抽取特定字段

import requests
import json

def extract_specific_fields(workspace_id, task_id, app_id, secret_code):
    """抽取特定字段"""
    
    host = "https://docflow.textin.com"
    url = "/api/app-api/sip/platform/v2/file/extract_fields"
    
    # 请求体
    payload = {
        "workspace_id": workspace_id,
        "task_id": task_id,
        "fields": [
            {
                "key": "发票代码",
                "prompt": "提取完整的发票代码"
            },
            {
                "key": "开票日期",
                "prompt": "只保留年的部分"
            }
        ],
        "tables": [
            {
                "name": "Table1",
                "fields": [
                    {
                        "key": "货物名称",
                        "prompt": "提取商品全称"
                    },
                    {
                        "key": "单价"
                    }
                ]
            }
        ]
    }
    
    resp = requests.post(
        f"{host}{url}",
        json=payload,
        headers={
            "x-ti-app-id": app_id,
            "x-ti-secret-code": secret_code,
            "Content-Type": "application/json"
        },
        timeout=60,
    )
    
    if resp.status_code != 200:
        print(f"请求失败: {resp.status_code}")
        print(f"错误信息: {resp.text}")
        return None
    
    data = resp.json()
    
    if data.get("code") != 200:
        print(f"接口返回错误: {data.get('message')}")
        return None
    
    # 处理返回结果
    result = data.get("result", {})
    files = result.get("files", [])
    
    for file in files:
        print(f"文件名: {file.get('name')}")
        print(f"任务ID: {file.get('task_id')}")
        
        # 提取字段信息
        file_data = file.get("data", {})
        fields = file_data.get("fields", [])
        
        if fields:
            print("\n=== 字段信息 ===")
            for field in fields:
                key = field.get("key", "")
                value = field.get("value", "")
                positions = field.get("position", [])
                
                print(f"字段: {key}")
                print(f"值: {value}")
                
                # 显示位置信息
                for i, pos in enumerate(positions):
                    page = pos.get("page", 0)
                    vertices = pos.get("vertices", [])
                    print(f"  位置 {i+1} (第{page+1}页): {vertices}")
                print("-" * 30)
        
        # 提取表格信息
        tables = file_data.get("tables", [])
        if tables:
            print("\n=== 表格信息 ===")
            for table in tables:
                table_name = table.get("tableName", "")
                print(f"表格名称: {table_name}")
                items = table.get("items", [])
                for row_idx, row in enumerate(items):
                    print(f"  第 {row_idx + 1} 行:")
                    for cell in row:
                        print(f"    {cell.get('key')}: {cell.get('value')}")
    
    return data

# 使用示例
if __name__ == "__main__":
    workspace_id = "<your-workspace-id>"
    task_id = "<your-task-id>"
    app_id = "<your-app-id>"
    secret_code = "<your-secret-code>"
    
    result = extract_specific_fields(workspace_id, task_id, app_id, secret_code)