curl --request POST \
--url https://api.brightdata.com/datasets/v3/trigger \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
[
{
"url": "https://www.airbnb.com/rooms/50122531"
},
{
"url": "https://www.airbnb.com/rooms/50127677"
}
]
'import requests
url = "https://api.brightdata.com/datasets/v3/trigger"
payload = [{ "url": "https://www.airbnb.com/rooms/50122531" }, { "url": "https://www.airbnb.com/rooms/50127677" }]
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([
{url: 'https://www.airbnb.com/rooms/50122531'},
{url: 'https://www.airbnb.com/rooms/50127677'}
])
};
fetch('https://api.brightdata.com/datasets/v3/trigger', 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/trigger",
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([
[
'url' => 'https://www.airbnb.com/rooms/50122531'
],
[
'url' => 'https://www.airbnb.com/rooms/50127677'
]
]),
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/v3/trigger"
payload := strings.NewReader("[\n {\n \"url\": \"https://www.airbnb.com/rooms/50122531\"\n },\n {\n \"url\": \"https://www.airbnb.com/rooms/50127677\"\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/datasets/v3/trigger")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("[\n {\n \"url\": \"https://www.airbnb.com/rooms/50122531\"\n },\n {\n \"url\": \"https://www.airbnb.com/rooms/50127677\"\n }\n]")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/datasets/v3/trigger")
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 {\n \"url\": \"https://www.airbnb.com/rooms/50122531\"\n },\n {\n \"url\": \"https://www.airbnb.com/rooms/50127677\"\n }\n]"
response = http.request(request)
puts response.read_body{
"snapshot_id": "s_m4x7enmven8djfqak"
}{
"error": "输入格式无效"
}{
"error": "未授权"
}异步请求
Bright Data Scrapers 使您能够触发数据收集,以实现自动化网页数据提取。
curl --request POST \
--url https://api.brightdata.com/datasets/v3/trigger \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
[
{
"url": "https://www.airbnb.com/rooms/50122531"
},
{
"url": "https://www.airbnb.com/rooms/50127677"
}
]
'import requests
url = "https://api.brightdata.com/datasets/v3/trigger"
payload = [{ "url": "https://www.airbnb.com/rooms/50122531" }, { "url": "https://www.airbnb.com/rooms/50127677" }]
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([
{url: 'https://www.airbnb.com/rooms/50122531'},
{url: 'https://www.airbnb.com/rooms/50127677'}
])
};
fetch('https://api.brightdata.com/datasets/v3/trigger', 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/trigger",
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([
[
'url' => 'https://www.airbnb.com/rooms/50122531'
],
[
'url' => 'https://www.airbnb.com/rooms/50127677'
]
]),
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/v3/trigger"
payload := strings.NewReader("[\n {\n \"url\": \"https://www.airbnb.com/rooms/50122531\"\n },\n {\n \"url\": \"https://www.airbnb.com/rooms/50127677\"\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/datasets/v3/trigger")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("[\n {\n \"url\": \"https://www.airbnb.com/rooms/50122531\"\n },\n {\n \"url\": \"https://www.airbnb.com/rooms/50127677\"\n }\n]")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.brightdata.com/datasets/v3/trigger")
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 {\n \"url\": \"https://www.airbnb.com/rooms/50122531\"\n },\n {\n \"url\": \"https://www.airbnb.com/rooms/50127677\"\n }\n]"
response = http.request(request)
puts response.read_body{
"snapshot_id": "s_m4x7enmven8djfqak"
}{
"error": "输入格式无效"
}{
"error": "未授权"
}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
"custom_output_fields" 参数用于筛选响应数据,仅包含指定字段。你可以用管道符 (|) 列出所需输出列。
例如,如果你只希望响应包含 URL 和最后更新时间,可以将参数设置为 "url|about.updated_on"。这允许你自定义数据输出,仅包含与你需求相关的字段。
"url|about.updated_on"
设置为 "discover_new" 以触发包含发现阶段的收集。
启用发现阶段,用于通过搜索、分类或关键词等方式查找新实体或产品。当收集数据时,如果特定目标未知,请使用此选项。它会根据提供的输入发现新信息,而不是使用预定义数据点。
discover_new 指定收集过程中发现新数据的方法,可用选项如下:
keyword:通过关键词发现新实体或产品。例如 "smartphones" - 将触发收集以发现新的智能手机产品或实体。best_sellers_url:使用列出畅销商品的 URL 发现新产品。例如 "https://example.com/best-sellers" - 用于发现网站上的畅销产品。category_url:使用列出类别的 URL 发现该类别下的新实体。例如 "https://example.com/electronics" - 用于发现电子类别下的新产品。location:基于位置发现与该位置相关的实体。例如 "New York" - 将触发收集以发现指定位置相关的数据。
在结果中包含错误报告。将 "include_errors" 设置为 true,可以收到数据收集过程中发生的任何错误的详细报告。
true
限制每个输入的结果数量
x >= 1限制总结果数量
x >= 1指定数据收集任务完成后是否发送通知。设置为 true 时,将向指定的 webhook 发送通知,告知收集状态或完成情况。
true
指定用于数据收集过程的 Webhook URL。
"https://example.com/webhook"
指定要交付的数据格式
json, ndjson, jsonl, csv "json"
Webhook 交付使用的授权头
默认情况下,数据将以压缩形式发送。传入 true 可发送未压缩的数据
true
请求体
你可以使用 JSON 或 CSV 格式提供输入数据。输入指定抓取器所需的 URL 或其他参数。
属性因数据集要求而异。最常见的是包含 'url' 字段。
示例: [{"url":"https://www.airbnb.com/rooms/50122531"},{"url":"https://www.airbnb.com/rooms/50127677"}]
[
{
"url": "https://www.airbnb.com/rooms/50122531"
},
{
"url": "https://www.airbnb.com/rooms/50127677"
}
]
响应
收集任务成功启动
Snapshot ID 是特定数据快照的唯一标识符,用于通过 API 触发的数据收集任务获取结果。更多信息请参阅 Snapshot ID。
"s_m4x7enmven8djfqak"
此页面对您有帮助吗?