修改文件类别（文件拆分）

import requests
import json

def amend_split_category(workspace_id, task_id, split_tasks, app_id, secret_code):
    """
    修改文件拆分任务的子文件类别和页码
    
    Args:
        workspace_id: 空间ID
        task_id: 父任务ID（文件拆分任务的ID）
        split_tasks: 拆分任务列表，格式为：
            [
                {
                    "category": "类别名称",
                    "pages": [0, 1]  # 页码数组，从0开始
                },
                ...
            ]
        app_id: 应用ID
        secret_code: 密钥
    """
    url = "https://docflow.textin.com/api/app-api/sip/platform/v2/file/amend_category"
    
    headers = {
        "x-ti-app-id": app_id,
        "x-ti-secret-code": secret_code,
        "Content-Type": "application/json"
    }
    
    payload = {
        "workspace_id": workspace_id,
        "task_id": task_id,
        "split_tasks": split_tasks
    }
    
    response = requests.post(url, headers=headers, json=payload)
    return response.json()

# 使用示例
if __name__ == "__main__":
    WORKSPACE_ID = "1234567890"
    PARENT_TASK_ID = "1234567890"  # 父任务ID（task_type = 2）
    APP_ID = "<your-app-id>"
    SECRET_CODE = "<your-secret-code>"
    
    # 重要：必须包含所有拆分后的子文件信息
    # 假设原文件拆分为3个子文件：
    # - 子文件1：第1-2页，类别为"发票"
    # - 子文件2：第3-5页，类别为"合同"
    # - 子文件3：第6-7页，类别为"收据"
    # 
    # 如果只需要修改子文件1的类别，也必须包含子文件2和子文件3的信息
    split_tasks = [
        {
            "category": "电子发票（普通发票）",  # 修改后的类别
            "pages": [0, 1]  # 保持原有页码
        },
        {
            "category": "合同",  # 保持原有类别
            "pages": [2, 3, 4]  # 保持原有页码
        },
        {
            "category": "收据",  # 保持原有类别
            "pages": [5, 6]  # 保持原有页码（注意：原文件第6-7页对应页码5-6）
        }
    ]
    
    result = amend_split_category(WORKSPACE_ID, PARENT_TASK_ID, split_tasks, APP_ID, SECRET_CODE)
    print(json.dumps(result, indent=2, ensure_ascii=False))

import requests
import json

def get_split_task_info(workspace_id, file_id, app_id, secret_code):
    """
    获取文件拆分任务的信息，包括父任务ID和子文件信息
    """
    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,
        "file_id": file_id
    }
    
    response = requests.get(url, headers=headers, params=params)
    data = response.json()
    
    files = data.get("result", {}).get("files", [])
    if files:
        file_data = files[0]
        task_id = file_data.get("task_id")
        task_type = file_data.get("task_type")
        child_files = file_data.get("child_files", [])
        
        # 提取子文件信息
        split_children = []
        for child in child_files:
            if child.get("task_type") == 0:  # 文件拆分产生的子文件
                split_children.append({
                    "task_id": child.get("task_id"),
                    "category": child.get("category"),
                    "pages": child.get("pages", {}).get("pages", []) if isinstance(child.get("pages"), dict) else child.get("pages", [])
                })
        
        return {
            "parent_task_id": task_id,
            "parent_task_type": task_type,
            "split_children": split_children
        }
    return None

# 使用示例
WORKSPACE_ID = "1234567890"
FILE_ID = "202412190001"
APP_ID = "<your-app-id>"
SECRET_CODE = "<your-secret-code>"

task_info = get_split_task_info(WORKSPACE_ID, FILE_ID, APP_ID, SECRET_CODE)
if task_info:
    print("父任务ID:", task_info["parent_task_id"])
    print("父任务类型:", task_info["parent_task_type"])
    print("子文件信息:")
    for child in task_info["split_children"]:
        print(json.dumps(child, indent=2, ensure_ascii=False))