Get job status - ScrapeLLM

GET

jobs

{job_id}

Get async job status

curl --request GET \
  --url https://api.scrapellm.com/jobs/{job_id}

import requests

url = "https://api.scrapellm.com/jobs/{job_id}"

response = requests.get(url)

print(response.text)

const options = {method: 'GET'};

fetch('https://api.scrapellm.com/jobs/{job_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.scrapellm.com/jobs/{job_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.scrapellm.com/jobs/{job_id}"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api.scrapellm.com/jobs/{job_id}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.scrapellm.com/jobs/{job_id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body

{
  "job_id": "3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c",
  "status": "pending",
  "scraper": "chatgpt",
  "prompt": "What brands do marketers recommend for email automation?",
  "country": "US",
  "created_at": "2026-05-11T12:00:00+00:00"
}

No authentication requiredThe job_id is an unguessable UUID v4 - no API key needed to poll job status.

Status values

Status	Description
`pending`	Job is queued - the scrape has not completed yet
`done`	Scrape succeeded - `result` contains the full response
`failed`	All retry attempts failed - `error` contains the reason

Example request

curl "https://api.scrapellm.com/jobs/3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c"

import time, requests

job_id = "3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c"

while True:
    job = requests.get(
        f"https://api.scrapellm.com/jobs/{job_id}"
    ).json()

    if job["status"] == "done":
        print(job["result"])
        break
    if job["status"] == "failed":
        print("Scrape failed:", job.get("error"))
        break

    time.sleep(3)

const jobId = "3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c";

async function waitForJob(jobId) {
  while (true) {
    const resp = await fetch(`https://api.scrapellm.com/jobs/${jobId}`);
    const job = await resp.json();

    if (job.status === "done") return job.result;
    if (job.status === "failed") throw new Error(job.error);

    await new Promise(r => setTimeout(r, 3000));
  }
}

const result = await waitForJob(jobId);
console.log(result);

Response

Pending

{
  "job_id": "3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c",
  "status": "pending",
  "scraper": "chatgpt",
  "prompt": "What brands do marketers recommend for email automation?",
  "country": "US",
  "created_at": "2026-05-11T12:00:00+00:00"
}

Done

{
  "job_id": "3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c",
  "status": "done",
  "scraper": "chatgpt",
  "prompt": "What brands do marketers recommend for email automation?",
  "country": "US",
  "result": {
    "scraper": "chatgpt",
    "status": "done",
    "result": "Marketers commonly recommend Mailchimp, HubSpot, and Klaviyo...",
    "links": [...],
    "search_queries": [...],
    "credits_used": 3,
    "elapsed_ms": 8243.5,
    "cached": false
  },
  "created_at": "2026-05-11T12:00:00+00:00",
  "completed_at": "2026-05-11T12:00:18+00:00"
}

Failed

{
  "job_id": "3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c",
  "status": "failed",
  "scraper": "chatgpt",
  "error": "execution failed",
  "created_at": "2026-05-11T12:00:00+00:00",
  "completed_at": "2026-05-11T12:01:45+00:00"
}

Response fields

string

The unique job identifier.

string

Current state: pending, done, or failed.

string

The scraper that processed this job.

object

Full scrape response. Present only when status is "done". Schema matches the sync endpoint response for the same scraper.

string

Error message. Present only when status is "failed".

string

ISO 8601 UTC timestamp when the job was submitted.

string

ISO 8601 UTC timestamp when the job finished (done or failed). Null while pending.

Job retention

Jobs are retained for 24 hours after creation. After that, the job ID returns HTTP 404.

Error codes

Status	Meaning
`404`	Job not found or expired (jobs are retained for 24 hours)

Path Parameters

job_id

string<uuid>

required

The UUID returned by POST /scrapers/chatgpt/jobs.

Response

Job found. Check the status field.

job_id

string<uuid>

required

The unique job identifier.

Example:

"3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c"

status

enum<string>

required

Current state of the job.

Available options:

pending,

done,

failed

Example:

"done"

scraper

string

required

The scraper that processed this job.

Example:

"chatgpt"

prompt

string

required

The prompt that was submitted.

Example:

"What brands do marketers recommend for email automation?"

country

string

required

The country the request was routed through.

Example:

"US"

created_at

string<date-time>

required

ISO 8601 UTC timestamp when the job was submitted.

Example:

"2026-05-11T12:00:00+00:00"

result

object | null

Full scrape response. Present only when status is "done". Schema matches the response from GET /scrapers/chatgpt.

Show child attributes

error

string | null

Error message. Present only when status is "failed".

Example:

"execution failed"

completed_at

string<date-time> | null

ISO 8601 UTC timestamp when the job finished (done or failed). Null while pending.

Example:

"2026-05-11T12:00:18+00:00"

Submit async job

Get async job status

curl --request GET \
  --url https://api.scrapellm.com/jobs/{job_id}

import requests

url = "https://api.scrapellm.com/jobs/{job_id}"

response = requests.get(url)

print(response.text)

const options = {method: 'GET'};

fetch('https://api.scrapellm.com/jobs/{job_id}', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.scrapellm.com/jobs/{job_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://api.scrapellm.com/jobs/{job_id}"

	req, _ := http.NewRequest("GET", url, nil)

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.get("https://api.scrapellm.com/jobs/{job_id}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.scrapellm.com/jobs/{job_id}")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)

response = http.request(request)
puts response.read_body

{
  "job_id": "3f7a2b1c-9e4d-4f8a-b2c1-7d6e5f4a3b2c",
  "status": "pending",
  "scraper": "chatgpt",
  "prompt": "What brands do marketers recommend for email automation?",
  "country": "US",
  "created_at": "2026-05-11T12:00:00+00:00"
}

​Status values

​Example request

​Response

​Pending

​Done

​Failed

​Response fields

​Job retention

​Error codes

Path Parameters

Response

Status values

Example request

Response

Pending

Done

Failed

Response fields

Job retention

Error codes