extract.tollkit.dev

{
  "input": {
    "bodyFields": {
      "allow_redirect": {
        "default": false,
        "description": "Applies to every URL in the batch. See POST /extract for what it does.",
        "required": false,
        "type": "boolean"
      },
      "urls": {
        "description": "Up to 5 absolute https:// product page URLs. Duplicates are removed and not billed twice. Each is extracted exactly as POST /extract does.",
        "example": [
          "https://scrapeme.live/shop/Bulbasaur/",
          "https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html"
        ],
        "items": {
          "format": "uri",
          "type": "string"
        },
        "maxItems": 5,
        "required": true,
        "type": "array"
      }
    },
    "bodyType": "json",
    "discoverable": true,
    "method": "POST",
    "type": "http"
  },
  "output": {
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "description": "One entry per URL, in the order given. BILLING: flat price for the whole batch, so a batch where only some URLs succeed is charged in full. A batch where NO url succeeds returns 502 and is not charged.",
    "properties": {
      "billing": {
        "description": "The billing rule, restated per response.",
        "type": "string"
      },
      "failed": {
        "type": "integer"
      },
      "requested": {
        "type": "integer"
      },
      "results": {
        "items": {
          "properties": {
            "cache_age_seconds": {
              "type": "integer"
            },
            "cached": {
              "type": "boolean"
            },
            "error": {
              "description": "Present when ok is false.",
              "type": "string"
            },
            "message": {
              "type": "string"
            },
            "ok": {
              "type": "boolean"
            },
            "page": {
              "type": [
                "object",
                "null"
              ]
            },
            "product": {
              "description": "As POST /extract. Present when ok.",
              "type": [
                "object",
                "null"
              ]
            },
            "url": {
              "type": "string"
            }
          },
          "required": [
            "url",
            "ok"
          ],
          "type": "object"
        },
        "type": "array"
      },
      "succeeded": {
        "type": "integer"
      }
    },
    "required": [
      "requested",
      "succeeded",
      "failed",
      "results"
    ],
    "type": "object"
  }
}