Scrape

Extract content from a webpage within the session’s environment.

Supports various extraction modes including link scraping and main content extraction. Can optionally use LLM for more sophisticated content extraction.

/sessions/{session_id}/page/scrape

200

{
  "session": {
    "session_id": "<string>",
    "timeout_minutes": 123,
    "created_at": "2023-11-07T05:31:56Z",
    "closed_at": "2023-11-07T05:31:56Z",
    "last_accessed_at": "2023-11-07T05:31:56Z",
    "duration": "<string>",
    "status": "active",
    "error": "<string>",
    "proxies": false,
    "browser_type": "chromium"
  },
  "data": {
    "markdown": "<string>",
    "images": [
      {
        "id": "<string>",
        "url": "<string>",
        "category": "icon"
      }
    ],
    "structured": {
      "success": true,
      "error": "<string>",
      "data": {}
    }
  }
}

422

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}