Crawl

Start a crawl job

POSThttps://app.hyperbrowser.ai/api/crawl

Authorization

ApiKeyAuth

Body

application/json

url*string

maxPagesinteger

followLinksboolean

ignoreSitemapboolean

excludePatternsarray of string

includePatternsarray of string

sessionOptionsCreateSessionParams (object)

scrapeOptionsScrapeOptions (object)

Response

200400500

Crawl job started successfully

Body

application/json

jobId*string

Request

JavaScriptCurlPython

const response = await fetch('https://app.hyperbrowser.ai/api/crawl', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "url": "text"
    }),
});
const data = await response.json();

Response

200400500

{
  "jobId": "text"
}

Get crawl job status and results

GEThttps://app.hyperbrowser.ai/api/crawl/{id}

Authorization

ApiKeyAuth

Path parameters

id*string

Query parameters

Response

200404500

Crawl job details retrieved successfully

Body

application/json

jobId*string (uuid)

status*enum

pendingrunningcompletedfailed

errornullable string

totalCrawledPagesinteger

totalPageBatchesinteger

currentPageBatchinteger

batchSizeinteger

dataarray of CrawledPage (object)

Request

JavaScriptCurlPython

const response = await fetch('https://app.hyperbrowser.ai/api/crawl/{id}', {
    method: 'GET',
    headers: {},
});
const data = await response.json();

Response

200404500

{
  "jobId": "123e4567-e89b-12d3-a456-426614174000",
  "status": "pending",
  "error": "text",
  "totalCrawledPages": 0,
  "totalPageBatches": 0,
  "currentPageBatch": 0,
  "batchSize": 0,
  "data": [
    {
      "url": "text",
      "status": "completed",
      "error": "text",
      "markdown": "text",
      "html": "text",
      "links": [
        "text"
      ]
    }
  ]
}