读取数据集记录
curl --request GET \
--url https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/recordsimport requests
url = "https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records"
response = requests.get(url)
print(response.text)const options = {method: 'GET'};
fetch('https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));const options = {method: 'GET'};
fetch('https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records"
req, _ := http.NewRequest("GET", url, nil)
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-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records")
.asString();<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}require 'uri'
require 'net/http'
url = URI("https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
response = http.request(request)
puts response.read_bodyusing RestSharp;
var options = new RestClientOptions("https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records");
var client = new RestClient(options);
var request = new RestRequest("");
var response = await client.GetAsync(request);
Console.WriteLine("{0}", response.Content);
val client = OkHttpClient()
val request = Request.Builder()
.url("https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records")
.get()
.build()
val response = client.newCall(request).execute()false{
"run_id": "<string>",
"dataset_id": "<string>",
"records": [
{}
],
"partial": true,
"pagination": {
"offset": 123,
"limit": 123,
"count": 123,
"total": 123,
"has_more": true
}
}数据集
读取数据集记录
分页读取一个数据集里的记录,支持 JSON、JSONL、CSV 与列裁剪。
GET
/
v1
/
datasets
/
{dataset_id}
/
records
读取数据集记录
curl --request GET \
--url https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/recordsimport requests
url = "https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records"
response = requests.get(url)
print(response.text)const options = {method: 'GET'};
fetch('https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));const options = {method: 'GET'};
fetch('https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));package main
import (
"fmt"
"net/http"
"io"
)
func main() {
url := "https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records"
req, _ := http.NewRequest("GET", url, nil)
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-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records")
.asString();<?php
$curl = curl_init();
curl_setopt_array($curl, [
CURLOPT_URL => "https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}require 'uri'
require 'net/http'
url = URI("https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Get.new(url)
response = http.request(request)
puts response.read_bodyusing RestSharp;
var options = new RestClientOptions("https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records");
var client = new RestClient(options);
var request = new RestRequest("");
var response = await client.GetAsync(request);
Console.WriteLine("{0}", response.Content);
val client = OkHttpClient()
val request = Request.Builder()
.url("https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records")
.get()
.build()
val response = client.newCall(request).execute()false{
"run_id": "<string>",
"dataset_id": "<string>",
"records": [
{}
],
"partial": true,
"pagination": {
"offset": 123,
"limit": 123,
"count": 123,
"total": 123,
"has_more": true
}
}端点
GET https://api-datahub.bazhuayu.com/v1/datasets/{dataset_id}/records
Authorization: Bearer <API Key>)。
分页读取数据集记录,参数与读取运行结果相同;归属门与数据集详情相同,不可见即 404。
请求
路径参数
string
必填
数据集标识。
查询参数
integer
默认值:"0"
分页起点。范围 ≥ 0。
integer
默认值:"100"
每页条数,最大 10000。范围 1 到 10000。
string
默认值:"json"
输出格式。
json 带信封与分页;jsonl 每行一条;csv 表格。取值:json / jsonl / csv。string
逗号分隔的字段名,只返回这些列。
示例请求
curl \
-H "Authorization: Bearer $BAZHUAYU_API_KEY" \
"https://api-datahub.bazhuayu.com/v1/datasets/ds_0bd5345d13d0/records?offset=0&limit=100"
响应
200 成功
{
"data": {
"run_id": null,
"dataset_id": "ds_0bd5345d13d0",
"records": [
{
"review_id": "103c9e-0000"
},
{
"review_id": "103c9e-0001"
}
],
"partial": false,
"pagination": {
"offset": 0,
"limit": 2,
"count": 2,
"total": 20,
"has_more": true
}
}
}
data 字段中,其内容如下。
string
数据集来自运行时为该运行标识,否则为
null。string
必填
数据集标识。
object[]
必填
记录数组。
boolean
来源运行是否部分成功或被取消。
错误
| HTTP | code | category | 说明 |
|---|---|---|---|
| 401 | unauthorized | forbidden | 缺少或无效的 API Key。 |
| 404 | dataset-not-found | not_found | 数据集不存在、不属于当前账号,或是平台公共样例集(不可标记)。 |
{"error": {code, category, message, retryable}},见错误。
客户端库
for record in client.iterate_dataset_records("ds_0bd5345d13d0"):
print(record)
for await (const record of client.iterateDatasetRecords("ds_0bd5345d13d0")) {
console.log(record);
}
