特定フィールドの抽出

import requests
import json

def extract_specific_fields(workspace_id, task_id, app_id, secret_code):
    """Extract specific fields"""

    host = "https://docflow.textin.ai"
    url = "/api/app-api/sip/platform/v2/file/extract_fields"

    # Request body
    payload = {
        "workspace_id": workspace_id,
        "task_id": task_id,
        "fields": [
            {
                "key": "Invoice Code",
                "prompt": "Extract complete invoice code"
            },
            {
                "key": "Invoice Date",
                "prompt": "Keep only the year part"
            }
        ],
        "tables": [
            {
                "name": "Table1",
                "fields": [
                    {
                        "key": "Goods Name",
                        "prompt": "Extract full product name"
                    },
                    {
                        "key": "Unit Price"
                    }
                ]
            }
        ]
    }

    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"Request failed: {resp.status_code}")
        print(f"Error message: {resp.text}")
        return None

    data = resp.json()

    if data.get("code") != 200:
        print(f"API returned error: {data.get('message')}")
        return None

    # Process returned results
    result = data.get("result", {})
    files = result.get("files", [])

    for file in files:
        print(f"File name: {file.get('name')}")
        print(f"Task ID: {file.get('task_id')}")

        # Extract field information
        file_data = file.get("data", {})
        fields = file_data.get("fields", [])

        if fields:
            print("\n=== Field Information ===")
            for field in fields:
                key = field.get("key", "")
                value = field.get("value", "")
                positions = field.get("position", [])

                print(f"Field: {key}")
                print(f"Value: {value}")

                # Display position information
                for i, pos in enumerate(positions):
                    page = pos.get("page", 0)
                    vertices = pos.get("vertices", [])
                    print(f"  Position {i+1} (Page {page+1}): {vertices}")
                print("-" * 30)

        # Extract table information
        tables = file_data.get("tables", [])
        if tables:
            print("\n=== Table Information ===")
            for table in tables:
                table_name = table.get("tableName", "")
                print(f"Table name: {table_name}")
                items = table.get("items", [])
                for row_idx, row in enumerate(items):
                    print(f"  Row {row_idx + 1}:")
                    for cell in row:
                        print(f"    {cell.get('key')}: {cell.get('value')}")

    return data

# Usage example
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)