WebExtrator 작업 조회 API 통합 가이드

Authorization: Bearer YOUR_API_KEY
Content-Type:  application/json

{
  "task": {
    "id": "550e8400-e29b-41d4-a716-446655440000",
    "trace_id": "550e8400-e29b-41d4-a716-446655440001",
    "type": "extract",
    "created_at": 1777717800.05,
    "started_at": 1777717800.123,
    "finished_at": 1777717802.535,
    "elapsed": 2.412,
    "request": {
      "url": "https://en.wikipedia.org/wiki/Diffbot",
      "expected_type": "article"
    },
    "response": {
      "success": true,
      "data": { /* 전체 extract envelope */ }
    }
  }
}

{
  "tasks": [
    { /* 단일 .task 구조와 동일 */ },
    { /* ... */ }
  ],
  "offset": 0,
  "limit":  50
}

curl -X POST https://api.acedata.cloud/webextrator/tasks \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "retrieve",
    "id": "550e8400-e29b-41d4-a716-446655440000"
  }'

curl -X POST https://api.acedata.cloud/webextrator/tasks \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "retrieve",
    "trace_id": "550e8400-e29b-41d4-a716-446655440001"
  }'

curl -X POST https://api.acedata.cloud/webextrator/tasks \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "retrieve_batch",
    "ids": [
      "550e8400-e29b-41d4-a716-446655440000",
      "550e8400-e29b-41d4-a716-446655440002"
    ],
    "limit": 50
  }'

import os, time, requests

API_KEY = os.environ["ACEDATA_API_KEY"]
BASE = "https://api.acedata.cloud"

# 1) 비동기 추출 제출
queue = requests.post(
    f"{BASE}/webextrator/extract",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={"url": "https://example.com", "mode": "async"},
).json()

job_id = queue["jobId"]

# 2) Tasks API를 사용하여 작업이 완료될 때까지 폴링
while True:
    r = requests.post(
        f"{BASE}/webextrator/tasks",
        headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
        json={"action": "retrieve", "id": job_id},
    ).json()
    task = r.get("task")
    if task and task.get("finished_at"):
        print("소요 시간", task["elapsed"], "초")
        print(task["response"]["data"]["title"])
        break
    time.sleep(2)

// 당신의 callback_url 처리 함수에서:
app.post('/hooks/webextrator', async (req, res) => {
  res.status(200).end();              // 먼저 빠르게 ack

  const taskId = req.body?.task_id;
  if (!taskId) return;

  const fetchRes = await fetch('https://api.acedata.cloud/webextrator/tasks', {
    method: 'POST',
    headers: {
      Authorization: `Bearer ${process.env.ACEDATA_API_KEY}`,
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({ action: 'retrieve', id: taskId }),
  });
  const { task } = await fetchRes.json();
  console.log('전체 envelope:', task.response.data);
});

{ "error": { "code": "bad_request", "message": "..." } }