Run a search

Run a search

curl --request POST \
  --url https://api.brightdata.com/webarchive/search \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "filters": {
    "max_age": "24h",
    "domain_whitelist": [
      "example.com"
    ],
    "domain_like_whitelist": [
      "%.example.%",
      "example%"
    ],
    "domain_regex_whitelist": [
      ".*example..*"
    ],
    "category_whitelist": [
      "Motor Vehicles"
    ],
    "url_like_whitelist": [
      "%/products/%",
      "%/search%"
    ],
    "url_regex_whitelist": [
      ".*/products/.*"
    ],
    "language_whitelist": [
      "eng"
    ],
    "ip_country_whitelist": [
      "us",
      "ie",
      "in"
    ],
    "captcha": true,
    "robots_block": true
  }
}
'

import requests

url = "https://api.brightdata.com/webarchive/search"

payload = { "filters": {
        "max_age": "24h",
        "domain_whitelist": ["example.com"],
        "domain_like_whitelist": ["%.example.%", "example%"],
        "domain_regex_whitelist": [".*example..*"],
        "category_whitelist": ["Motor Vehicles"],
        "url_like_whitelist": ["%/products/%", "%/search%"],
        "url_regex_whitelist": [".*/products/.*"],
        "language_whitelist": ["eng"],
        "ip_country_whitelist": ["us", "ie", "in"],
        "captcha": True,
        "robots_block": True
    } }
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({
    filters: {
      max_age: '24h',
      domain_whitelist: ['example.com'],
      domain_like_whitelist: ['%.example.%', 'example%'],
      domain_regex_whitelist: ['.*example..*'],
      category_whitelist: ['Motor Vehicles'],
      url_like_whitelist: ['%/products/%', '%/search%'],
      url_regex_whitelist: ['.*/products/.*'],
      language_whitelist: ['eng'],
      ip_country_whitelist: ['us', 'ie', 'in'],
      captcha: true,
      robots_block: true
    }
  })
};

fetch('https://api.brightdata.com/webarchive/search', 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/webarchive/search",
  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([
    'filters' => [
        'max_age' => '24h',
        'domain_whitelist' => [
                'example.com'
        ],
        'domain_like_whitelist' => [
                '%.example.%',
                'example%'
        ],
        'domain_regex_whitelist' => [
                '.*example..*'
        ],
        'category_whitelist' => [
                'Motor Vehicles'
        ],
        'url_like_whitelist' => [
                '%/products/%',
                '%/search%'
        ],
        'url_regex_whitelist' => [
                '.*/products/.*'
        ],
        'language_whitelist' => [
                'eng'
        ],
        'ip_country_whitelist' => [
                'us',
                'ie',
                'in'
        ],
        'captcha' => true,
        'robots_block' => true
    ]
  ]),
  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/webarchive/search"

	payload := strings.NewReader("{\n  \"filters\": {\n    \"max_age\": \"24h\",\n    \"domain_whitelist\": [\n      \"example.com\"\n    ],\n    \"domain_like_whitelist\": [\n      \"%.example.%\",\n      \"example%\"\n    ],\n    \"domain_regex_whitelist\": [\n      \".*example..*\"\n    ],\n    \"category_whitelist\": [\n      \"Motor Vehicles\"\n    ],\n    \"url_like_whitelist\": [\n      \"%/products/%\",\n      \"%/search%\"\n    ],\n    \"url_regex_whitelist\": [\n      \".*/products/.*\"\n    ],\n    \"language_whitelist\": [\n      \"eng\"\n    ],\n    \"ip_country_whitelist\": [\n      \"us\",\n      \"ie\",\n      \"in\"\n    ],\n    \"captcha\": true,\n    \"robots_block\": true\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/webarchive/search")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"filters\": {\n    \"max_age\": \"24h\",\n    \"domain_whitelist\": [\n      \"example.com\"\n    ],\n    \"domain_like_whitelist\": [\n      \"%.example.%\",\n      \"example%\"\n    ],\n    \"domain_regex_whitelist\": [\n      \".*example..*\"\n    ],\n    \"category_whitelist\": [\n      \"Motor Vehicles\"\n    ],\n    \"url_like_whitelist\": [\n      \"%/products/%\",\n      \"%/search%\"\n    ],\n    \"url_regex_whitelist\": [\n      \".*/products/.*\"\n    ],\n    \"language_whitelist\": [\n      \"eng\"\n    ],\n    \"ip_country_whitelist\": [\n      \"us\",\n      \"ie\",\n      \"in\"\n    ],\n    \"captcha\": true,\n    \"robots_block\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.brightdata.com/webarchive/search")

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  \"filters\": {\n    \"max_age\": \"24h\",\n    \"domain_whitelist\": [\n      \"example.com\"\n    ],\n    \"domain_like_whitelist\": [\n      \"%.example.%\",\n      \"example%\"\n    ],\n    \"domain_regex_whitelist\": [\n      \".*example..*\"\n    ],\n    \"category_whitelist\": [\n      \"Motor Vehicles\"\n    ],\n    \"url_like_whitelist\": [\n      \"%/products/%\",\n      \"%/search%\"\n    ],\n    \"url_regex_whitelist\": [\n      \".*/products/.*\"\n    ],\n    \"language_whitelist\": [\n      \"eng\"\n    ],\n    \"ip_country_whitelist\": [\n      \"us\",\n      \"ie\",\n      \"in\"\n    ],\n    \"captcha\": true,\n    \"robots_block\": true\n  }\n}"

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

{
  "search_id": "ucd_abc123xyz"
}

POST

webarchive

Run a search

curl --request POST \
  --url https://api.brightdata.com/webarchive/search \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "filters": {
    "max_age": "24h",
    "domain_whitelist": [
      "example.com"
    ],
    "domain_like_whitelist": [
      "%.example.%",
      "example%"
    ],
    "domain_regex_whitelist": [
      ".*example..*"
    ],
    "category_whitelist": [
      "Motor Vehicles"
    ],
    "url_like_whitelist": [
      "%/products/%",
      "%/search%"
    ],
    "url_regex_whitelist": [
      ".*/products/.*"
    ],
    "language_whitelist": [
      "eng"
    ],
    "ip_country_whitelist": [
      "us",
      "ie",
      "in"
    ],
    "captcha": true,
    "robots_block": true
  }
}
'

import requests

url = "https://api.brightdata.com/webarchive/search"

payload = { "filters": {
        "max_age": "24h",
        "domain_whitelist": ["example.com"],
        "domain_like_whitelist": ["%.example.%", "example%"],
        "domain_regex_whitelist": [".*example..*"],
        "category_whitelist": ["Motor Vehicles"],
        "url_like_whitelist": ["%/products/%", "%/search%"],
        "url_regex_whitelist": [".*/products/.*"],
        "language_whitelist": ["eng"],
        "ip_country_whitelist": ["us", "ie", "in"],
        "captcha": True,
        "robots_block": True
    } }
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({
    filters: {
      max_age: '24h',
      domain_whitelist: ['example.com'],
      domain_like_whitelist: ['%.example.%', 'example%'],
      domain_regex_whitelist: ['.*example..*'],
      category_whitelist: ['Motor Vehicles'],
      url_like_whitelist: ['%/products/%', '%/search%'],
      url_regex_whitelist: ['.*/products/.*'],
      language_whitelist: ['eng'],
      ip_country_whitelist: ['us', 'ie', 'in'],
      captcha: true,
      robots_block: true
    }
  })
};

fetch('https://api.brightdata.com/webarchive/search', 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/webarchive/search",
  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([
    'filters' => [
        'max_age' => '24h',
        'domain_whitelist' => [
                'example.com'
        ],
        'domain_like_whitelist' => [
                '%.example.%',
                'example%'
        ],
        'domain_regex_whitelist' => [
                '.*example..*'
        ],
        'category_whitelist' => [
                'Motor Vehicles'
        ],
        'url_like_whitelist' => [
                '%/products/%',
                '%/search%'
        ],
        'url_regex_whitelist' => [
                '.*/products/.*'
        ],
        'language_whitelist' => [
                'eng'
        ],
        'ip_country_whitelist' => [
                'us',
                'ie',
                'in'
        ],
        'captcha' => true,
        'robots_block' => true
    ]
  ]),
  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/webarchive/search"

	payload := strings.NewReader("{\n  \"filters\": {\n    \"max_age\": \"24h\",\n    \"domain_whitelist\": [\n      \"example.com\"\n    ],\n    \"domain_like_whitelist\": [\n      \"%.example.%\",\n      \"example%\"\n    ],\n    \"domain_regex_whitelist\": [\n      \".*example..*\"\n    ],\n    \"category_whitelist\": [\n      \"Motor Vehicles\"\n    ],\n    \"url_like_whitelist\": [\n      \"%/products/%\",\n      \"%/search%\"\n    ],\n    \"url_regex_whitelist\": [\n      \".*/products/.*\"\n    ],\n    \"language_whitelist\": [\n      \"eng\"\n    ],\n    \"ip_country_whitelist\": [\n      \"us\",\n      \"ie\",\n      \"in\"\n    ],\n    \"captcha\": true,\n    \"robots_block\": true\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/webarchive/search")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"filters\": {\n    \"max_age\": \"24h\",\n    \"domain_whitelist\": [\n      \"example.com\"\n    ],\n    \"domain_like_whitelist\": [\n      \"%.example.%\",\n      \"example%\"\n    ],\n    \"domain_regex_whitelist\": [\n      \".*example..*\"\n    ],\n    \"category_whitelist\": [\n      \"Motor Vehicles\"\n    ],\n    \"url_like_whitelist\": [\n      \"%/products/%\",\n      \"%/search%\"\n    ],\n    \"url_regex_whitelist\": [\n      \".*/products/.*\"\n    ],\n    \"language_whitelist\": [\n      \"eng\"\n    ],\n    \"ip_country_whitelist\": [\n      \"us\",\n      \"ie\",\n      \"in\"\n    ],\n    \"captcha\": true,\n    \"robots_block\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.brightdata.com/webarchive/search")

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  \"filters\": {\n    \"max_age\": \"24h\",\n    \"domain_whitelist\": [\n      \"example.com\"\n    ],\n    \"domain_like_whitelist\": [\n      \"%.example.%\",\n      \"example%\"\n    ],\n    \"domain_regex_whitelist\": [\n      \".*example..*\"\n    ],\n    \"category_whitelist\": [\n      \"Motor Vehicles\"\n    ],\n    \"url_like_whitelist\": [\n      \"%/products/%\",\n      \"%/search%\"\n    ],\n    \"url_regex_whitelist\": [\n      \".*/products/.*\"\n    ],\n    \"language_whitelist\": [\n      \"eng\"\n    ],\n    \"ip_country_whitelist\": [\n      \"us\",\n      \"ie\",\n      \"in\"\n    ],\n    \"captcha\": true,\n    \"robots_block\": true\n  }\n}"

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

{
  "search_id": "ucd_abc123xyz"
}

POST /webarchive/search searches the Bright Data Archive and returns either the full search result object or a search_id you poll for status.

Every search needs a time range. The filters object is required, and it must carry either max_age, or both min_date and max_date. A request with no filters object returns HTTP 400 with "filters" is required.

How to set the search time range

Use max_age for a window relative to now. Write it as a number followed by a unit:

Unit	Meaning	Example
`h`	Hours	`24h`
`d`	Days	`7d`
`mo`	Months	`3mo`
`y`	Years	`1y`

Bright Data recommends max_age of 24h for a first search, because recent data is delivered fastest.

curl -X POST https://api.brightdata.com/webarchive/search \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "filters": {
      "max_age": "24h",
      "domain_whitelist": ["example.com"]
    }
  }'

Use min_date and max_date for a fixed calendar range. Both dates use YYYY-MM-DD format and both must be sent together.

curl -X POST https://api.brightdata.com/webarchive/search \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "filters": {
      "min_date": "2026-08-01",
      "max_date": "2026-08-08",
      "domain_whitelist": ["example.com"]
    }
  }'

Send one form or the other, never both. max_age combined with min_date and max_date in the same request is a conflict, and the results are undefined.

For date ranges older than 24 hours, use min_date and max_date rather than max_age. See Data range vs delivery time for how the requested range affects delivery speed.

If the search takes longer than 30 seconds, the response returns only a search_id and you should poll the status asynchronously. If the search completes within 30 seconds, the response returns the full search result object (same as GET /webarchive/search/<search_id>).

You can run up to 100 searches per day without triggering a dump. Once you trigger a dump, that search no longer counts against your limit.

LIKE vs Regex Filters

Use LIKE filters (domain_like_*, url_like_*) for simple pattern matching with % (any sequence) and _ (single character).
LIKE patterns are case-insensitive and often faster than regex for simple prefix/suffix matching like %.com or amazon%.
Use regex filters (domain_regex_*, url_regex_*) for complex patterns requiring full regex syntax. LIKE patterns use backslash escaping: \% for literal %, \_ for literal _.

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 b5648e1096c6442f60a6c4bbbe73f8d2234d3d8324554bd6a7ec8f3f251f07df

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

Body

application/json

filters

object

required

Filters that scope the search. The filters object is required, and it must carry a time range: either max_age, or both min_date and max_date.

Show child attributes

Response

Search initiated successfully

Async (Still Running)
Completed within 30s

search_id

string

Returned if search is async

Example:

"ucd_abc123xyz"

Overview

Products

Administrative API

How to set the search time range

Authorizations

Body

Response

​How to set the search time range

Authorizations

Body

Response

How to set the search time range