> ## 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.
# Scrape Images
> Extract image assets from a web page, including standard URLs, inline SVGs, data URIs, responsive image sources, metadata, CSS backgrounds, video posters, and embeds. The base request costs 1 credit; enrichment costs 1 credit per returned image.
1 CreditEnriched: 1 Credit / Image
## OpenAPI
````yaml https://app.stainless.com/api/spec/documented/context.dev/openapi.documented.yml get /web/scrape/images
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: []
paths:
/web/scrape/images:
get:
tags:
- Web Scraping
summary: Scrape Images
description: >-
Extract image assets from a web page, including standard URLs, inline
SVGs, data URIs, responsive image sources, metadata, CSS backgrounds,
video posters, and embeds. The base request costs 1 credit; enrichment
costs 1 credit per returned image.
parameters:
- name: url
in: query
required: true
schema:
type: string
format: uri
description: Page URL to inspect. Must include http:// or https://.
- name: maxAgeMs
in: query
required: false
schema:
type: integer
minimum: 0
maximum: 2592000000
default: 86400000
description: >-
Reuse a cached result this many milliseconds old or newer. Default:
86400000 (1 day). Set to 0 to bypass cache. Maximum: 2592000000 (30
days).
- name: enrichment
in: query
required: false
style: deepObject
explode: true
schema:
type: object
additionalProperties: false
properties:
resolution:
type: boolean
default: false
description: Measure image width and height when possible.
hostedUrl:
type: boolean
default: false
description: >-
Host materializable images on the Brand.dev CDN and return
their URL and MIME type.
classification:
type: boolean
default: false
description: Classify each image by visual asset type.
maxTimePerMs:
type: integer
default: 30000
minimum: 1
maximum: 60000
description: >-
Per-image enrichment timeout in milliseconds. Default: 30000.
Maximum: 60000.
description: >-
Optional per-image processing, sent as deep-object query params such
as enrichment[resolution]=true.
- name: waitForMs
in: query
required: false
schema:
type: integer
minimum: 0
maximum: 30000
description: >-
Optional browser wait time in milliseconds after initial page load
before collecting images. Min: 0. Max: 30000 (30 seconds).
- $ref: '#/components/parameters/TimeoutMS'
responses:
'200':
description: Successful response
content:
application/json:
schema:
type: object
properties:
success:
type: boolean
enum:
- true
description: Always true on success.
images:
type: array
description: Images found on the page.
items:
type: object
properties:
src:
type: string
description: >-
Original image value: URL, inline SVG or HTML, or
base64 data URI.
element:
type: string
enum:
- img
- svg
- link
- source
- video
- css
- object
- meta
- background
description: Where the image was found.
type:
type: string
enum:
- url
- html
- base64
description: Format of src.
alt:
type: string
nullable: true
description: Image alt text, or null when unavailable.
enrichment:
type: object
description: >-
Requested metadata for images that could be
processed.
properties:
width:
type: integer
description: Image width in pixels, when measured.
height:
type: integer
description: Image height in pixels, when measured.
mimetype:
type: string
description: Detected MIME type, when hosted.
url:
type: string
format: uri
description: Brand.dev CDN URL, when hosted.
type:
type: string
enum:
- photography
- illustration
- logo
- wordmark
- icon
- pattern
- graphic
- other
description: Visual asset category, when classified.
required:
- src
- element
- type
- alt
url:
type: string
description: Page URL that was scraped.
required:
- success
- images
- url
'400':
description: Invalid URL or scrape failed.
content:
application/json:
schema:
type: object
properties:
message:
type: string
description: Error message describing the issue
error_code:
type: string
enum:
- INPUT_VALIDATION_ERROR
- WEBSITE_ACCESS_ERROR
description: Error code indicating the type of error
required:
- message
- error_code
'401':
description: Unauthorized - Invalid or missing API key
content:
application/json:
schema:
type: object
properties:
message:
type: string
description: Error message
error_code:
type: string
enum:
- UNAUTHORIZED
description: Error code indicating unauthorized access
'403':
description: Forbidden - Insufficient permissions or usage limit exceeded
content:
application/json:
schema:
type: object
properties:
message:
type: string
description: Error message
error_code:
type: string
enum:
- FORBIDDEN
- USAGE_EXCEEDED
- DISABLED
- INSUFFICIENT_PERMISSIONS
description: Error code indicating forbidden access
'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
'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
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.web.webScrapeImages({ url:
'https://example.com' });
console.log(response.images);
- 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.web.web_scrape_images(
url="https://example.com",
)
print(response.images)
- lang: Ruby
source: >-
require "context_dev"
context_dev = ContextDev::Client.new(api_key: "My API Key")
response = context_dev.web.web_scrape_images(url:
"https://example.com")
puts(response)
components:
parameters:
TimeoutMS:
name: timeoutMS
in: query
required: false
schema:
$ref: '#/components/schemas/TimeoutMS'
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).
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).
securitySchemes:
bearerAuth:
type: http
scheme: bearer
````