> ## Documentation Index
> Fetch the complete documentation index at: https://docs.context.dev/llms.txt
> Use this file to discover all available pages before exploring further.
# Extract Products
> Build a structured product catalog from a brand website without hand-written scrapers.
10 Credits Beta Feature
## OpenAPI
````yaml POST /brand/ai/products
openapi: 3.0.0
info:
title: Context API
description: API for retrieving context data from any website
version: 1.0.0
servers:
- url: https://api.context.dev/v1
security: []
tags:
- name: Monitors
description: >-
Monitor pages, sitemaps, and extracted website data for exact or semantic
changes. The change.detected webhook payload is documented by the
MonitorsChangeDetectedWebhookPayload schema.
paths:
/brand/ai/products:
post:
tags:
- Web Extraction
summary: Extract products from a brand's website
description: >-
Extract product information from a brand's website. We will analyze the
website and return a list of products with details such as name,
description, image, pricing, features, and more.
requestBody:
required: true
content:
application/json:
schema:
oneOf:
- title: By Domain
type: object
required:
- domain
properties:
domain:
type: string
description: The domain name to analyze.
maxProducts:
type: integer
minimum: 1
maximum: 12
description: Maximum number of products to extract.
maxAgeMs:
type: integer
minimum: 0
maximum: 2592000000
default: 604800000
description: >-
Return a cached result if a prior scrape for the same
parameters exists and is younger than this many
milliseconds. Defaults to 7 days (604800000 ms) when
omitted. Max is 30 days (2592000000 ms). Set to 0 to
always scrape fresh.
timeoutMS:
$ref: '#/components/schemas/TimeoutMS'
- title: By Direct URL
type: object
required:
- directUrl
properties:
directUrl:
type: string
format: uri
description: >-
A specific URL to use directly as the starting point for
extraction without domain resolution.
maxProducts:
type: integer
minimum: 1
maximum: 12
description: Maximum number of products to extract.
maxAgeMs:
type: integer
minimum: 0
maximum: 2592000000
default: 604800000
description: >-
Return a cached result if a prior scrape for the same
parameters exists and is younger than this many
milliseconds. Defaults to 7 days (604800000 ms) when
omitted. Max is 30 days (2592000000 ms). Set to 0 to
always scrape fresh.
timeoutMS:
$ref: '#/components/schemas/TimeoutMS'
responses:
'200':
description: Successful response
content:
application/json:
schema:
type: object
properties:
products:
type: array
description: Array of products extracted from the website
items:
type: object
properties:
name:
type: string
description: Name of the product
description:
type: string
description: Description of the product
price:
type: number
nullable: true
description: Price of the product
currency:
type: string
nullable: true
description: Currency code for the price (e.g., USD, EUR)
billing_frequency:
type: string
nullable: true
enum:
- monthly
- yearly
- one_time
- usage_based
description: Billing frequency for the product
pricing_model:
type: string
nullable: true
enum:
- per_seat
- flat
- tiered
- freemium
- custom
description: Pricing model for the product
url:
type: string
nullable: true
description: URL to the product page
category:
type: string
nullable: true
description: Category of the product
features:
type: array
description: List of product features
items:
type: string
target_audience:
type: array
description: Target audience for the product (array of strings)
items:
type: string
tags:
type: array
description: Tags associated with the product
items:
type: string
image_url:
type: string
nullable: true
description: URL to the product image
images:
type: array
description: URLs to product images on the page (up to 7)
items:
type: string
sku:
type: string
nullable: true
description: >-
Stock Keeping Unit (product identifier). Null if no
identifier is found.
required:
- name
- description
- features
- target_audience
- tags
- images
- sku
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
'400':
description: Bad Request - validation error
content:
application/json:
schema:
type: object
properties:
message:
type: string
description: Error message
error_code:
type: string
enum:
- INTERNAL_ERROR
- VALID
- NOT_FOUND
- FORBIDDEN
- USAGE_EXCEEDED
- RATE_LIMITED
- UNAUTHORIZED
- DISABLED
- INSUFFICIENT_PERMISSIONS
- TIMEOUT_EXCEEDS_MAXIMUM
- WEBSITE_ACCESS_ERROR
- INPUT_VALIDATION_ERROR
description: Error code indicating the type of error
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
'401':
description: Unauthorized
content:
application/json:
schema:
type: object
properties:
error_code:
type: string
enum:
- INTERNAL_ERROR
- VALID
- NOT_FOUND
- FORBIDDEN
- USAGE_EXCEEDED
- RATE_LIMITED
- UNAUTHORIZED
- DISABLED
- INSUFFICIENT_PERMISSIONS
- TIMEOUT_EXCEEDS_MAXIMUM
- WEBSITE_ACCESS_ERROR
- INPUT_VALIDATION_ERROR
description: Error code indicating the type of error
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
'408':
description: Request Timeout
content:
application/json:
schema:
type: object
properties:
message:
type: string
description: Timeout error message
error_code:
type: string
enum:
- REQUEST_TIMEOUT
description: Error code indicating request timeout
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
'429':
$ref: '#/components/responses/RateLimited'
'500':
description: Internal server error
content:
application/json:
schema:
type: object
properties:
message:
type: string
description: Error message
error_code:
type: string
enum:
- INTERNAL_ERROR
description: Error code indicating internal server error
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
security:
- bearerAuth: []
x-codeSamples:
- lang: JavaScript
source: >-
import ContextDev from 'context.dev';
const client = new ContextDev({
apiKey: process.env['CONTEXT_DEV_API_KEY'], // This is the default and can be omitted
});
const response = await client.ai.extractProducts({ domain: 'domain'
});
console.log(response.key_metadata);
- lang: Python
source: |-
import os
from context.dev import ContextDev
client = ContextDev(
api_key=os.environ.get("CONTEXT_DEV_API_KEY"), # This is the default and can be omitted
)
response = client.ai.extract_products(
domain="domain",
)
print(response.key_metadata)
- lang: Go
source: "package main\n\nimport (\n\t\"context\"\n\t\"fmt\"\n\n\t\"github.com/context-dot-dev/context-go-sdk\"\n\t\"github.com/context-dot-dev/context-go-sdk/option\"\n)\n\nfunc main() {\n\tclient := contextdev.NewClient(\n\t\toption.WithAPIKey(\"My API Key\"),\n\t)\n\tresponse, err := client.AI.ExtractProducts(context.TODO(), contextdev.AIExtractProductsParams{\n\t\tOfByDomain: &contextdev.AIExtractProductsParamsBodyByDomain{\n\t\t\tDomain: \"domain\",\n\t\t},\n\t})\n\tif err != nil {\n\t\tpanic(err.Error())\n\t}\n\tfmt.Printf(\"%+v\\n\", response.KeyMetadata)\n}\n"
- lang: Ruby
source: |-
require "context_dev"
context_dev = ContextDev::Client.new(api_key: "My API Key")
response = context_dev.ai.extract_products(body: {domain: "domain"})
puts(response)
- lang: PHP
source: >-
ai->extractProducts(
domain: 'domain',
maxAgeMs: 0,
maxProducts: 1,
timeoutMs: 1000,
directURL: 'https://example.com',
);
var_dump($response);
} catch (APIException $e) {
echo $e->getMessage();
}
- lang: CLI
source: |-
context-dev ai extract-products \
--api-key 'My API Key' \
--domain domain \
--direct-url https://example.com
components:
schemas:
TimeoutMS:
type: integer
minimum: 1000
maximum: 300000
description: >-
Optional timeout in milliseconds for the request. If the request takes
longer than this value, it will be aborted with a 408 status code.
Maximum allowed value is 300000ms (5 minutes).
KeyMetadata:
type: object
description: >-
Metadata about the API key used for the request. Included in every
response whenever a valid API key is provided, even when the response
status is not 200.
properties:
credits_consumed:
type: integer
description: The number of credits consumed by this request.
credits_remaining:
type: integer
description: >-
The number of credits remaining for your organization after this
request.
required:
- credits_consumed
- credits_remaining
responses:
RateLimited:
description: Rate limit exceeded
headers:
Retry-After:
description: Seconds until the per-minute rate limit window resets
schema:
type: integer
minimum: 1
maximum: 60
content:
application/json:
schema:
type: object
properties:
message:
type: string
description: Error message
error_code:
type: string
enum:
- RATE_LIMITED
description: Error code indicating the rate limit was exceeded
key_metadata:
$ref: '#/components/schemas/KeyMetadata'
required:
- message
- error_code
securitySchemes:
bearerAuth:
type: http
scheme: bearer
````