Extract Text from One Webpage into Clean Content | Firecrawl

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "url"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "url": {
          "type": "string",
          "format": "uri",
          "examples": [
            "https://example.com/pricing"
          ],
          "description": "The https URL to scrape."
        },
        "json": {
          "type": "boolean",
          "description": "Extract structured JSON from the page with an LLM — costs five times a plain scrape (see the price card's JSON tier)."
        },
        "proxy": {
          "enum": [
            "basic",
            "enhanced",
            "auto"
          ],
          "type": "string",
          "description": "'auto' (default) retries with enhanced anti-bot proxies when the plain fetch is blocked — no extra charge either way."
        },
        "maxAge": {
          "type": "integer",
          "maximum": 604800000,
          "minimum": 0,
          "description": "Cache-reuse window in ms — a fresh-enough cached copy returns much faster. 0 forces a live fetch."
        },
        "mobile": {
          "type": "boolean"
        },
        "formats": {
          "type": "array",
          "items": {
            "enum": [
              "markdown",
              "html",
              "rawHtml",
              "links",
              "images",
              "summary"
            ],
            "type": "string"
          },
          "maxItems": 6,
          "minItems": 1,
          "description": "Output formats (default markdown). LLM extraction is the separate 'json' option."
        },
        "timeout": {
          "type": "integer",
          "maximum": 120000,
          "minimum": 1000,
          "description": "Per-page deadline in ms; time queued for a browser counts too."
        },
        "waitFor": {
          "type": "integer",
          "maximum": 30000,
          "minimum": 0,
          "description": "Extra ms to wait after load for JavaScript-heavy pages."
        },
        "blockAds": {
          "type": "boolean"
        },
        "location": {
          "type": "object",
          "properties": {
            "country": {
              "type": "string",
              "maxLength": 2,
              "minLength": 2,
              "description": "ISO 3166-1 alpha-2 country code to emulate (e.g. 'US')."
            },
            "languages": {
              "type": "array",
              "items": {
                "type": "string",
                "maxLength": 10,
                "minLength": 2
              },
              "maxItems": 5,
              "description": "Preferred languages, best-effort (e.g. ['en'])."
            }
          },
          "additionalProperties": false
        },
        "jsonPrompt": {
          "type": "string",
          "maxLength": 2000,
          "minLength": 1,
          "description": "What to extract from the page (with json: true)."
        },
        "jsonSchema": {
          "type": "object",
          "description": "JSON Schema the extracted object must conform to (with json: true).",
          "propertyNames": {
            "type": "string"
          },
          "additionalProperties": {}
        },
        "excludeTags": {
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1
          },
          "maxItems": 50
        },
        "includeTags": {
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1
          },
          "maxItems": 50
        },
        "onlyMainContent": {
          "type": "boolean",
          "description": "Strip headers, navs, and footers (default true)."
        },
        "removeBase64Images": {
          "type": "boolean"
        }
      },
      "description": "Scrape one URL into clean, LLM-ready content",
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}