curl --request GET \
--url https://api.brightdata.com/datasets/v3/scrapers \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.brightdata.com/datasets/v3/scrapers"
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/scrapers', 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/scrapers",
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/scrapers"
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/datasets/v3/scrapers")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/datasets/v3/scrapers")
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[
{
"id": "gd_mk57m0301khq4jmsul",
"name": "npmjs",
"description": null,
"domain": "npmjs.com",
"scraper_type": [
"collect_by_url"
],
"scrapers": {
"collect_by_url": {
"input_schema": [
{
"name": "package_name",
"type": "text",
"required": true
}
],
"output_fields": [
{
"name": "url",
"type": "url"
},
{
"name": "package_name",
"type": "text",
"description": "NPMjs package name"
},
{
"name": "version",
"type": "text",
"description": "NPMjs version number"
},
{
"name": "readme_content",
"type": "text",
"description": "NPMjs README.md content"
}
],
"sample_input": [
{
"package_name": "@brightdata/sdk"
}
],
"sample_output": {},
"link": "https://brightdata.com/cp/scrapers/gd_mk57m0301khq4jmsul/pdp/configuration"
}
}
}
]获取所有采集器
列出 Bright Data 账户中的每个采集器。GET /datasets/v3/scrapers 返回每个采集器的数据集 ID、域名、输入 schema 和输出字段。
curl --request GET \
--url https://api.brightdata.com/datasets/v3/scrapers \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.brightdata.com/datasets/v3/scrapers"
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/scrapers', 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/scrapers",
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/scrapers"
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/datasets/v3/scrapers")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/datasets/v3/scrapers")
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[
{
"id": "gd_mk57m0301khq4jmsul",
"name": "npmjs",
"description": null,
"domain": "npmjs.com",
"scraper_type": [
"collect_by_url"
],
"scrapers": {
"collect_by_url": {
"input_schema": [
{
"name": "package_name",
"type": "text",
"required": true
}
],
"output_fields": [
{
"name": "url",
"type": "url"
},
{
"name": "package_name",
"type": "text",
"description": "NPMjs package name"
},
{
"name": "version",
"type": "text",
"description": "NPMjs version number"
},
{
"name": "readme_content",
"type": "text",
"description": "NPMjs README.md content"
}
],
"sample_input": [
{
"package_name": "@brightdata/sdk"
}
],
"sample_output": {},
"link": "https://brightdata.com/cp/scrapers/gd_mk57m0301khq4jmsul/pdp/configuration"
}
}
}
]授权
在 Authorization 头中使用您的 Bright Data API Key 作为 Bearer token。
认证方法:
- 从 Bright Data 账户设置获取您的 API Key: https://brightdata.com/cp/setting/users
- 在请求的 Authorization 头中包含 API Key
- 格式:
Authorization: Bearer YOUR_API_KEY
示例:
Authorization: Bearer b5648e1096c6442f60a6c4bbbe73f8d2234d3d8324554bd6a7ec8f3f251f07df
了解如何获取 Bright Data API Key: https://docs.brightdata.com/cn/api-reference/authentication#如何生成新的-api-key?
查询参数
仅返回该数据集 ID 对应的采集器。省略时返回账户中的全部采集器。
"gd_l7q7dkf244hwjntr0"
仅返回 domain 与该值匹配的采集器。省略时返回账户中的全部采集器。
"amazon.com"
响应
OK
采集器的数据集 ID。在触发、抓取和快照端点中用作 dataset_id 查询参数。
"gd_l7q7dkf244hwjntr0"
采集器在 Bright Data 控制面板中显示的名称。
"Amazon products"
采集器所采集的目标站点。可按该字段将采集器归入同一站点系列。
"amazon.com"
该采集器支持的采集方式。collect_by_url 直接根据 URL 或其他标识符采集单条记录。每种 discover_by_* 方式会先执行发现阶段,再采集发现到的记录。要运行发现方式,请在 POST /datasets/v3/trigger 中传入 type=discover_new,并将去掉 discover_by_ 前缀的方式名作为 discover_by 传入,例如 discover_by_keyword 对应 discover_by=keyword。该数组的值与 scrapers 对象的键完全一致。
["collect_by_url", "discover_by_keyword"]
按采集方式名称索引的详细信息。其键与 scraper_type 数组完全一致。
Show child attributes
Show child attributes
采集器所返回数据的概述。采集器没有已发布的描述时返回 null 或省略该字段。
市场分类。返回值为 ecomm、social、business、travel、real_estate、ad_verification、classifieds、financial、geospatial、AI Search 和 Data for AI。未分类的采集器会省略该字段。
"ecomm"
对应的 Bright Data 市场数据集的记录数。仅在采集器有对应数据集时返回。
300000000
对应市场数据集的精选子集。采集器未发布子集时返回 null 或省略该字段。
Show child attributes
Show child attributes
此页面对您有帮助吗?