cURL
curl --request POST \
--url https://api.brightdata.com/datasets/filter \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form 'filter={
"name": "name",
"operator": "=",
"value": "John"
}'import requests
url = "https://api.brightdata.com/datasets/filter"
payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--"
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "multipart/form-data"
}
response = requests.post(url, data=payload, headers=headers)
print(response.text)const form = new FormData();
form.append('filter', '{
"name": "name",
"operator": "=",
"value": "John"
}');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://api.brightdata.com/datasets/filter', 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/filter",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: multipart/form-data"
],
]);
$response = curl_exec($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/filter"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
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.post("https://api.brightdata.com/datasets/filter")
.header("Authorization", "Bearer <token>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/datasets/filter")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"snapshot_id": "<string>"
}{
"validation_errors": [
"\"filter.filters[0].invalid_prop\" 不允许",
"\"records_limit\" 必须为正数"
]
}{
"error": "您当前的余额不足以处理此数据收集请求。请向您的账户充值或调整请求以继续。 ($1 缺失)"
}{
"error": "提供的筛选条件未匹配任何记录"
}{
"error": "每个数据集的最大任务限制 100 已超出"
}Marketplace Dataset API
筛选数据集(JSON 或文件上传)
根据提供的筛选条件创建数据集快照
POST
/
datasets
/
filter
cURL
curl --request POST \
--url https://api.brightdata.com/datasets/filter \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form 'filter={
"name": "name",
"operator": "=",
"value": "John"
}'import requests
url = "https://api.brightdata.com/datasets/filter"
payload = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--"
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "multipart/form-data"
}
response = requests.post(url, data=payload, headers=headers)
print(response.text)const form = new FormData();
form.append('filter', '{
"name": "name",
"operator": "=",
"value": "John"
}');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://api.brightdata.com/datasets/filter', 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/filter",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: multipart/form-data"
],
]);
$response = curl_exec($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/filter"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
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.post("https://api.brightdata.com/datasets/filter")
.header("Authorization", "Bearer <token>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/datasets/filter")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"filter\"\r\n\r\n{\r\n \"name\": \"name\",\r\n \"operator\": \"=\",\r\n \"value\": \"John\"\r\n}\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"snapshot_id": "<string>"
}{
"validation_errors": [
"\"filter.filters[0].invalid_prop\" 不允许",
"\"records_limit\" 必须为正数"
]
}{
"error": "您当前的余额不足以处理此数据收集请求。请向您的账户充值或调整请求以继续。 ($1 缺失)"
}{
"error": "提供的筛选条件未匹配任何记录"
}{
"error": "每个数据集的最大任务限制 100 已超出"
}Bright Data 市场数据集 API 的 Filter 端点可以按存储在 CSV 或 JSON 文件中的成千上万个值对数据集进行筛选。以 multipart 模式上传一个或多个文件,并在筛选中引用每个文件名。
文件引用仅可与
将您的 API Key 粘贴到授权字段。要获取 API Key,请创建账户并了解如何生成 API Key。
基于文件的筛选如何工作?
当您需要按大型值列表筛选时使用文件上传,例如包含或排除 10 万以上的公司 ID:- 以
multipart/form-data模式上传 CSV 或 JSON 文件,并在筛选中引用每个文件名。 - 每个文件最多包含 10,000 行数据,整个请求最大为 200 MiB。
- Filter 任务以异步方式运行,并返回一个
snapshot_id,可在任务完成后下载。
如何格式化 CSV 或 JSON 文件?
- CSV
- JSON
- 第一行必须是与筛选字段名称匹配的表头。
- 后续每行包含单个值。
Example: industries.csv
industries:value
Accounting
Ad Network
Advertising
- 必须是对象数组,每个对象的键与筛选字段名称匹配。
Example industries.json
[
{"industries:value": "Accounting"},
{"industries:value": "Ad Network"},
{"industries:value": "Advertising"}
]
如何在筛选中引用文件?
使用文件上传时,将筛选的value 字段设为文件名:
Example
{
"operator": "and",
"filters": [
{
"name": "industries:value",
"operator": "includes",
"value": "industries.csv"
}
]
}
in、not_in、includes、not_includes、array_includes 和 not_array_includes 运算符配合使用。完整的运算符表和字段类型,请参阅筛选语法参考。
使用多个文件进行筛选
curl \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: multipart/form-data" \
-F "files[]=@/path/to/industries.csv" \
-F "files[]=@/path/to/regions.csv" \
-F "filter={\"operator\":\"and\",\"filters\":[{\"name\":\"industries:value\",\"operator\":\"includes\",\"value\":\"industries.csv\"},{\"name\":\"region\",\"operator\":\"in\",\"value\":\"regions.csv\"}]}" \
"api.brightdata.com/datasets/filter?dataset_id=gd_l1vijqt9jfj7olije"
排查文件上传问题
| 问题 | 可能解决方案 |
|---|---|
| ”File not found” | 确保筛选中引用的文件名与上传文件名完全匹配。 |
| “Invalid file format” | 检查 CSV 表头是否与筛选字段名称匹配,或确保 JSON 是对象数组。 |
| “Field not found” | 验证字段是否存在于数据集中。使用 获取数据集元数据。 |
相关文档
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
要筛选的数据集 ID(在 multipart/form-data 模式下为必填)
示例:
"gd_l1viktl72bvl7bjuj0"
限制包含在快照中的记录数量
示例:
1000
请求体
multipart/form-data
- 单字段筛选器
- 筛选器组
- 无值单字段筛选器
Show child attributes
Show child attributes
示例:
{
"name": "name",
"operator": "=",
"value": "John"
}
响应
创建快照的任务已成功启动
快照 ID
此页面对您有帮助吗?
⌘I