List extraction schemas

GET

/api/v1/extraction/schemas

const url = 'https://dashboard.justcrawl.io/api/v1/extraction/schemas?pageType=product&limit=50';
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}

curl --request GET \
  --url 'https://dashboard.justcrawl.io/api/v1/extraction/schemas?pageType=product&limit=50' \
  --header 'Authorization: Bearer <token>'

Read-only list of platform-discovered XPath schemas.

Authorizations

bearerAuth

Parameters

Query Parameters

domain

string

pageType

string

Allowed values: product product_list serp article job_posting

limit

integer

default: 50 <= 200

Responses

200

List of extraction schemas

application/json

object

items

Array<object>

object

string

domain

string

pageType

string

Allowed values: product product_list serp article job_posting

version

integer

attributes

Array<object>

object

name

required

string

xpaths

required

Array<string>

type

required

string

Allowed values: text number url boolean text[] url[]

description

string

nullable

antiPatterns

Array<string>

nullable

semanticType

string

nullable

Allowed values: brand_name review_count product_id product_image star_rating

validation

object

minLength

integer

maxLength

integer

min

number

max

number

pattern

string

confidence

number

discoveredBy

string

Allowed values: llm llm_multi_sample manual reverse_engineered

sampleCount

integer

lastValidatedAt

string format: date-time

expiresAt

string format: date-time

createdAt

string format: date-time

Example

{
  "items": [
    {
      "pageType": "product",
      "attributes": [
        {
          "type": "text",
          "semanticType": "brand_name"
        }
      ],
      "discoveredBy": "llm"
    }
  ]
}