> For the complete documentation index, see [llms.txt](https://developers.oxylabs.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developers.oxylabs.io/api-targets/pt-br/llms-e-ia/chatgpt.md). # ChatGPT O `ChatGPT` A fonte permite enviar um prompt para o ChatGPT e receber uma resposta totalmente parseada e estruturada, incluindo a resposta em texto simples e Markdown, citações de fontes, consultas de pesquisa usadas pelo modelo e produtos e anúncios de compras. ## Exemplos de solicitação Os exemplos de código a seguir demonstram como enviar um prompt e recuperar uma resposta do ChatGPT com resultados parseados. {% tabs %} {% tab title="cURL" %} ```bash curl 'https://realtime.oxylabs.io/v1/queries' \ --user 'USERNAME:PASSWORD' \ -H 'Content-Type: application/json' \ -d '{ "source": "chatgpt", "prompt": "best supplements for better sleep", "parse": true, "geo_location": "United States" }' ``` {% endtab %} {% tab title="Python" %} ```python import requests from pprint import pprint # Structure payload. payload = { 'source': 'chatgpt', 'prompt': 'best supplements for better sleep', 'parse': True, 'geo_location': "United States" } # Get response. response = requests.request( 'POST', 'https://realtime.oxylabs.io/v1/queries', auth=('USERNAME', 'PASSWORD'), json=payload, ) # Print prettified response to stdout. pprint(response.json()) ``` {% endtab %} {% tab title="Node.js" %} ```javascript const https = require("https"); const username = "USERNAME"; const password = "PASSWORD"; const body = { source: "chatgpt", prompt: "best supplements for better sleep", parse: true, geo_location: "United States" }; const options = { hostname: "realtime.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(); ``` {% endtab %} {% tab title="HTTP" %} ```http https://realtime.oxylabs.io/v1/queries?source=chatgpt&prompt=best%20supplements%20for%20better%20sleep&parse=true&geo_location=United%20States&access_token=12345abcde ``` {% endtab %} {% tab title="PHP" %} ```php 'chatgpt', 'prompt' => 'best supplements for better sleep', 'parse' => true, 'geo_location' => "United States" ); $ch = curl_init(); curl_setopt($ch, CURLOPT_URL, "https://realtime.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); ``` {% endtab %} {% tab title="Golang" %} ```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": "chatgpt", "prompt": "best supplements for better sleep", "parse": true, "geo_location": "United States" } jsonValue, _ := json.Marshal(payload) client := &http.Client{} request, _ := http.NewRequest("POST", "https://realtime.oxylabs.io/v1/queries", bytes.NewBuffer(jsonValue), ) request.SetBasicAuth(Username, Password) response, _ := client.Do(request) responseText, _ := ioutil.ReadAll(response.Body) fmt.Println(string(responseText)) } ``` {% endtab %} {% tab title="C#" %} ```csharp 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 = "chatgpt", prompt = "best supplements for better sleep", parse = true, geo_location = "United States" }; var client = new HttpClient(); Uri baseUri = new Uri("https://realtime.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); } } } ``` {% endtab %} {% tab title="Java" %} ```java package org.example; import okhttp3.*; import org.json.JSONArray; import org.json.JSONObject; import java.util.concurrent.TimeUnit; 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", "chatgpt"); jsonObject.put("prompt", "best supplements for better sleep"); jsonObject.put("parse", true); jsonObject.put("geo_location", "United States"); 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) .readTimeout(180, TimeUnit.SECONDS) .build(); var mediaType = MediaType.parse("application/json; charset=utf-8"); var body = RequestBody.create(jsonObject.toString(), mediaType); var request = new Request.Builder() .url("https://realtime.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(); } } ``` {% endtab %} {% tab title="JSON" %} ```json { "source": "chatgpt", "prompt": "best supplements for better sleep", "parse": true, "geo_location": "United States" } ``` {% endtab %} {% endtabs %} {% hint style="info" %} **Observação:** A renderização de JavaScript está habilitada por padrão para todas as fontes de LLM. Você não precisa incluir parâmetros de renderização no payload da sua requisição. {% endhint %} Usamos integração síncrona [**Realtime**](/products/pt-br/web-scraper-api/integration-methods/realtime.md) método de integração em nossos exemplos. Se você quiser usar [**Proxy Endpoint**](/products/pt-br/web-scraper-api/integration-methods/proxy-endpoint.md) ou assíncrona [**Push-Pull**](/products/pt-br/web-scraper-api/integration-methods/push-pull.md) integração (incluindo [consultas em lote](/products/pt-br/web-scraper-api/integration-methods/push-pull.md#batch-query)), consulte a [**seção de métodos de integração**](/products/pt-br/web-scraper-api/integration-methods.md) seção. ### Parâmetros da requisição Opções básicas de configuração e personalização para fazer scraping do ChatGPT.
ParâmetroDescriçãoValor padrão
sourceDefine o alvo do scraper. Use ChatGPT.–
promptO prompt ou pergunta a enviar ao ChatGPT. Deve ter menos de 4000 caracteres.–
searchDefina como true para busca na web.false
parseDefina como true para resultados JSON estruturados.false
geo_locationEspecifique um país de origem para rotear a requisição. Mais informações.–
callback_urlURL para seu endpoint de callback. Mais informações–
\- parâmetro obrigatório ## Dados estruturados Web Scraper API pode retornar um objeto HTML ou JSON que contém a saída do ChatGPT, com dados estruturados em vários elementos da página de resultados.
ChatGPT saída estruturada ```json { "results": [ { "job_id": "7470033199733683201", "status_code": 200, "url": "https://chatgpt.com/?model=auto", "content": { "prompt": "best supplements for better sleep", "llm_model": "gpt-5-5", "response_text": "If you're looking for supplements with the best evidence for improving sleep, I'd rank them roughly like this: 1. Magnesium glycinate Best all-around starting point for many people ...", "markdown_text": "If you're looking for supplements with the best evidence for improving sleep, I'd rank them roughly like this:\n\n### 1. Magnesium glycinate\n\n**Best all-around starting point for many people**\n\n* ...", "markdown_json": [ { "type": "paragraph", "children": [ { "type": "text", "raw": "If you're looking for supplements with the best evidence for improving sleep, I'd rank them roughly like this:" } ] }, { "type": "blank_line" }, ... ], "citations": [ { "title": "Best Sleep Supplements: Evidence-Based Gui | Holistic Health", "url": "https://holistic.health/journal/best-sleep-supplements-beyond-melatonin?utm_source=chatgpt.com", "text": "Holistic Health", "description": "May 26, 2026" }, { "title": "Natural Sleep Aids: Which Are the Most Effective?", "url": "https://www.sleepfoundation.org/sleep-aids/natural-sleep-aids?utm_source=chatgpt.com", "text": "sleepfoundation.org", "description": "July 14, 2025 — NATURAL SLEEP AIDS: WHICH ARE THE MOST EFFECTIVE? Updated July 15, 2025 Written by Lucy Bryan ...", "section": "more" }, { "title": "Do Magnesium Sleep Drinks Really Work? What the Science Says", "url": "https://www.health.com/magnesium-drink-before-bed-11920427?utm_source=chatgpt.com", "text": "Health", "description": "Magnesium sleep drinks are beverages containing powdered magnesium and often calming ingredients like herbs or amino acids..." }, ... ], "search_queries": [ "best supplements for sleep evidence melatonin magnesium valerian 2025" ], "parse_status_code": 12000 } } ] } ```
{% hint style="warning" %} A composição da resposta pode variar dependendo de se a consulta foi feita a partir de um **desktop** ou **mobile** dispositivo. {% endhint %} ### Dicionário de dados de saída #### Exemplo de HTML
#### Estrutura JSON Todos os alvos de LLM retornam o mesmo envelope de nível superior `job` e `results[]` envelope. Veja [LLMs e IA](/api-targets/pt-br/llms-e-ia.md) para a referência completa de metadados. A tabela a seguir mostra os campos específicos de ChatGPT de `results[].content` campos: {% hint style="info" %} O número de itens e campos para um tipo específico de resultado pode variar dependendo do prompt enviado. {% endhint %}
CampoDescriçãoTipo
promptPrompt enviado para gerar o resultado.cadeia de caracteres
llm_modelModelo específico do ChatGPT usado para a resposta (por exemplo, gpt-4o).cadeia de caracteres
response_textResposta em texto simples do ChatGPT.cadeia de caracteres
markdown_textResposta do ChatGPT em Markdown.cadeia de caracteres
markdown_jsonRepresentação JSON estruturada da resposta em Markdown. Cada item contém tipo e children.array
citationsLista de citações de fontes da resposta. Os objetos contêm title, url, text, description, e section.array
search_queriesConsultas de pesquisa usadas pelo modelo para reunir informações.array de cadeias de caracteres
linksLista de objetos para detalhes do link de origem inline: url e text.array
shopping_productsLista de objetos contendo detalhes do produto: price, title, rating, currency, price_str, e thumbnail.array
adsDetalhes do anúncio contendo url, title, image_url, description, e um advertiser_info objeto.array
ads.advertiser_infoObjeto com nome do anunciante url, name, e image_urlobjeto
parse_status_code12000 – bem-sucedido. Caso contrário, o parser falhou ao extrair alguns ou todos os campos estruturados.inteiro
– condicional, retornado apenas quando o conteúdo estiver na resposta do LLM. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://developers.oxylabs.io/api-targets/pt-br/llms-e-ia/chatgpt.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.