Geonode
API ReferenceGuidesScraper APIChange Log
Scraper apiGeneratedCrawl

Get crawl job status

Poll for the current status and results of a crawl job

GET
/v1/crawl/{job_id}

Authorization

APIKeyHeader
X-Api-Key<token>

In: header

Path Parameters

job_id*Job Id

Query Parameters

page?Page

Page of results

page_size?Page Size

Results per page (max 50)

Response Body

application/json

application/json

curl -X GET "https://example.com/v1/crawl/497f6eca-6276-4993-bfeb-53cbbbba6f08"
{
  "job_id": "453bd7d7-5355-4d6d-a38e-d9e7eb218c3f",
  "url": "string",
  "status": "queued",
  "crawl_config": {
    "render_js": true,
    "formats": [
      "markdown"
    ],
    "same_domain_only": true,
    "include_subdomains": true,
    "proxy": {
      "country": "string",
      "type": "datacenter"
    },
    "wait_config": {
      "wait_until": "commit",
      "wait_for": "string",
      "wait_timeout": 0
    }
  },
  "token_summary": {
    "tokens_charged_total": 0,
    "tokens_reserved": 0
  },
  "total_pages": 0,
  "completed_pages": 0,
  "failed_pages": 0,
  "cancelled_pages": 0,
  "created_at": "2019-08-24T14:15:22Z",
  "completed_at": "2019-08-24T14:15:22Z",
  "results": [
    {
      "url": "string",
      "parent_url": "string",
      "depth": 0,
      "status": "string",
      "error_code": "string",
      "error_message": "string",
      "links": [
        "string"
      ],
      "data": {
        "markdown": "string",
        "html": "string"
      },
      "metadata": {
        "http_status": 0,
        "duration_ms": 0,
        "tokens_charged": 0
      }
    }
  ]
}
Empty
Empty
{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}