cURL
curl --request GET \
--url https://api.brightdata.com/dca/dataset \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.brightdata.com/dca/dataset"
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/dca/dataset', 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/dca/dataset",
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/dca/dataset"
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))
}HttpResponse<String> response = Unirest.get("https://api.brightdata.com/dca/dataset")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/dca/dataset")
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[
{
"Image": "https://targetwebsite.com/product_id.png",
"Title": "product_name",
"Price": "product_price",
"input": {
"url": "https://targetwebsite.com/product_id/"
}
}
]{
"status": "building",
"message": "Dataset is not ready yet, try again in XXs"
}获取数据
接收批量数据
使用 GET /dca/dataset?id=<collection_id> 获取异步 Scraper Studio 批量采集的结果。采集进行中返回状态对象,采集就绪后返回 JSON 记录数组。
GET
/
dca
/
dataset
cURL
curl --request GET \
--url https://api.brightdata.com/dca/dataset \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.brightdata.com/dca/dataset"
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/dca/dataset', 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/dca/dataset",
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 $response;
}package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api.brightdata.com/dca/dataset"
req, _ := http.NewRequest("GET", url, nil)
req.Header.Add("Authorization", "Bearer <token>")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.get("https://api.brightdata.com/dca/dataset")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/dca/dataset")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'
response = http.request(request)
puts response.read_body[
{
"Image": "https://targetwebsite.com/product_id.png",
"Title": "product_name",
"Price": "product_price",
"input": {
"url": "https://targetwebsite.com/product_id/"
}
}
]{
"status": "building",
"message": "Dataset is not ready yet, try again in XXs"
}使用
当采集就绪后(HTTP 200):
具体的字段集取决于您在构建采集器时定义的输出模式。默认情况下,每个成功的输入对应一行。
GET /dca/dataset?id=<collection_id> 获取异步 Bright Data Scraper Studio 批量采集的结果。当采集仍在运行时,该端点返回一个状态对象。当采集就绪后,它会返回一个 JSON 记录数组。
请将 POST /dca/trigger 返回的
collection_id 用作本端点的 id 查询参数。批量采集结果在采集后 16 天内可供下载。为了避免过期,请在 16 天内下载数据,或配置推送递送方式以将其自动发送到您的存储。
请求
curl --request GET \
--url 'https://api.brightdata.com/dca/dataset?id=YOUR_COLLECTION_ID' \
--header 'Authorization: Bearer YOUR_API_KEY'
response = requests.get(
"https://api.brightdata.com/dca/dataset",
params={"id": collection_id},
headers={"Authorization": f"Bearer {API_TOKEN}"},
)
const response = await fetch(
`https://api.brightdata.com/dca/dataset?id=${collectionId}`,
{ headers: { Authorization: `Bearer ${process.env.BRIGHT_DATA_API_TOKEN}` } }
);
响应
当采集仍在构建中时(HTTP 202):{
"status": "building",
"message": "Dataset is not ready yet, try again in XXs"
}
[
{
"url": "https://example.com/product/1",
"title": "product_name",
"price": 8.45,
"availability": "in stock",
"input": {
"url": "https://example.com/product/1"
}
}
]
获取结果
当采集仍在运行时,该端点返回202 Accepted 以及一个状态对象。当采集就绪后,它返回 200 OK 以及一个 JSON 记录数组。
对于可能耗时数分钟或数小时的长时间采集,请避免频繁轮询。请改用以下方式之一:
- 以较长的时间间隔定期检查采集状态。
- 配置推送递送方式,例如 webhook、Amazon S3、Google Cloud Storage、Azure Blob Storage、SFTP/FTP 或电子邮件。
- 使用控制面板监控运行进度。
错误
| 状态码 | 原因 | 解决方法 |
|---|---|---|
401 Unauthorized | 令牌缺失、格式错误或已撤销 | 从账户设置 → API 令牌重新复制 |
404 Not Found | 采集 ID 不存在、已删除或已过期(16 天) | 如果仍需要数据,请重新触发采集器 |
[](空数组) | 采集已完成但没有产生任何行 | 检查输入 URL 和采集器的输出模式 |
5xx | Bright Data API 临时错误 | 使用指数退避重试,例如 1s、2s、4s |
授权
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
查询参数
Collection ID returned by POST /dca/trigger. Use this value as the id query parameter.
示例:
"j_abc123def456"
响应
Dataset (Ready)
此页面对您有帮助吗?