Polling for Status - HasData Documentation

You can check the status of a scraper job and fetch results manually using the job ID. This is useful if you’re not using webhooks or need to monitor job progress in your system.

Check Job Status

To check whether a job is still running or finished:

curl --request GET \
  --url 'https://api.hasdata.com/scrapers/jobs/:jobId' \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <your-api-key>'

const axios = require('axios').default;

const options = {
  method: 'GET',
  url: 'https://api.hasdata.com/scrapers/jobs/:jobId',
  headers: {'Content-Type': 'application/json', 'x-api-key': '<your-api-key>'}
};

try {
  const { data } = await axios.request(options);
  console.log(data);
} catch (error) {
  console.error(error);
}

import requests

url = "https://api.hasdata.com/scrapers/jobs/:jobId"

headers = {
    "Content-Type": "application/json",
    "x-api-key": "<your-api-key>"
}

response = requests.get(url, headers=headers)

print(response.json())

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.hasdata.com/scrapers/jobs/:jobId",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <your-api-key>",
  ],
]);

$response = curl_exec($curl);
curl_close($curl);

echo $response;

OkHttpClient client = new OkHttpClient();

Request request = new Request.Builder()
  .url("https://api.hasdata.com/scrapers/jobs/:jobId")
  .get()
  .addHeader("Content-Type", "application/json")
  .addHeader("x-api-key", "<your-api-key>")
  .build();

Response response = client.newCall(request).execute();

using System.Net.Http;

var client = new HttpClient();

var request = new HttpRequestMessage(new HttpMethod("GET"), "https://api.hasdata.com/scrapers/jobs/:jobId");
request.Headers.Add("x-api-key", "<your-api-key>");

using var response = await client.SendAsync(request);
response.EnsureSuccessStatusCode();
var content = await response.Content.ReadAsStringAsync();
Console.WriteLine(content);

require 'net/http'
require 'uri'

uri = URI("https://api.hasdata.com/scrapers/jobs/:jobId")

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

request = Net::HTTP::Get.new(uri)
request["Content-Type"] = 'application/json'
request["x-api-key"] = '<your-api-key>'

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

use reqwest::blocking::Client;

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = Client::new();
    let res = client
        .get("https://api.hasdata.com/scrapers/jobs/:jobId")
        .header("Content-Type", "application/json")
        .header("x-api-key", "<your-api-key>")
        .send()?
        .text()?;
    println!("{}", res);
    Ok(())
}

package main

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

func main() {
	req, _ := http.NewRequest("GET", "https://api.hasdata.com/scrapers/jobs/:jobId", nil)
	req.Header.Add("Content-Type", "application/json")
	req.Header.Add("x-api-key", "<your-api-key>")

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

	body, _ := io.ReadAll(res.Body)
	fmt.Println(string(body))
}

Example Response

{
  "id": "dd1a8c53-2d47-4444-977d-8d653a6a3c82",
  "status": "in_progress",
  "creditsSpent": 200,
  "dataRowsCount": 20,
  "input": {
    /* job parameters */
  }
}

{
  "id": "dd1a8c53-2d47-4444-977d-8d653a6a3c82",
  "status": "finished",
  "creditsSpent": 200,
  "dataRowsCount": 20,
  "data": {
    "csv": "https://api.hasdata.com/scrapers/jobs/dd1a8c53-2d47-4444-977d-8d653a6a3c82/results/b6cc6733-6d0e-4e44-9e94-38688aad3884.csv",
    "json": "https://api.hasdata.com/scrapers/jobs/dd1a8c53-2d47-4444-977d-8d653a6a3c82/results/9cb592e3-6700-42ff-b58c-e7da3f478f28.json",
    "xlsx": "https://api.hasdata.com/scrapers/jobs/dd1a8c53-2d47-4444-977d-8d653a6a3c82/results/ecea853c-e0ca-4a23-ae74-eea0588e54b6.xlsx"
  },
  "input": {
    "limit": 25,
    "urls": ["https://hasdata.com", "https://example.com"],
    "maxDepth": 5,
    "includePaths": "(blog/.+|articles/.+)",
    "webhook": {
      "url": "https://example.com/webhook",
      "events": ["scraper.job.started", "scraper.job.finished", "scraper.data.scraped"]
    }
  }
}

Job Statuses

pending — Waiting to be processed
in_progress — Currently running
finished — Completed

Fetch Results

Once the job status is finished, you can retrieve results:

curl --request GET -G \
  --url 'https://api.hasdata.com/scrapers/jobs/:jobId/results' \
  --data-urlencode 'page=1' \
  --data-urlencode 'limit=100' \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <your-api-key>'

const axios = require('axios').default;

const options = {
  method: 'GET',
  url: 'https://api.hasdata.com/scrapers/jobs/:jobId/results',
  params: {page: '1', limit: '100'},
  headers: {'Content-Type': 'application/json', 'x-api-key': '<your-api-key>'}
};

try {
  const { data } = await axios.request(options);
  console.log(data);
} catch (error) {
  console.error(error);
}

import requests

url = "https://api.hasdata.com/scrapers/jobs/:jobId/results"

querystring = {"page":"1","limit":"100"}

headers = {
    "Content-Type": "application/json",
    "x-api-key": "<your-api-key>"
}

response = requests.get(url, headers=headers, params=querystring)

print(response.json())

<?php

$params = [
    "page" => "1",
    "limit" => "100",
];

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.hasdata.com/scrapers/jobs/:jobId/results?" . http_build_query($params),
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <your-api-key>",
  ],
]);

$response = curl_exec($curl);
curl_close($curl);

echo $response;

OkHttpClient client = new OkHttpClient();

HttpUrl url = HttpUrl.parse("https://api.hasdata.com/scrapers/jobs/:jobId/results")
  .newBuilder()
  .addQueryParameter("page", "1")
  .addQueryParameter("limit", "100")
  .build();

Request request = new Request.Builder()
  .url(url)
  .get()
  .addHeader("Content-Type", "application/json")
  .addHeader("x-api-key", "<your-api-key>")
  .build();

Response response = client.newCall(request).execute();

using System.Net.Http;
using System.Web;

var client = new HttpClient();

var query = HttpUtility.ParseQueryString(string.Empty);
query["page"] = "1";
query["limit"] = "100";

var url = $"https://api.hasdata.com/scrapers/jobs/:jobId/results?{query}";

var request = new HttpRequestMessage(new HttpMethod("GET"), url);
request.Headers.Add("x-api-key", "<your-api-key>");

using var response = await client.SendAsync(request);
response.EnsureSuccessStatusCode();
var content = await response.Content.ReadAsStringAsync();
Console.WriteLine(content);

require 'net/http'
require 'uri'

uri = URI("https://api.hasdata.com/scrapers/jobs/:jobId/results")
params = {
  "page" => "1",
  "limit" => "100",
}
uri.query = URI.encode_www_form(params)

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

request = Net::HTTP::Get.new(uri)
request["Content-Type"] = 'application/json'
request["x-api-key"] = '<your-api-key>'

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

use reqwest::blocking::Client;

fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = Client::new();
    let res = client
        .get("https://api.hasdata.com/scrapers/jobs/:jobId/results")
        .query(&[("page", "1")])
        .query(&[("limit", "100")])
        .header("Content-Type", "application/json")
        .header("x-api-key", "<your-api-key>")
        .send()?
        .text()?;
    println!("{}", res);
    Ok(())
}

package main

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

func main() {
	params := url.Values{}
	params.Set("page", "1")
	params.Set("limit", "100")

	u := "https://api.hasdata.com/scrapers/jobs/:jobId/results?" + params.Encode()

	req, _ := http.NewRequest("GET", u, nil)
	req.Header.Add("Content-Type", "application/json")
	req.Header.Add("x-api-key", "<your-api-key>")

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

	body, _ := io.ReadAll(res.Body)
	fmt.Println(string(body))
}

Maximum limit is 100 per request.

Response Example

{
  "meta": {
    "total": 122,
    "perPage": 100,
    "currentPage": 1,
    "lastPage": 2,
    "firstPage": 1,
    "firstPageUrl": "/?page=1",
    "lastPageUrl": "/?page=2",
    "nextPageUrl": "/?page=2",
    "previousPageUrl": null
  },
  "data": [
    {
      "id": "8e705f7b-c542-403d-8acc-3e3d5c2f1271",
      "data": {
        "url": "https://example.com/page1",
        "statusCode": 200,
        "text": "Extracted content...",
        "title": "Example Page",
        "depth": 1
      },
      "createdAt": "2025-05-02T17:26:28.603+03:00",
      "updatedAt": "2025-05-02T17:26:28.603+03:00"
    },
    {
      "id": "01d1f7d2-43b4-4752-a114-b5e6601c5722",
      "data": {
        "url": "https://example.com/page2",
        "statusCode": 404,
        "error": "Page not found",
        "depth": 1
      },
      "createdAt": "2025-05-02T17:26:25.740+03:00",
      "updatedAt": "2025-05-02T17:26:25.740+03:00"
    }
  ]
}

​Check Job Status

​Example Response

​Job Statuses

​Fetch Results

​Response Example

Check Job Status

Example Response

Job Statuses

Fetch Results

Response Example