# Naver AI Overview API (`parsebird/naver-ai-overview-api`) Actor Fetch Naver's AI Overview (AI 브리핑) for any Korean search query — generated answer text, cited sources, and related media. Batch queries in one run. - **URL**: https://apify.com/parsebird/naver-ai-overview-api.md - **Developed by:** [ParseBird](https://apify.com/parsebird) (community) - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 1 bookmarks - **User rating**: No ratings yet ## Pricing from $15.49 / 1,000 ai overview results This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README ### Naver AI Overview API Naver AI Overview API fetches Naver's **AI 브리핑 (AI Overview/Briefing)** — the AI-generated answer box that now appears above organic results on [search.naver.com](https://search.naver.com) — for any Korean (or other-language) search query, returned as clean structured JSON. 한국어: 네이버 AI 브리핑 API는 네이버 통합검색 상단에 표시되는 AI 생성 답변("AI 브리핑")을 검색어별로 가져와 정형화된 JSON으로 제공합니다.
Submit one query or a batch of queries and get the AI Overview's markdown answer, structured content blocks, cited sources, related media, and follow-up questions — or a clear "not shown" note when Naver has no AI Overview for that query.

##### Copy to your AI assistant ``` Use the Apify actor "parsebird/naver-ai-overview-api" (call it via ApifyClient) to fetch Naver's AI Overview (AI 브리핑) for one or more search queries. Example run input: {"queries": ["당뇨병 증상", "전기차 보조금"]}. Key inputs: query (string, a single search query), queries (array of strings, batched and merged with query, de-duplicated), proxyConfiguration (object, default Residential/KR — keep it for reliable results), maxConcurrency (integer, default 5, advanced). Output: one JSON object per resolved query with result_type ("ai_overview" or "error"), query, ai_overview_present (boolean), markdown (the full AI Overview answer as markdown), text_blocks (ordered paragraph/list blocks with reference_indexes), references (cited sources: index, title, link, source), media (related images/videos: title, platform, link, thumbnail), related_questions, note (explains why no overview was shown, when applicable), fetched_at, and error_message/error_type on error rows. Full API reference: https://apify.com/parsebird/naver-ai-overview-api/api. Get an API token at https://console.apify.com/account/integrations. ``` ### What does Naver AI Overview API do? [Naver](https://www.naver.com) — South Korea's dominant search engine — rolled out **AI 브리핑**, an AI-generated summary box shown above regular search results for many queries, similar in concept to Google's AI Overviews. Naver AI Overview API reads that box directly from Naver's own search-results payload and returns it as structured data, so you don't have to open a browser, parse HTML, or guess which queries trigger it. - 🔎 **Batch queries** — submit a single query or a list of queries in one run, de-duplicated automatically - 📝 **Full markdown answer** — the generated answer text, with headings and lists preserved - 🧩 **Structured content blocks** — the answer broken into paragraph/list segments, each tagged with which sources back it - 🔗 **Cited sources** — every reference Naver's AI cited, with title, link, and publisher - 🖼️ **Related media** — images and videos Naver surfaces alongside the answer - ❓ **Related/follow-up questions** — the topics and queries Naver links from the AI Overview, when present - 🚫 **Graceful "not shown" handling** — queries with no AI Overview return `ai_overview_present: false` with a explanatory note instead of an error 한국어: 네이버는 일부 검색어에 대해 통합검색 결과 상단에 "AI 브리핑"이라는 AI 생성 요약을 보여줍니다. 이 액터는 해당 브리핑 데이터를 직접 읽어 답변 텍스트, 출처, 관련 이미지·동영상, 연관 질문까지 구조화된 JSON으로 반환합니다. Results are ready to export as **JSON, CSV, or Excel**, available through the [Apify API](https://docs.apify.com/api/v2), and can run on a [schedule](https://docs.apify.com/platform/schedules) or be wired into [Make, Zapier, and other integrations](https://apify.com/integrations). ### Input parameters | Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | query | string | No\* | — | A single query, in Korean or any language, e.g. `당뇨병 증상`. | | queries | array of strings | No\* | `[]` | A batch of queries to check in one run. Merged with `query` and de-duplicated. | | proxyConfiguration | object | No | Residential (KR) | Keep the default — Naver's AI Overview renders most reliably to South Korean IPs. | | maxConcurrency | integer | No | 5 | Maximum number of queries resolved in parallel (advanced). | \* Provide `query`, `queries`, or both — at least one non-empty query is required. 한국어: `query`(단일 검색어) 또는 `queries`(검색어 배열) 중 하나 이상을 입력해야 합니다. 두 값 모두 입력하면 병합 후 중복이 제거됩니다. `proxyConfiguration`은 기본값(레지덴셜, 대한민국)을 유지하는 것을 권장합니다. **Single query:** ```json { "query": "당뇨병 증상" } ``` **Batch of queries:** ```json { "queries": ["당뇨병 증상", "전기차 보조금", "아이폰16 스펙"] } ``` ### What data can you extract from Naver's AI Overview? | Field | Description | |-------|-------------| | result\_type | `ai_overview` for a resolved query row, or `error` for a validation/fetch error row | | query | The search query this row corresponds to | | ai\_overview\_present | `true` if Naver returned an AI Overview for this query, `false` if none was shown | | markdown | The full AI Overview answer, rendered as markdown (headings, lists) | | text\_blocks | Ordered content blocks (paragraphs, lists), each with `type`, `snippet`, and `reference_indexes` | | references | Cited sources, each with `index`, `title`, `link`, and `source` (publisher name) | | media | Related images/videos, each with `title`, `platform`, `link`, and `thumbnail` | | related\_questions | Follow-up topics/questions Naver links from the AI Overview, when present | | note | Why no overview was returned, when `ai_overview_present` is `false` | | fetched\_at | ISO 8601 timestamp of when the row was produced | 한국어: 각 필드의 의미는 위 표를 참고하세요. `markdown`에는 전체 답변이, `references`에는 출처가, `media`에는 관련 이미지·동영상이 담깁니다. AI 브리핑이 없으면 `ai_overview_present`는 `false`가 되고 `note`에 이유가 설명됩니다. ### Output example ```json { "result_type": "ai_overview", "query": "당뇨병 증상", "ai_overview_present": true, "markdown": "당뇨병은 혈당이 높은 상태가 지속되는 만성질환으로... \n\n### 당뇨병의 증상\n- **삼다(三多) 증상**: 다음, 다뇨, 다식 현상이 나타납니다.", "text_blocks": [ { "type": "paragraph", "snippet": "당뇨병은 혈당이 높은 상태가 지속되는 만성질환으로...", "reference_indexes": [0, 1, 2] } ], "references": [ { "index": 0, "title": "당뇨병의 증상 - 삼성서울병원", "link": "http://www.samsunghospital.com/...", "source": "삼성서울병원" } ], "media": [ { "title": "당뇨병 - 인하대병원", "platform": "image", "link": "https://www.inha.com/...", "thumbnail": "https://www.inha.com/..." } ], "related_questions": [ { "question": "고혈압", "query": "고혈압" } ], "fetched_at": "2026-09-20T01:42:56.492Z" } ``` Full field-by-field description is in the table above. Download results in **JSON, HTML, CSV, or Excel** from the Dataset tab, or via the [Input/Output tab](https://docs.apify.com/platform/actors/running/runs-and-builds#outputs). ### Use cases - Monitor whether your brand, product, or medical/legal topic is cited as a source in Naver's AI Overview - Track how Naver's AI answers a set of customer-support or FAQ-style queries over time - Feed AI Overview text and citations into a Korean SEO or content-gap analysis tool - Compare AI-generated answers against your own published content for accuracy checks - Build a monitoring dashboard for AI-answer visibility across a list of target keywords 한국어: 브랜드·제품·의료/법률 주제가 AI 브리핑의 출처로 인용되는지 모니터링하거나, 다수의 검색어에 대한 AI 답변 변화를 추적하는 데 활용할 수 있습니다. ### How to use Naver AI Overview API 1. Click **Try for free** (no code needed) or grab the Actor ID for the API/SDK. 2. Enter one query in `query`, or list several in `queries`. 3. Keep the default `proxyConfiguration` (Residential, South Korea) for reliable results. 4. Click **Start** and watch resolved rows land in the dataset in real time. 5. Export the results as **JSON, CSV, or Excel**, or pull them via the [Apify API](https://docs.apify.com/api/v2) into your own pipeline. 한국어: 검색어를 하나 또는 여러 개 입력하고 실행(Start)하면 결과가 실시간으로 데이터셋에 저장됩니다. JSON, CSV, Excel로 내보내거나 API로 바로 가져올 수 있습니다. #### Python ```python from apify_client import ApifyClient client = ApifyClient("") run = client.actor("parsebird/naver-ai-overview-api").call(run_input={ "queries": ["당뇨병 증상", "전기차 보조금"], }) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item["query"], item["ai_overview_present"]) ``` #### JavaScript ```javascript import { ApifyClient } from 'apify-client'; const client = new ApifyClient({ token: '' }); const run = await client.actor('parsebird/naver-ai-overview-api').call({ queries: ['당뇨병 증상', '전기차 보조금'], }); const { items } = await client.dataset(run.defaultDatasetId).listItems(); console.log(items); ``` ### How much does it cost to use Naver AI Overview API? Naver AI Overview API uses [pay-per-event pricing](https://docs.apify.com/platform/actors/publishing/monetize#pay-per-event-pricing-model) — you're charged once per query resolved (whether or not Naver showed an AI Overview for it), never for compute time, and never for a failed request. | Event | Price per event | Price per 1,000 | |-------|----------------|-----------------| | Query resolved (Free plan) | $0.01699 | **$16.99** | | Query resolved (Bronze plan) | $0.01649 | **$16.49** | | Query resolved (Silver plan) | $0.01599 | **$15.99** | | Query resolved (Gold plan) | $0.01549 | **$15.49** | Resolving 1,000 queries costs **$16.99** on the Free plan, down to **$15.49** on the Gold plan — see the [Pricing tab](https://apify.com/parsebird/naver-ai-overview-api/pricing) for details. Failed requests are never charged. 한국어: 검색어 1건이 해결(resolve)될 때마다 한 번 과금되며, AI 브리핑이 없더라도(=`ai_overview_present: false`) 결과가 반환되면 과금됩니다. 요청이 실패한 경우는 과금되지 않습니다. ### Is it legal to use Naver AI Overview API? Naver AI Overview API only collects the AI Overview content that Naver **publicly displays** on search.naver.com for a given query, without logging in or bypassing any access control. Scraping publicly available data is generally legal, but you're responsible for how you use the data — always review [Naver's Terms of Service](https://www.naver.com) and consult [Apify's guide on the legality of web scraping](https://www.apify.com/is-web-scraping-legal) before reusing content commercially, especially medical or legal information, which is provided by Naver's AI "for reference only." 한국어: 이 액터는 로그인 없이 search.naver.com에서 공개적으로 표시되는 AI 브리핑 콘텐츠만 수집합니다. 공개 데이터 수집은 일반적으로 합법이지만, 특히 의료·법률 정보는 참고용으로만 사용하고 활용 방식에 대한 책임은 사용자에게 있습니다. ### Related Actors - [Naver Shopping Scraper](https://apify.com/parsebird/naver-shopping-scraper) — product listings from Naver Brand Store - [Naver Map Scraper](https://apify.com/parsebird/naver-map-scraper) — places, ratings, and business info from Naver Map - [Naver Blog & Cafe Scraper](https://apify.com/parsebird/naver-blog-cafe-scraper) — posts and comments from Naver Blog and Cafe - [Naver Place Review Scraper](https://apify.com/parsebird/naver-place-review-scraper) — reviews from Naver Place listings ### FAQ **What is Naver's AI Overview (AI 브리핑)?** It's an AI-generated answer box Naver shows above organic results for many search queries — summarizing several web sources into one answer, with citations, similar to Google's AI Overviews. **Does every query return an AI Overview?** No. Many queries — obscure, ambiguous, or navigational ones — show no AI Overview at all, or Naver may generate one live in the browser instead of pre-rendering it. Both cases return `ai_overview_present: false` with a `note` explaining why, not an error. **Can I query in English or another language?** Yes — `query`/`queries` accept any text Naver's search box accepts, including non-Korean queries, though the AI Overview itself (when shown) is generated in Korean. **Why does the Actor use a Residential (KR) proxy by default?** Naver's AI Overview renders most consistently for South Korean IPs. Keep the default proxy setting for reliable results. **Can I schedule recurring runs?** Yes. Use Apify's [Scheduler](https://docs.apify.com/platform/schedules) to re-run a fixed list of queries daily or weekly and track how Naver's AI answers change over time. **Something looks wrong or a query won't resolve — what do I do?** Open an issue on the Actor's **Issues** tab with the query and run URL. Naver updates its AI Overview format periodically; report it and it'll be investigated. 한국어: AI 브리핑은 검색어에 따라 표시되지 않을 수 있으며, 이 경우 오류가 아닌 `ai_overview_present: false`와 설명이 담긴 결과가 반환됩니다. 문제가 발견되면 Actor의 Issues 탭에 검색어와 실행 URL을 남겨주세요. # Changelog This Actor's version history is a separate document: https://apify.com/parsebird/naver-ai-overview-api/changelog.md # Actor input Schema ## `query` (type: `string`): A single search query, in Korean or any language, e.g. 당뇨병 증상. Provide this, queries, or both. ## `queries` (type: `array`): A batch of queries to check in one run. Merged with Query and de-duplicated. ## `proxyConfiguration` (type: `object`): Naver serves AI Overview results most reliably to South Korean IPs. Keep the default (Residential, South Korea). ## `maxConcurrency` (type: `integer`): Maximum number of queries resolved in parallel. ## Actor input object example ```json { "query": "전기차 보조금", "queries": [ "당뇨병 증상", "전기차 보조금" ], "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "KR" }, "maxConcurrency": 5 } ``` # Actor output Schema ## `dataset` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "query": "전기차 보조금", "queries": [ "당뇨병 증상", "전기차 보조금" ], "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "KR" } }; // Run the Actor and wait for it to finish const run = await client.actor("parsebird/naver-ai-overview-api").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "query": "전기차 보조금", "queries": [ "당뇨병 증상", "전기차 보조금", ], "proxyConfiguration": { "useApifyProxy": True, "apifyProxyGroups": ["RESIDENTIAL"], "apifyProxyCountry": "KR", }, } # Run the Actor and wait for it to finish run = client.actor("parsebird/naver-ai-overview-api").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "query": "전기차 보조금", "queries": [ "당뇨병 증상", "전기차 보조금" ], "proxyConfiguration": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "KR" } }' | apify call parsebird/naver-ai-overview-api --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,parsebird/naver-ai-overview-api" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/d4dZfTxPxITMMS1CK/builds/Gy6Mr7fHib0LYzNgX/openapi.json