过滤数据集 - Bright Data Docs

cURL

curl --request POST \
  --url https://api.brightdata.com/datasets/filter \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "dataset_id": "<string>",
  "filter": {
    "name": "name",
    "operator": "=",
    "value": "John"
  },
  "records_limit": 123
}
'

import requests

url = "https://api.brightdata.com/datasets/filter"

payload = {
    "dataset_id": "<string>",
    "filter": {
        "name": "name",
        "operator": "=",
        "value": "John"
    },
    "records_limit": 123
}
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({
    dataset_id: '<string>',
    filter: {name: 'name', operator: '=', value: 'John'},
    records_limit: 123
  })
};

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 => json_encode([
    'dataset_id' => '<string>',
    'filter' => [
        'name' => 'name',
        'operator' => '=',
        'value' => 'John'
    ],
    'records_limit' => 123
  ]),
  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/filter"

	payload := strings.NewReader("{\n  \"dataset_id\": \"<string>\",\n  \"filter\": {\n    \"name\": \"name\",\n    \"operator\": \"=\",\n    \"value\": \"John\"\n  },\n  \"records_limit\": 123\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/filter")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"dataset_id\": \"<string>\",\n  \"filter\": {\n    \"name\": \"name\",\n    \"operator\": \"=\",\n    \"value\": \"John\"\n  },\n  \"records_limit\": 123\n}")
  .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["Content-Type"] = 'application/json'
request.body = "{\n  \"dataset_id\": \"<string>\",\n  \"filter\": {\n    \"name\": \"name\",\n    \"operator\": \"=\",\n    \"value\": \"John\"\n  },\n  \"records_limit\": 123\n}"

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

{
  "snapshot_id": "<string>"
}

{
  "validation_errors": [
    "\"filter.filters[0].invalid_prop\" is not allowed",
    "\"records_limit\" must be a positive number"
  ]
}

{
  "error": "Your current balance is insufficient to process this data collection request. Please add funds to your account or adjust your request to continue. ($1 is missing)"
}

{
  "error": "Provided filter did not match any records"
}

{
  "error": "Maximum limit of 100 jobs per dataset has been exceeded"
}

POST

datasets

filter

cURL

curl --request POST \
  --url https://api.brightdata.com/datasets/filter \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "dataset_id": "<string>",
  "filter": {
    "name": "name",
    "operator": "=",
    "value": "John"
  },
  "records_limit": 123
}
'

import requests

url = "https://api.brightdata.com/datasets/filter"

payload = {
    "dataset_id": "<string>",
    "filter": {
        "name": "name",
        "operator": "=",
        "value": "John"
    },
    "records_limit": 123
}
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({
    dataset_id: '<string>',
    filter: {name: 'name', operator: '=', value: 'John'},
    records_limit: 123
  })
};

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 => json_encode([
    'dataset_id' => '<string>',
    'filter' => [
        'name' => 'name',
        'operator' => '=',
        'value' => 'John'
    ],
    'records_limit' => 123
  ]),
  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/filter"

	payload := strings.NewReader("{\n  \"dataset_id\": \"<string>\",\n  \"filter\": {\n    \"name\": \"name\",\n    \"operator\": \"=\",\n    \"value\": \"John\"\n  },\n  \"records_limit\": 123\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/filter")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"dataset_id\": \"<string>\",\n  \"filter\": {\n    \"name\": \"name\",\n    \"operator\": \"=\",\n    \"value\": \"John\"\n  },\n  \"records_limit\": 123\n}")
  .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["Content-Type"] = 'application/json'
request.body = "{\n  \"dataset_id\": \"<string>\",\n  \"filter\": {\n    \"name\": \"name\",\n    \"operator\": \"=\",\n    \"value\": \"John\"\n  },\n  \"records_limit\": 123\n}"

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

{
  "snapshot_id": "<string>"
}

{
  "validation_errors": [
    "\"filter.filters[0].invalid_prop\" is not allowed",
    "\"records_limit\" must be a positive number"
  ]
}

{
  "error": "Your current balance is insufficient to process this data collection request. Please add funds to your account or adjust your request to continue. ($1 is missing)"
}

{
  "error": "Provided filter did not match any records"
}

{
  "error": "Maximum limit of 100 jobs per dataset has been exceeded"
}

将您的 API 令牌粘贴到授权字段中。要获取令牌，创建一个账户，并了解如何生成令牌。

一般描述

调用此端点将启动异步作业，以过滤数据集并在您的账户中创建包含过滤数据的快照。
该作业的最大完成时间为 5 分钟。如果在此时间范围内未完成，作业将被取消。
创建数据集快照的费用取决于快照大小和记录单价。
过滤组的最大嵌套深度为 3。

过滤语法

运算符

下表显示了可用于字段过滤的运算符。

操作符	字段类型	描述
=	任意	等于
!=	任意	不等于
<	数字, 日期	小于
<=	数字, 日期	小于或等于
>	数字, 日期	大于
>=	数字, 日期	大于或等于
`in`	任意	测试字段值是否等于筛选值中提供的任意值
`not_in`	任意	测试字段值是否不等于筛选值中提供的所有值
`includes`	数组, 文本	测试字段值是否包含筛选值。如果筛选值是一个单一字符串，则匹配字段值包含该字符串的记录。如果筛选值是一个字符串数组，则匹配字段值包含数组中的至少一个字符串的记录。
`not_includes`	数组, 文本	测试字段值是否不包含筛选值。如果筛选值是一个单一字符串，则匹配字段值不包含该字符串的记录。如果筛选值是一个字符串数组，则匹配字段值不包含数组中的任何字符串的记录。
`array_includes`	数组	测试筛选值是否在字段值中（精确匹配）
`not_array_includes`	数组	测试筛选值是否不在字段值中（精确匹配）
`is_null`	任意	测试字段值是否等于 NULL。操作符不接受任何值。
`is_not_null`	任意	测试字段值是否不等于 NULL。操作符不接受任何值。

组合多个筛选器

可以使用两个逻辑运算符：‘and’（与），‘or’（或）将多个字段筛选器组合成筛选器组。
API 支持最多 3 层嵌套的筛选器。
筛选器组示例：

{
    // operator can be one of ["and", "or"]
    "operator": "and",
    // an array of field filters
    "filters": [
        {
            "name": "reviews_count",
            "opeartor": ">",
            "value": "200"
        },
        {
            "name": "rating",
            "operator": ">",
            "value": "4.5"
        }
    ]
}

授权

Authorization

string

header

必填

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

请求体

application/json

dataset_id

string

必填

ID of the dataset to filter

filter

Single field filter · object

必填

Single field filter
Filters group
Single field filter w/out value

Show child attributes

示例:

{
  "name": "name",
  "operator": "=",
  "value": "John"
}

records_limit

integer

响应

Job of creating the snapshot successfully started

snapshot_id

string

ID of the snapshot

​一般描述

​过滤语法

​运算符

​组合多个筛选器

授权

请求体

响应

一般描述

过滤语法

运算符

组合多个筛选器