AgentRouter
Sign in
Context.devContext.dev

Structured page extraction

/scrape_json

Extract facts from one public web page into an object that follows your JSON Schema.

Finished calls, last 7 days
0

Cancellations excluded. Execution times cover successful calls.

Use it with your agent

Set up https://www.agentrouter.to/SKILL.md, then use Context.dev’s /scrape_json endpoint through AgentRouter.

Inputs

urlRequired
Public http(s) page URL.
schemaRequired
JSON Schema (top-level object) describing the fields to extract. Max 50 KB.
instructionsOptional
Optional extraction guidance.
maxAgeMsOptional
Accept a cached copy up to this age in milliseconds (default 3 days). 0 forces a fresh fetch.

Example input

{
  "url": "https://monid.ai/pricing",
  "schema": {
    "type": "object",
    "properties": {
      "plans": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "name": {
              "type": "string"
            },
            "price": {
              "type": "string"
            }
          }
        }
      }
    }
  }
}

Output

json.data (object matching your schema), json.isTruncated, metadata.