Collect Google AI Mode Search by URL

Use the Bright Data Web Scraper API to collect Google AI Mode search answers and citations by URL. POST /datasets/v3/scrape returns records as JSON.

POST /datasets/v3/scrape

Collect Google AI Mode Search by URL

cURL

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

import requests

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

payload = { "input": [
        {
            "url": "<string>",
            "prompt": "<string>",
            "country": "<string>"
        }
    ] }
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: [{url: '<string>', prompt: '<string>', country: '<string>'}]})
};

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' => [
        [
                'url' => '<string>',
                'prompt' => '<string>',
                'country' => '<string>'
        ]
    ]
  ]),
  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      \"url\": \"<string>\",\n      \"prompt\": \"<string>\",\n      \"country\": \"<string>\"\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      \"url\": \"<string>\",\n      \"prompt\": \"<string>\",\n      \"country\": \"<string>\"\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      \"url\": \"<string>\",\n      \"prompt\": \"<string>\",\n      \"country\": \"<string>\"\n    }\n  ]\n}"

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

200

[
  {
    "prompt": "how to train for a marathon",
    "answer": "A typical marathon training plan runs 16 to 20 weeks...",
    "citations": [
      {
        "title": "Marathon Training Plan for Beginners",
        "url": "https://example.com/marathon-plan"
      }
    ],
    "url": "https://www.google.com/search?udm=50&q=how+to+train+for+a+marathon"
  }
]

Query Parameters

dataset_id · string · default: "gd_mcswdt6z2elth3zqr2" · required

The dataset ID used for this request.

Must be set to gd_mcswdt6z2elth3zqr2 to collect Google AI Mode Search by URL.

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

url · string · required

The Google AI Mode Search URL to scrape (includes the udm=50 parameter).

prompt · string · required

The prompt used in the AI Mode Search query.

country · string

ISO 3166-1 alpha-2 country code for localized results.

Example

{
  "input": [
    {
      "url": "https://www.google.com/search?udm=50&q=how+to+train+for+a+marathon",
      "prompt": "how to train for a marathon",
      "country": "US"
    }
  ]
}

200

[
  {
    "prompt": "how to train for a marathon",
    "answer": "A typical marathon training plan runs 16 to 20 weeks...",
    "citations": [
      {
        "title": "Marathon Training Plan for Beginners",
        "url": "https://example.com/marathon-plan"
      }
    ],
    "url": "https://www.google.com/search?udm=50&q=how+to+train+for+a+marathon"
  }
]