Extract page links

Fetches one public HTML page and returns unique normalized HTTP/HTTPS links with anchor text, rel values, and same-origin classification. Use this for bounded navigation discovery; it does not crawl the returned links. Limit: 8 s, 5 redirects, 768 KiB, 500 links.

When to use it

Fetches one public HTML page and returns unique normalized HTTP/HTTPS links with anchor text, rel values, and same-origin classification. Use this for bounded navigation discovery; it does not crawl the returned links.

Input schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "minLength": 8,
      "maxLength": 2048,
      "description": "Absolute public HTTP or HTTPS URL without embedded credentials."
    },
    "include_external": {
      "default": true,
      "type": "boolean"
    },
    "max_links": {
      "default": 100,
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    }
  },
  "required": [
    "url",
    "include_external",
    "max_links"
  ],
  "additionalProperties": false
}

Output schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "ok": {
      "const": true
    },
    "data": {
      "type": "object",
      "properties": {
        "requested_url": {
          "type": "string"
        },
        "final_url": {
          "type": "string"
        },
        "links": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "url": {
                "type": "string"
              },
              "text": {
                "type": [
                  "string",
                  "null"
                ]
              },
              "rel": {
                "type": "array",
                "items": {
                  "type": "string"
                }
              },
              "external": {
                "type": "boolean"
              }
            },
            "required": [
              "url",
              "text",
              "rel",
              "external"
            ]
          }
        },
        "truncated": {
          "type": "boolean"
        },
        "max_links": {
          "type": "integer"
        }
      },
      "required": [
        "requested_url",
        "final_url",
        "links",
        "truncated",
        "max_links"
      ]
    },
    "meta": {
      "type": "object",
      "properties": {
        "request_id": {
          "type": "string"
        },
        "duration_ms": {
          "type": "integer"
        },
        "limits": {
          "type": "object"
        }
      },
      "required": [
        "request_id",
        "duration_ms"
      ]
    }
  },
  "required": [
    "ok",
    "data",
    "meta"
  ],
  "additionalProperties": false
}

REST example

curl -X POST https://plainport.exportitnow.workers.dev/api/v1/extract-links \
  -H "content-type: application/json" \
  -d '{"url":"https://example.com"}'

Example result

{
  "ok": true,
  "data": {
    "links": [
      {
        "url": "https://example.com/more",
        "text": "More information",
        "external": false
      }
    ],
    "truncated": false
  },
  "meta": {
    "request_id": "018f…",
    "duration_ms": 12
  }
}

Limit