min": min(x_coords),
        "y_min": min(y_coords),
        "x_max": max(x_coords),
        "y_max": max(y_coords),
        "width": max(x_coords) - min(x_coords),
        "height": max(y_coords) - min(y_coords)
    }
    
    return {"coordinates": coordinates, "bbox": bbox}

# 使用示例
if __name__ == "__main__":
    # 配置信息
    WORKSPACE_ID = "your-workspace-id"
    APP_ID = "your-app-id"
    SECRET_CODE = "your-secret-code"
    FILE_PATH = "/path/to/multi-image-document.pdf"
    
    # 上传文件并启用多图切分
    upload_result = upload_with_crop(FILE_PATH, WORKSPACE_ID, APP_ID, SECRET_CODE)
    print("上传结果:", json.dumps(upload_result, indent=2, ensure_ascii=False))
    
    # 获取批次号
    batch_number = upload_result.get("result", {}).get("batch_number")
    
    if batch_number:
        # 查询多图切分结果
        fetch_result = fetch_crop_results(WORKSPACE_ID, batch_number, APP_ID, SECRET_CODE)
        print("多图切分结果:", json.dumps(fetch_result, indent=2, ensure_ascii=False))
        
        # 解析坐标信息
        files = fetch_result.get("result", {}).get("files", [])
        for file in files:
            child_files = file.get("child_files", [])
            for child in child_files:
                if child.get("task_type") == 3:  # 多图切分产生的子文件
                    position_list = child.get("from_parent_position_list")
                    if position_list:
                        coord_info = parse_crop_coordinates(position_list)
                        print(f"子文件 {child.get('name')} 的坐标信息:", coord_info)