Monitor progress

cURL

curl --request GET \
  --url https://api.brightdata.com/datasets/v3/progress/{snapshot_id} \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.brightdata.com/datasets/v3/progress/{snapshot_id}"

headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.brightdata.com/datasets/v3/progress/{snapshot_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.brightdata.com/datasets/v3/progress/{snapshot_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($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.brightdata.com/datasets/v3/progress/{snapshot_id}"

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

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.brightdata.com/datasets/v3/progress/{snapshot_id}")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

{
  "snapshot_id": "s_m4x7enmven8djfqak",
  "dataset_id": "ds_123456789",
  "status": "running"
}

{
  "error": "User authentication is required"
}

{
  "error": "Snapshot not found"
}

GET

datasets

progress

{snapshot_id}

cURL

curl --request GET \
  --url https://api.brightdata.com/datasets/v3/progress/{snapshot_id} \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.brightdata.com/datasets/v3/progress/{snapshot_id}"

headers = {"Authorization": "Bearer <token>"}

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

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.brightdata.com/datasets/v3/progress/{snapshot_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.brightdata.com/datasets/v3/progress/{snapshot_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($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.brightdata.com/datasets/v3/progress/{snapshot_id}"

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

	req.Header.Add("Authorization", "Bearer <token>")

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

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

	fmt.Println(string(body))

}

require 'uri'
require 'net/http'

url = URI("https://api.brightdata.com/datasets/v3/progress/{snapshot_id}")

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

{
  "snapshot_id": "s_m4x7enmven8djfqak",
  "dataset_id": "ds_123456789",
  "status": "running"
}

{
  "error": "User authentication is required"
}

{
  "error": "Snapshot not found"
}

Asynchronous Usage: Trigger a data collection job via the async endpoint (/trigger), receive a snapshot_id, and poll the Monitor Progress API until the status is ready, then download the results.
Synchronous Usage: If a sync request (/scrape) exceeds the 1-minute timeout, receive a snapshot_id to poll the Monitor Progress API and download the results once they are ready.

The Monitor Progress API provides flexibility and stability, allowing efficient handling of large data volumes by differentiating between immediate and delayed result retrievals.

If the request takes too long, we recommend sending an Asynchronous request.

Authorizations

Authorization

string

header

required

Use your Bright Data API Key as a Bearer token in the Authorization header.

How to authenticate:

Obtain your API Key from the Bright Data account settings at https://brightdata.com/cp/setting/users
Include the API Key in the Authorization header of your requests
Format: Authorization: Bearer YOUR_API_KEY

Example:

Authorization: Bearer YOUR_API_KEY

Learn how to get your Bright Data API key: https://docs.brightdata.com/api-reference/authentication

Path Parameters

snapshot_id

string

required

The ID that was returned when the collection was triggered

Example:

"s_m4x7enmven8djfqak"

Response

Running

When status is failed, error_message is one of:

Something went wrong. Bright Data is looking into it.
Account is suspended
Account is new, please activate it in account settings. URL
No data found in discovery
Snapshot is empty
Failed to deliver snapshot
Failed to download response
Failed to trigger collector
Internal Server Error
Input validation failed: DETAILS

snapshot_id

string

dataset_id

string

status

enum<string>

Status of the snapshot

Available options:

starting,

running,

ready,

failed,

canceled

Essentials

Data extraction

AI training data

Proxy

Administrative APIs

Authorizations

Path Parameters

Response