sites

Preview a site

Finds a site's pages (its sitemaps, else its links) without creating anything, so you can try rules on urls before POST /v1/resources with type: "site". Pages forbidden by robots.txt are left out.

POST/v1/sites/preview

Request

curl --request POST \
  --url 'https://api.lookio.app/v1/sites/preview' \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "url": "<string>"
}'

import json
import requests

url = "https://api.lookio.app/v1/sites/preview"
headers = {
  "Authorization": "<api-key>",
  "Content-Type": "application/json"
}
payload = json.loads("{\"url\":\"<string>\"}")

response = requests.request("POST", url, headers=headers, json=payload)
print(response.json())

const response = await fetch("https://api.lookio.app/v1/sites/preview", {
  method: "POST",
  headers: {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "url": "<string>"
  }),
});

const data = await response.json();
console.log(data);

<?php
$client = curl_init();

curl_setopt($client, CURLOPT_URL, "https://api.lookio.app/v1/sites/preview");
curl_setopt($client, CURLOPT_CUSTOMREQUEST, "POST");
curl_setopt($client, CURLOPT_HTTPHEADER, [
    "Authorization: <api-key>",
    "Content-Type: application/json",
]);
curl_setopt($client, CURLOPT_POSTFIELDS, "{\"url\":\"<string>\"}");
curl_setopt($client, CURLOPT_RETURNTRANSFER, true);

$response = curl_exec($client);
curl_close($client);
echo $response;

package main

import (
  "bytes"
  "fmt"
  "io"
  "net/http"
)

func main() {
  req, _ := http.NewRequest("POST", "https://api.lookio.app/v1/sites/preview", bytes.NewBuffer([]byte("{\"url\":\"<string>\"}")))
  req.Header.Set("Authorization", "<api-key>")
  req.Header.Set("Content-Type", "application/json")
  res, _ := http.DefaultClient.Do(req)
  defer res.Body.Close()
  data, _ := io.ReadAll(res.Body)
  fmt.Println(string(data))
}

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

var request = HttpRequest.newBuilder(URI.create("https://api.lookio.app/v1/sites/preview"))
    .header("Authorization", "<api-key>")
    .header("Content-Type", "application/json")
    .method("POST", HttpRequest.BodyPublishers.ofString("{\"url\":\"<string>\"}"))
    .build();

var response = HttpClient.newHttpClient().send(
    request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());

require 'net/http'
require 'json'

uri = URI("https://api.lookio.app/v1/sites/preview")
request = Net::HTTP::Post.new(uri)
request["Authorization"] = "<api-key>"
request["Content-Type"] = "application/json"
request.body = "{\"url\":\"<string>\"}"

response = Net::HTTP.start(uri.hostname, uri.port, use_ssl: uri.scheme == "https") do |http|
  http.request(request)
end

puts response.body

application/json

{
  "data": {
    "url": "<string>",
    "source": "sitemap",
    "sitemaps": [
      "<string>"
    ],
    "total": 123,
    "truncated": true,
    "disallowed": 123,
    "urls": [
      "<string>"
    ]
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "type": "<string>",
    "code": "<string>",
    "message": "<string>",
    "param": "<string>",
    "docs_url": "<string>",
    "action_url": "<string>"
  },
  "request_id": "<string>"
}

Requires resources:write.

Nothing is created and nothing is charged. It needs the same scope as creating a resource, because it fetches pages for you.

Lookio looks for the site’s sitemaps, then falls back to following links, and leaves out pages that robots.txt forbids. A site is capped at 10,000 pages, and truncated tells you when the cap was reached: narrow the rules.

Use the urls you get back to try your rules, then create the site with Create a resource. An address that cannot be analysed fails with invalid_request.

Authorizations

Authorizationbearerin headerrequired

Header parameters

Idempotency-Keystringlength: 1–255 chars

A unique key for this request, such as a UUID, 1 to 255 visible ASCII characters. Send the same key when you retry: the first response is returned (with Idempotent-Replayed: true) instead of running the request again, for 24 hours, per credential. The same key on a different request is a 409 conflict. A streamed answer is not recorded.

Body

application/jsonrequired

urlstringrequiredlength: 4–2000 chars

The site, a section such as https://docs.acme.com/guide, or its sitemap.

Response

application/json

Preview a site before importing it

dataobjectrequired

Show child attributes

data.urlstringrequired

data.sourceenum<string>requiredone of: sitemap, links

sitemap when the site publishes one, else links: pages found by following links.

data.sitemapsstring[]required

data.totalintegerrequired

data.truncatedbooleanrequired

True when the 10,000-page limit was reached: narrow the rules.

data.disallowedintegerrequired

Pages the site's robots.txt forbids, left out.

data.urlsstring[]required

The first pages found, to try rules against.

request_idstringrequired

{ "data": { "url": "<string>", "source": "sitemap", "sitemaps": [ "<string>" ], "total": 123, "truncated": true, "disallowed": 123, "urls": [ "<string>" ] }, "request_id": "<string>" }

{ "error": { "type": "<string>", "code": "<string>", "message": "<string>", "param": "<string>", "docs_url": "<string>", "action_url": "<string>" }, "request_id": "<string>" }

Preview a site

Authorizations

Header parameters

Body

Response

Use these docs with your AI tools

Query these docs via MCP

Query these docs over HTTP

Read these docs as Markdown