Discover by keywords

Use the Bright Data Web Scraper API to discover by Keywords. POST /datasets/v3/scrape starts a job that returns structured product records as JSON.

POST /datasets/v3/scrape

Discover by Keywords

cURL

curl --request POST \
  --url https://api.brightdata.com/datasets/v3/scrape \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "input": [
    {
      "keyword": "<string>",
      "url": "<string>",
      "pages_to_search": 123
    }
  ]
}
'

import requests

url = "https://api.brightdata.com/datasets/v3/scrape"

payload = { "input": [
        {
            "keyword": "<string>",
            "url": "<string>",
            "pages_to_search": 123
        }
    ] }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({input: [{keyword: '<string>', url: '<string>', pages_to_search: 123}]})
};

fetch('https://api.brightdata.com/datasets/v3/scrape', 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/scrape",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'input' => [
        [
                'keyword' => '<string>',
                'url' => '<string>',
                'pages_to_search' => 123
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

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

curl_close($curl);

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

package main

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

func main() {

	url := "https://api.brightdata.com/datasets/v3/scrape"

	payload := strings.NewReader("{\n  \"input\": [\n    {\n      \"keyword\": \"<string>\",\n      \"url\": \"<string>\",\n      \"pages_to_search\": 123\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.brightdata.com/datasets/v3/scrape")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"input\": [\n    {\n      \"keyword\": \"<string>\",\n      \"url\": \"<string>\",\n      \"pages_to_search\": 123\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.brightdata.com/datasets/v3/scrape")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"input\": [\n    {\n      \"keyword\": \"<string>\",\n      \"url\": \"<string>\",\n      \"pages_to_search\": 123\n    }\n  ]\n}"

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

200

[
  {
    "title": "Adjustable Laptop Stand for Desk",
    "url": "https://www.amazon.com/dp/B0B77889EF",
    "asin": "B0B77889EF",
    "price": 34.99,
    "currency": "USD",
    "rating": 4.7,
    "reviews_count": 15200,
    "seller_name": "DeskPro Accessories",
    "brand": "DeskPro",
    "availability": "In Stock",
    "main_image": "https://m.media-amazon.com/images/I/example-stand.jpg",
    "description": "Ergonomic aluminum laptop stand with adjustable height and angle.",
    "category": "Office Products > Desk Accessories > Laptop Stands",
    "country_domain": "amazon.com"
  }
]

Query Parameters

dataset_id · string · default: "gd_lwhideng15g8jg63s7" · required

The dataset ID used for this request.

Must be set to gd_lwhideng15g8jg63s7 to collect Discover by Keywords data.

type · string · default: "discover_new"

Must be set to discover_new.

discover_by · string · default: "keyword"

Must be set to keyword.

notify · boolean · default: false

Whether to send notifications when the request is completed.

include_errors · boolean · default: true

Whether to include errors in the response.

Request Body

input · object[] · required

An array of input objects.

Show properties

keyword · string · required

The keyword to search for products.

url · string · required

The Amazon domain to search on (e.g. https://www.amazon.com).

pages_to_search · number

The number of search result pages to collect.

Example

{
  "input": [
    {
      "keyword": "laptop stand",
      "url": "https://www.amazon.com",
      "pages_to_search": 3
    }
  ]
}

200

[
  {
    "title": "Adjustable Laptop Stand for Desk",
    "url": "https://www.amazon.com/dp/B0B77889EF",
    "asin": "B0B77889EF",
    "price": 34.99,
    "currency": "USD",
    "rating": 4.7,
    "reviews_count": 15200,
    "seller_name": "DeskPro Accessories",
    "brand": "DeskPro",
    "availability": "In Stock",
    "main_image": "https://m.media-amazon.com/images/I/example-stand.jpg",
    "description": "Ergonomic aluminum laptop stand with adjustable height and angle.",
    "category": "Office Products > Desk Accessories > Laptop Stands",
    "country_domain": "amazon.com"
  }
]