Web Page Image Scraper

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "Full URL to fetch, including the http:// or https:// scheme."
    },
    "dedupe": {
      "type": "boolean",
      "default": false,
      "description": "Remove visually duplicate images: every image is loaded and perceptually hashed and only the highest-resolution copy of each duplicate group is kept. Default false."
    },
    "maxAgeMs": {
      "type": "integer",
      "default": 86400000,
      "maximum": 2592000000,
      "minimum": 0,
      "description": "Reuse a cached result younger than this many milliseconds. Default 86400000 (1 day), max 2592000000 (30 days). Set 0 to always fetch fresh."
    },
    "timeoutMS": {
      "type": "integer",
      "maximum": 300000,
      "minimum": 1000,
      "description": "Upstream timeout in milliseconds (max 300000). Context.dev aborts the call with a 408 when exceeded. Keep it below the endpoint's requestTimeoutMs so the provider answers before the platform's own budget expires."
    },
    "waitForMs": {
      "type": "integer",
      "maximum": 30000,
      "minimum": 0,
      "description": "Extra browser wait in milliseconds after page load before the content is captured (0-30000). Useful for JavaScript-heavy pages."
    }
  },
  "additionalProperties": false
}

{
  "type": "object",
  "required": [
    "success",
    "url",
    "images",
    "cache_metadata"
  ],
  "properties": {
    "url": {
      "type": "string",
      "format": "uri",
      "description": "The URL that was scraped (echoes the request)."
    },
    "images": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "alt": {
            "type": [
              "string",
              "null"
            ],
            "description": "The image's alt text. Observed null on most images (including every linked asset seen) and a short string on at least one inline icon -- not reliably present."
          },
          "src": {
            "type": "string",
            "description": "The image's location: an absolute URL when `type` is \"url\" (a linked asset, e.g. an <img> src or favicon), or the raw inline markup (e.g. a full `<svg>...</svg>` string) when `type` is \"html\"."
          },
          "type": {
            "type": "string",
            "description": "\"url\" when `src` is a linked asset, \"html\" when `src` is inline markup."
          },
          "element": {
            "type": "string",
            "description": "The source HTML context the image was found in, e.g. \"img\", \"svg\", \"link\", \"meta\", or \"css\" (a CSS background-image), as observed across fixtures."
          }
        },
        "additionalProperties": true
      },
      "description": "Every image asset found on the page, in document order. Empty when the page has no detectable image assets (observed on example.com)."
    },
    "success": {
      "type": "boolean",
      "description": "Whether the scrape completed successfully."
    },
    "cache_metadata": {
      "type": "object",
      "properties": {
        "age_ms": {
          "type": "number",
          "description": "Age of the cached result in milliseconds. 0 on a fresh (miss) fetch."
        },
        "status": {
          "type": "string",
          "description": "\"miss\" or \"hit\", both observed across the two kept fixtures."
        }
      },
      "description": "Whether this result was served from cache and, if so, how old it is.",
      "additionalProperties": true
    }
  },
  "description": "The scrape result, narrowed to routing.responseResultPath ($.output).",
  "additionalProperties": true
}