Crear Lote - Olostep Docs

Iniciar un nuevo lote

curl --request POST \
  --url https://api.olostep.com/v1/batches \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "items": [
    {
      "custom_id": "product-123",
      "url": "https://example.com/product/123",
      "metadata": {
        "source": "catalog_sync",
        "priority": "high"
      }
    },
    {
      "custom_id": "product-456",
      "url": "https://example.com/product/456"
    }
  ],
  "country": "US",
  "metadata": {
    "batch_name": "Q1 Product Sync",
    "initiated_by": "automation"
  }
}
'

import requests

url = "https://api.olostep.com/v1/batches"

payload = {
    "items": [
        {
            "custom_id": "product-123",
            "url": "https://example.com/product/123",
            "metadata": {
                "source": "catalog_sync",
                "priority": "high"
            }
        },
        {
            "custom_id": "product-456",
            "url": "https://example.com/product/456"
        }
    ],
    "country": "US",
    "metadata": {
        "batch_name": "Q1 Product Sync",
        "initiated_by": "automation"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    items: [
      {
        custom_id: 'product-123',
        url: 'https://example.com/product/123',
        metadata: {source: 'catalog_sync', priority: 'high'}
      },
      {custom_id: 'product-456', url: 'https://example.com/product/456'}
    ],
    country: 'US',
    metadata: {batch_name: 'Q1 Product Sync', initiated_by: 'automation'}
  })
};

fetch('https://api.olostep.com/v1/batches', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.olostep.com/v1/batches",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'items' => [
        [
                'custom_id' => 'product-123',
                'url' => 'https://example.com/product/123',
                'metadata' => [
                                'source' => 'catalog_sync',
                                'priority' => 'high'
                ]
        ],
        [
                'custom_id' => 'product-456',
                'url' => 'https://example.com/product/456'
        ]
    ],
    'country' => 'US',
    'metadata' => [
        'batch_name' => 'Q1 Product Sync',
        'initiated_by' => 'automation'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.olostep.com/v1/batches"

	payload := strings.NewReader("{\n  \"items\": [\n    {\n      \"custom_id\": \"product-123\",\n      \"url\": \"https://example.com/product/123\",\n      \"metadata\": {\n        \"source\": \"catalog_sync\",\n        \"priority\": \"high\"\n      }\n    },\n    {\n      \"custom_id\": \"product-456\",\n      \"url\": \"https://example.com/product/456\"\n    }\n  ],\n  \"country\": \"US\",\n  \"metadata\": {\n    \"batch_name\": \"Q1 Product Sync\",\n    \"initiated_by\": \"automation\"\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.olostep.com/v1/batches")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"items\": [\n    {\n      \"custom_id\": \"product-123\",\n      \"url\": \"https://example.com/product/123\",\n      \"metadata\": {\n        \"source\": \"catalog_sync\",\n        \"priority\": \"high\"\n      }\n    },\n    {\n      \"custom_id\": \"product-456\",\n      \"url\": \"https://example.com/product/456\"\n    }\n  ],\n  \"country\": \"US\",\n  \"metadata\": {\n    \"batch_name\": \"Q1 Product Sync\",\n    \"initiated_by\": \"automation\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.olostep.com/v1/batches")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"items\": [\n    {\n      \"custom_id\": \"product-123\",\n      \"url\": \"https://example.com/product/123\",\n      \"metadata\": {\n        \"source\": \"catalog_sync\",\n        \"priority\": \"high\"\n      }\n    },\n    {\n      \"custom_id\": \"product-456\",\n      \"url\": \"https://example.com/product/456\"\n    }\n  ],\n  \"country\": \"US\",\n  \"metadata\": {\n    \"batch_name\": \"Q1 Product Sync\",\n    \"initiated_by\": \"automation\"\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "id": "batch_abc123def456",
  "object": "batch",
  "status": "in_progress",
  "created": 1704067200,
  "total_urls": 2,
  "completed_urls": 0,
  "country": "US",
  "metadata": {
    "batch_name": "Q1 Product Sync",
    "initiated_by": "automation"
  }
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "validation_error",
  "type": "https://docs.olostep.com/api-reference/errors/bad_request",
  "status": 400,
  "title": "Solicitud Incorrecta",
  "detail": "The 'items' array is required and must contain at least one item.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "invalid_api_key",
  "type": "https://docs.olostep.com/api-reference/errors/unauthorized",
  "status": 401,
  "title": "No autorizado",
  "detail": "Your API key is invalid. Try double-checking it or reaching out to info@olostep.com if you're facing issues.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "credits_exhausted",
  "type": "https://docs.olostep.com/api-reference/errors/payment_required",
  "status": 402,
  "title": "Pago Requerido",
  "detail": "You have consumed all available credits. Please upgrade your plan from the dashboard: https://www.olostep.com/auth/",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "access_denied",
  "type": "https://docs.olostep.com/api-reference/errors/forbidden",
  "status": 403,
  "title": "Prohibido",
  "detail": "You don't have access to this feature. Please reach out to info@olostep.com to get approved",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "idempotency_key_in_progress",
  "type": "https://docs.olostep.com/api-reference/errors/idempotency_error",
  "status": 409,
  "title": "Error de Idempotencia",
  "detail": "A request with this idempotency key is currently being processed. Please wait and retry.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "idempotency_key_reuse",
  "type": "https://docs.olostep.com/api-reference/errors/unprocessable_entity",
  "status": 422,
  "title": "Entidad No Procesable",
  "detail": "A request with this idempotency key was already made with different parameters. Idempotency keys must be unique per request.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "internal_server_error",
  "type": "https://docs.olostep.com/api-reference/errors/internal_error",
  "status": 500,
  "title": "Error Interno del Servidor",
  "detail": "An unexpected error occurred",
  "created": 1704067200,
  "metadata": {}
}

POST

batches

Iniciar un nuevo lote

curl --request POST \
  --url https://api.olostep.com/v1/batches \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "items": [
    {
      "custom_id": "product-123",
      "url": "https://example.com/product/123",
      "metadata": {
        "source": "catalog_sync",
        "priority": "high"
      }
    },
    {
      "custom_id": "product-456",
      "url": "https://example.com/product/456"
    }
  ],
  "country": "US",
  "metadata": {
    "batch_name": "Q1 Product Sync",
    "initiated_by": "automation"
  }
}
'

import requests

url = "https://api.olostep.com/v1/batches"

payload = {
    "items": [
        {
            "custom_id": "product-123",
            "url": "https://example.com/product/123",
            "metadata": {
                "source": "catalog_sync",
                "priority": "high"
            }
        },
        {
            "custom_id": "product-456",
            "url": "https://example.com/product/456"
        }
    ],
    "country": "US",
    "metadata": {
        "batch_name": "Q1 Product Sync",
        "initiated_by": "automation"
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    items: [
      {
        custom_id: 'product-123',
        url: 'https://example.com/product/123',
        metadata: {source: 'catalog_sync', priority: 'high'}
      },
      {custom_id: 'product-456', url: 'https://example.com/product/456'}
    ],
    country: 'US',
    metadata: {batch_name: 'Q1 Product Sync', initiated_by: 'automation'}
  })
};

fetch('https://api.olostep.com/v1/batches', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.olostep.com/v1/batches",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'items' => [
        [
                'custom_id' => 'product-123',
                'url' => 'https://example.com/product/123',
                'metadata' => [
                                'source' => 'catalog_sync',
                                'priority' => 'high'
                ]
        ],
        [
                'custom_id' => 'product-456',
                'url' => 'https://example.com/product/456'
        ]
    ],
    'country' => 'US',
    'metadata' => [
        'batch_name' => 'Q1 Product Sync',
        'initiated_by' => 'automation'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.olostep.com/v1/batches"

	payload := strings.NewReader("{\n  \"items\": [\n    {\n      \"custom_id\": \"product-123\",\n      \"url\": \"https://example.com/product/123\",\n      \"metadata\": {\n        \"source\": \"catalog_sync\",\n        \"priority\": \"high\"\n      }\n    },\n    {\n      \"custom_id\": \"product-456\",\n      \"url\": \"https://example.com/product/456\"\n    }\n  ],\n  \"country\": \"US\",\n  \"metadata\": {\n    \"batch_name\": \"Q1 Product Sync\",\n    \"initiated_by\": \"automation\"\n  }\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.olostep.com/v1/batches")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"items\": [\n    {\n      \"custom_id\": \"product-123\",\n      \"url\": \"https://example.com/product/123\",\n      \"metadata\": {\n        \"source\": \"catalog_sync\",\n        \"priority\": \"high\"\n      }\n    },\n    {\n      \"custom_id\": \"product-456\",\n      \"url\": \"https://example.com/product/456\"\n    }\n  ],\n  \"country\": \"US\",\n  \"metadata\": {\n    \"batch_name\": \"Q1 Product Sync\",\n    \"initiated_by\": \"automation\"\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.olostep.com/v1/batches")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"items\": [\n    {\n      \"custom_id\": \"product-123\",\n      \"url\": \"https://example.com/product/123\",\n      \"metadata\": {\n        \"source\": \"catalog_sync\",\n        \"priority\": \"high\"\n      }\n    },\n    {\n      \"custom_id\": \"product-456\",\n      \"url\": \"https://example.com/product/456\"\n    }\n  ],\n  \"country\": \"US\",\n  \"metadata\": {\n    \"batch_name\": \"Q1 Product Sync\",\n    \"initiated_by\": \"automation\"\n  }\n}"

response = http.request(request)
puts response.read_body

{
  "id": "batch_abc123def456",
  "object": "batch",
  "status": "in_progress",
  "created": 1704067200,
  "total_urls": 2,
  "completed_urls": 0,
  "country": "US",
  "metadata": {
    "batch_name": "Q1 Product Sync",
    "initiated_by": "automation"
  }
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "validation_error",
  "type": "https://docs.olostep.com/api-reference/errors/bad_request",
  "status": 400,
  "title": "Solicitud Incorrecta",
  "detail": "The 'items' array is required and must contain at least one item.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "invalid_api_key",
  "type": "https://docs.olostep.com/api-reference/errors/unauthorized",
  "status": 401,
  "title": "No autorizado",
  "detail": "Your API key is invalid. Try double-checking it or reaching out to info@olostep.com if you're facing issues.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "credits_exhausted",
  "type": "https://docs.olostep.com/api-reference/errors/payment_required",
  "status": 402,
  "title": "Pago Requerido",
  "detail": "You have consumed all available credits. Please upgrade your plan from the dashboard: https://www.olostep.com/auth/",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "access_denied",
  "type": "https://docs.olostep.com/api-reference/errors/forbidden",
  "status": 403,
  "title": "Prohibido",
  "detail": "You don't have access to this feature. Please reach out to info@olostep.com to get approved",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "idempotency_key_in_progress",
  "type": "https://docs.olostep.com/api-reference/errors/idempotency_error",
  "status": 409,
  "title": "Error de Idempotencia",
  "detail": "A request with this idempotency key is currently being processed. Please wait and retry.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "idempotency_key_reuse",
  "type": "https://docs.olostep.com/api-reference/errors/unprocessable_entity",
  "status": 422,
  "title": "Entidad No Procesable",
  "detail": "A request with this idempotency key was already made with different parameters. Idempotency keys must be unique per request.",
  "created": 1704067200,
  "metadata": {}
}

{
  "id": "error_abc123",
  "object": "error",
  "code": "internal_server_error",
  "type": "https://docs.olostep.com/api-reference/errors/internal_error",
  "status": 500,
  "title": "Error Interno del Servidor",
  "detail": "An unexpected error occurred",
  "created": 1704067200,
  "metadata": {}
}

Recibe notificaciones al completar: Pasa el parámetro webhook con la URL de tu endpoint para recibir un HTTP POST cuando el lote se complete. Consulta Webhooks para más detalles.

Adjunta datos personalizados: Usa el parámetro metadata para almacenar pares clave-valor. Se admite en dos niveles:

Nivel de lote — en el cuerpo de la solicitud
Nivel de elemento — en cada elemento del array items

Consulta Metadata para más detalles.

Autorizaciones

Authorization

string

header

requerido

Encabezado de autenticación Bearer de la forma Bearer , donde es tu token de autenticación.

Cuerpo

application/json

items

object[]

requerido

Array de elementos a procesar en el lote.

Show child attributes

country

string

País para la ejecución del lote. Proporciona en códigos ISO 3166-1 alfa-2 como US(USA), IN(India), etc.

parser

object

Puedes usar este parámetro para especificar el parser a utilizar. Los parsers son útiles para extraer contenido estructurado de páginas web. Olostep tiene algunos parsers integrados para las páginas web más comunes, y también puedes crear tus propios parsers.

Show child attributes

links_on_page

object

Obtén todos los enlaces presentes en cada página del lote. Los enlaces siempre se devuelven como URLs absolutas.

Show child attributes

metadata

object

Conjunto de pares clave-valor para almacenar información adicional sobre un objeto. Sigue el enfoque de Stripe con reglas de validación: máximo 50 claves, clave máximo 40 caracteres (sin corchetes), valor máximo 500 caracteres, todos los valores almacenados como cadenas.

Show child attributes

Ejemplo:

{
  "order_id": "12345",
  "customer_name": "John Doe",
  "priority": "high",
  "processed": "true"
}

webhook

string<uri>

URL HTTPS para recibir una solicitud POST cuando el lote se complete. Debe ser un URL públicamente accesible usando el protocolo http:// o https://. No puede apuntar a localhost o direcciones IP privadas. Consulta Webhooks para el formato de carga útil y el comportamiento de reintento.

Respuesta

Lote iniciado con éxito.

string

ID del Lote

object

string

El tipo de objeto. "batch" para este endpoint.

status

string

in_progress o completed

created

number

Época creada

total_urls

number

Conteo de URLs en el lote

completed_urls

number

Conteo de URLs completadas

parser

string

country

string

metadata

object

Show child attributes

Ejemplo:

{
  "order_id": "12345",
  "customer_name": "John Doe",
  "priority": "high",
  "processed": "true"
}

webhook

string

URL del webhook para recibir notificación de finalización

credits_consumed

integer | null

Número de créditos consumidos por esta solicitud. Se completa después de que la ejecución finaliza. Los créditos son la fuente de verdad para la facturación.

cost_usd

number | null

Costo estimado en USD para esta solicitud. Se completa después de que la ejecución finaliza. Calculado a partir de los créditos consumidos y tu tarifa de plan — 99% preciso, pero credits_consumed es el valor autoritativo.

Obtener Scrape Información del Lote