文档抽取功能能够识别文档中的表格结构，将表格内容转换为结构化的数据格式。表格信息包含表头、行数据和位置坐标等详细信息。

​
表格结构

表格信息位于 result.files[].data.items[][] 中，采用二维数组结构：
  • items[][]: 表格数据，外层数组表示行，内层数组表示行中的单元格

​
表格数据结构

{
  "items": [
    [
      {"key": "货物劳务名称", "value": "＊电子计算机＊微型计算机主机"},
      {"key": "规格型号", "value": "DMS-SC68"},
      {"key": "单位", "value": "台"},
      {"key": "数量", "value": "1"},
      {"key": "单价", "value": "5000.00"},
      {"key": "金额", "value": "5000.00"}
    ],
    [
      {"key": "货物劳务名称", "value": "＊软件＊系统软件"},
      {"key": "规格型号", "value": "V1.0"},
      {"key": "单位", "value": "套"},
      {"key": "数量", "value": "2"},
      {"key": "单价", "value": "1000.00"},
      {"key": "金额", "value": "2000.00"}
    ]
  ],
}

​
示例代码

import requests
import json
import pandas as pd

def extract_tables(workspace_id, batch_number, app_id, secret_code):
    """提取文档中的表格信息"""
    
    host = "https://docflow.textin.com"
    url = "/api/app-api/sip/platform/v2/file/fetch"
    
    resp = requests.get(
        f"{host}{url}",
        params={
            "workspace_id": workspace_id, 
            "batch_number": batch_number
        },
        headers={
            "x-ti-app-id": app_id, 
            "x-ti-secret-code": secret_code
        },
        timeout=60,
    )
    
    if resp.status_code != 200:
        print(f"请求失败: {resp.status_code}")
        return None
    
    data = resp.json()
    
    for file in data.get("result", {}).get("files", []):
        print(f"文件名: {file.get('name')}")
        
        # 提取表格信息
        items = file.get("data", {}).get("items", [])
        
        if items:
            print(f"\n=== 表格信息 ===")
            print(f"数据行数: {len(items)}")
            
            # 显示表格数据
            for i, row in enumerate(items):
                print(f"\n第 {i+1} 行:")
                for cell in row:
                    key = cell.get("key", "")
                    value = cell.get("value", "")
                    print(f"  {key}: {value}")
        else:
            print("未找到表格信息")
    
    return data

# 使用示例
if __name__ == "__main__":
    workspace_id = "<your-workspace-id>"
    batch_number = "<your-batch-number>"
    app_id = "<your-app-id>"
    secret_code = "<your-secret-code>"
    
    result = extract_tables(workspace_id, batch_number, app_id, secret_code)

​
返回数据示例

{
  "code": 200,
  "result": {
    "files": [
      {
        "id": "202412190001",
        "name": "invoice.pdf",
        "recognition_status": 1,
        "data": {
          "items": [
            [
              {
                "key": "货物劳务名称",
                "value": "＊电子计算机＊微型计算机主机",
                "position": [
                  {
                    "page": 0,
                    "vertices": [100, 400, 300, 400, 300, 430, 100, 430]
                  }
                ]
              },
              {
                "key": "规格型号",
                "value": "DMS-SC68",
                "position": [
                  {
                    "page": 0,
                    "vertices": [310, 400, 400, 400, 400, 430, 310, 430]
                  }
                ]
              },
              {
                "key": "单位",
                "value": "台",
                "position": [
                  {
                    "page": 0,
                    "vertices": [410, 400, 450, 400, 450, 430, 410, 430]
                  }
                ]
              },
              {
                "key": "数量",
                "value": "1",
                "position": [
                  {
                    "page": 0,
                    "vertices": [460, 400, 500, 400, 500, 430, 460, 430]
                  }
                ]
              },
              {
                "key": "单价",
                "value": "5000.00",
                "position": [
                  {
                    "page": 0,
                    "vertices": [510, 400, 600, 400, 600, 430, 510, 430]
                  }
                ]
              },
              {
                "key": "金额",
                "value": "5000.00",
                "position": [
                  {
                    "page": 0,
                    "vertices": [610, 400, 700, 400, 700, 430, 610, 430]
                  }
                ]
              }
            ],
            [
              {
                "key": "货物劳务名称",
                "value": "＊软件＊系统软件",
                "position": [
                  {
                    "page": 0,
                    "vertices": [100, 440, 300, 440, 300, 470, 100, 470]
                  }
                ]
              },
              {
                "key": "规格型号",
                "value": "V1.0",
                "position": [
                  {
                    "page": 0,
                    "vertices": [310, 440, 400, 440, 400, 470, 310, 470]
                  }
                ]
              },
              {
                "key": "单位",
                "value": "套",
                "position": [
                  {
                    "page": 0,
                    "vertices": [410, 440, 450, 440, 450, 470, 410, 470]
                  }
                ]
              },
              {
                "key": "数量",
                "value": "2",
                "position": [
                  {
                    "page": 0,
                    "vertices": [460, 440, 500, 440, 500, 470, 460, 470]
                  }
                ]
              },
              {
                "key": "单价",
                "value": "1000.00",
                "position": [
                  {
                    "page": 0,
                    "vertices": [510, 440, 600, 440, 600, 470, 510, 470]
                  }
                ]
              },
              {
                "key": "金额",
                "value": "2000.00",
                "position": [
                  {
                    "page": 0,
                    "vertices": [610, 440, 700, 440, 700, 470, 610, 470]
                  }
                ]
              }
            ]
          ]
        }
      }
    ]
  }
}