pagedistill.thumm.workers.dev

{
  "input": {
    "discoverable": true,
    "method": "GET",
    "queryParams": {
      "url": "Required. The absolute http(s) URL of the page to extract, percent-encoded."
    },
    "type": "http"
  },
  "output": {
    "properties": {
      "canonical": {
        "description": "Canonical URL, or null.",
        "type": [
          "string",
          "null"
        ]
      },
      "content_root": {
        "description": "Which element the text was taken from: 'main', 'article' or 'body'.",
        "type": "string"
      },
      "description": {
        "description": "Meta/OG description, or null.",
        "type": [
          "string",
          "null"
        ]
      },
      "headings": {
        "description": "Heading outline keyed h1..h6; each value is an array of heading strings.",
        "type": "object"
      },
      "text": {
        "description": "Boilerplate-stripped plain text of the main content.",
        "type": "string"
      },
      "title": {
        "description": "Page title, or null if absent.",
        "type": [
          "string",
          "null"
        ]
      },
      "truncated": {
        "description": "True if `text` hit the length cap.",
        "type": "boolean"
      },
      "url": {
        "description": "The URL that was fetched, after redirects.",
        "type": "string"
      },
      "word_count": {
        "description": "Word count of `text`.",
        "type": "number"
      }
    },
    "required": [
      "url",
      "text",
      "word_count",
      "truncated",
      "content_root"
    ],
    "type": "object"
  }
}