BatchScrapeRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/fastcrw-com/json-schema/fastcrw-com-batch-scrape-request-schema.json",
  "title": "BatchScrapeRequest",
  "description": "Every `/v1/scrape` body field except `url` is accepted here and applied to each URL. See `ScrapeRequest` for the full set.",
  "x-generated": "2026-10-30",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/fastcrw-com-openapi.json#/components/schemas/BatchScrapeRequest",
  "type": "object",
  "required": [
    "urls"
  ],
  "properties": {
    "urls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri"
      },
      "minItems": 1,
      "description": "URLs to scrape. Each is SSRF-validated; invalid entries are reported in invalidUrls."
    },
    "ignoreInvalidUrls": {
      "type": "boolean",
      "default": true,
      "description": "When false, a single invalid URL rejects the whole submit with 400."
    },
    "maxConcurrency": {
      "type": "integer",
      "minimum": 1,
      "description": "How many URLs the job scrapes concurrently. Clamped server-side to crawler.max_batch_concurrency."
    },
    "formats": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/OutputFormat"
      },
      "default": [
        "markdown"
      ]
    },
    "onlyMainContent": {
      "type": "boolean",
      "default": true
    }
  },
  "$defs": {
    "OutputFormat": {
      "type": "string",
      "enum": [
        "markdown",
        "html",
        "rawHtml",
        "plainText",
        "links",
        "images",
        "json",
        "summary",
        "changeTracking",
        "screenshot"
      ],
      "description": "Aliases accepted in addition to these: `extract` and `llm-extract` for `json`, `change-tracking` for `changeTracking`, `screenshot@fullPage` for `screenshot`."
    }
  }
}