Gemini

通过提交提示词提取 Gemini 响应，并以结构化 JSON、纯文本或 Markdown 形式接收解析数据。

该 gemini source 允许您向 Google Gemini 提交提示词，并接收经过解析的结构化响应，包括纯文本和 Markdown 答案。

请求示例

以下代码示例展示了如何使用以下方式向 Gemini 提交提示词 Push-Pull.

cURL

curl 'https://data.oxylabs.io/v1/queries' \\
--user 'USERNAME:PASSWORD' \\
-H 'Content-Type: application/json' \\
-d '{
        "source": "gemini",
        "prompt": "best supplements for better sleep",
        "parse": true,
        "geo_location": "United States",
        "callback_url": "https://your-server.com/oxylabs-callback"
    }'

Python

import requests
from pprint import pprint

# 结构化载荷。
payload = {
    'source': 'gemini',
    'prompt': 'best supplements for better sleep',
    'parse': True,
    'geo_location': "United States",
    'callback_url': "https://your-server.com/oxylabs-callback"
}

# 获取响应。
response = requests.request(
    'POST',
    'https://data.oxylabs.io/v1/queries',
    auth=('USERNAME', 'PASSWORD'),
    json=payload,
)

# Print prettified response to stdout.
pprint(response.json())

Node.js

const https = require("https");

const username = "USERNAME";
const password = "PASSWORD";
const body = {
    source: "gemini",
    prompt: "best supplements for better sleep",
    解析：true,
    geo_location: "United States",
    callback_url: "https://your-server.com/oxylabs-callback"
};

const options = {
    hostname: "data.oxylabs.io",
    path: "/v1/queries",
    method: "POST",
    headers: {
        "Content-Type": "application/json",
        Authorization:
            "Basic " + Buffer.from(`${username}:${password}`).toString("base64"),
    },
};

const request = https.request(options, (response) => {
    let data = "";

    response.on("data", (chunk) => {
        data += chunk;
    });

    response.on("end", () => {
        const responseData = JSON.parse(data);
        console.log(JSON.stringify(responseData, null, 2));
    });
});

request.on("error", (error) => {
    console.error("Error:", error);
});

request.write(JSON.stringify(body));
request.end();

PHP

<?php

$params = array(
    'source' => 'gemini',
    'prompt' => 'best supplements for better sleep',
    'parse' => true,
    'geo_location' => "United States",
    'callback_url' => "https://your-server.com/oxylabs-callback"
);

$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, "https://data.oxylabs.io/v1/queries");
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($params));
curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt($ch, CURLOPT_USERPWD, "USERNAME" . ":" . "PASSWORD");

$headers = array();
$headers[] = "Content-Type: application/json";
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);

$result = curl_exec($ch);
echo $result;

if (curl_errno($ch)) {
    echo 'Error:' . curl_error($ch);
}
curl_close($ch);

Go

package main

import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)

func main() {
const Username = "USERNAME"
const Password = "PASSWORD"

payload := map[string]interface{}{
"source":       "gemini",
"prompt":       "改善睡眠的最佳补充剂",
"parse":        true,
"geo_location": "United States",
"callback_url": "https://your-server.com/oxylabs-callback",
}

jsonValue, _ := json.Marshal(payload)

client := &http.Client{}
request, _ := http.NewRequest("POST",
"https://data.oxylabs.io/v1/queries",
bytes.NewBuffer(jsonValue),
)

request.SetBasicAuth(Username, Password)
response, _ := client.Do(request)

responseText, _ := ioutil.ReadAll(response.Body)
fmt.Println(string(responseText))
}

C#

using System;
using System.Collections.Generic;
using System.Net.Http;
using System.Net.Http.Json;
using System.Threading.Tasks;

namespace OxyApi
{
    class Program
    {
        static async Task Main()
        {
            const string Username = "USERNAME";
            const string Password = "PASSWORD";

            var parameters = new
            {
                source = "gemini",
                prompt = "best supplements for better sleep",
                parse = true,
                geo_location = "United States",
                callback_url = "https://your-server.com/oxylabs-callback"
            };

            var client = new HttpClient();

            Uri baseUri = new Uri("https://data.oxylabs.io");
            client.BaseAddress = baseUri;

            var requestMessage = new HttpRequestMessage(HttpMethod.Post, "/v1/queries");
            requestMessage.Content = JsonContent.Create(parameters);

            var authenticationString = $"{Username}:{Password}";
            var base64EncodedAuthenticationString = Convert.ToBase64String(System.Text.ASCIIEncoding.UTF8.GetBytes(authenticationString));
            requestMessage.Headers.Add("Authorization", "Basic " + base64EncodedAuthenticationString);

            var response = await client.SendAsync(requestMessage);
            var contents = await response.Content.ReadAsStringAsync();

            Console.WriteLine(contents);
        }
    }
}

Java

package org.example;

import okhttp3.*;
import org.json.JSONObject;

public class Main implements Runnable {
    private static final String AUTHORIZATION_HEADER = "Authorization";
    public static final String USERNAME = "USERNAME";
    public static final String PASSWORD = "PASSWORD";

    public void run() {
        JSONObject jsonObject = new JSONObject();
        jsonObject.put("source", "gemini");
        jsonObject.put("prompt", "best supplements for better sleep");
        jsonObject.put("parse", true);
        jsonObject.put("geo_location", "United States");
        jsonObject.put("callback_url", "https://your-server.com/oxylabs-callback");

        Authenticator authenticator = (route, response) => {
            String credential = Credentials.basic(USERNAME, PASSWORD);
            return response
                    .request()
                    .newBuilder()
                    .header(AUTHORIZATION_HEADER, credential)
                    .build();
        };

        var client = new OkHttpClient.Builder()
                .authenticator(authenticator)
                .build();

        var mediaType = MediaType.parse("application/json; charset=utf-8");
        var body = RequestBody.create(jsonObject.toString(), mediaType);
        var request = new Request.Builder()
                .url("https://data.oxylabs.io/v1/queries")
                .post(body)
                .build();

        try (var response = client.newCall(request).execute()) {
            if (response.body() != null) {
                try (var responseBody = response.body()) {
                    System.out.println(responseBody.string());
                }
            }
        } catch (Exception exception) {
            System.out.println("Error: " + exception.getMessage());
        }

        System.exit(0);
    }

    public static void main(String[] args) {
        new Thread(new Main()).start();
    }
}

JSON

{
    "source": "gemini",
    "prompt": "best supplements for better sleep",
    "parse": true,
    "geo_location": "United States",
    "callback_url": "https://your-server.com/oxylabs-callback"
}

注意： 所有 LLM 来源默认启用 JavaScript 渲染。您无需在请求负载中包含渲染参数。

使用以下方式提交作业 Push-Pull 集成（包括 批量查询) 方法会立即返回作业 ID，而不是结果。一旦作业状态为 done，即可获取解析后的响应。参见 集成方式 LLMs 和 AI 页面上的完整提交与检索流程。

请求参数

用于抓取 Gemini 的基本设置和自定义选项。

参数	描述	默认值
source	设置爬虫目标。使用 gemini.	–
prompt	要提交给 Gemini 的提示词或问题。必须少于 8000 个字符。	–
callback_url	推荐。 作业完成后我们发送通知的 URL。 更多信息.	–
解析	设置为 true 用于结构化 JSON 数据。	false
geo_location	指定请求路由所在的国家/地区。 更多信息.	–
browser_instructions	渲染 JavaScript 时的可选自定义浏览器指令。 更多信息.	–

- 必填参数

结构化数据

通过 Push-Pull 结果端点获取任务后，网页爬虫API能够提取包含 Gemini 输出的 JSON 对象，从而提供有关结果页面各元素的结构化数据。

gemini 结构化输出

{
  "results": [
    {
      "job_id": "7470031540181837825",
      "status_code": 200,
      "url": "https://gemini.google.com/app/ca6b069d5af5c809",
      "content": {
        "prompt": "best supplements for better sleep",
        "response_text": "如果您辗转反侧，您绝对不是唯一一个。补充剂货架上摆满了声称能帮助您入睡的产品，但根据它们实际影响身体的方式，这些产品通常可分为几种不同类别。这里……",
        "markdown_text": "如果您辗转反侧，您绝对不是唯一一个。补充剂货架上摆满了声称能帮助您入睡的产品，但根据它们实际影响身体的方式，这些产品通常可分为几种不同类别。\n\n 这里……",
        "citations": [
          {
            "title": "Hartford HealthCare",
            "url": "https://hartfordhealthcare.org/about-us/news-press/news-detail?articleId=66180",
            "text": "这 3 种补充剂真的能改善您的睡眠吗？| Hartford HealthCare | CT",
            "description": "- 缬草根。这种草本助眠选择可能通过作用于大脑中的 GABA 受体发挥作用，与镁类似。\"但它并非没有副作用，\"……说。"
          },
          {
            "title": "BBC Good Food",
            "url": "https://www.bbcgoodfood.com/review/best-sleep-supplements#:~:text=It's%20easy%20to%20get%20enough,a%20role%20in%20sleep%20regulation.",
            "text": "2026 年最佳助眠补充剂——经过试用和测试 - BBC Good Food",
            "description": "通过饮食很容易摄入足量，但如果您想补充，NRV 约为 300mg，并且应选择已被证明能够……的甘氨酸镁。"
          },
          {
            "title": "PMC - NIH",
            "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC11082867/#:~:text=Melatonin%20is%20a%20hormone%20produced,promotes%20relaxation%20and%20reduced%20alertness.",
            "text": "关于改善睡眠质量的常见膳食补充剂的当前证据 - PMC - NIH",
            "description": "褪黑素是由大脑松果体产生的一种激素，在调节睡眠-觉醒周期中发挥关键作用。松果体开始……"
          },
          ...
        ],
        "parse_status_code": 12000
      }
    }
  ]
}

响应的组成可能会因查询是否来自 desktop 或 mobile 设备而有所不同。

输出数据字典

所有 LLM 目标返回相同的顶层 作业 和 results[] 封装。参见 LLMs 和 AI 以查看完整的元数据参考。

下表展示了 Gemini 专用的 results[].content 字段：

字段名称	描述	类型
prompt	已提交的提示词。	字符串
raw	流式响应中的原始数据。	数组
response_text	Gemini 返回的纯文本响应。	字符串
markdown_text	Markdown 格式的完整响应。	字符串
citations	响应中引用的来源。每个对象包含 title, url, text，以及 description.	数组
parse_status_code	12000 – 成功。否则，解析器未能提取部分或全部结构化字段。	整数
model	用于生成响应的 AI 模型。	字符串

– 条件返回，仅在内容出现在 LLM 响应中时返回。