# Naver AI Briefing Scraper (네이버 AI 브리핑 · AI Overview) (`magenta_courser/naver-ai-briefing-scraper`) Actor

Enter search queries and get Naver's AI Briefing (AI 브리핑) for each one: whether it appears, the answer text, every cited source with URL and domain, follow-up questions, and whether your own domains are cited. One row per query, no API key, no browser.

- **URL**: https://apify.com/magenta_courser/naver-ai-briefing-scraper.md
- **Developed by:** [SUNGHWAN CHO](https://apify.com/magenta_courser) (community)
- **Categories:** SEO tools, AI, Marketing
- **Features:** Limited permissions
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.60 / 1,000 ai briefings

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 Briefing Scraper (네이버 AI 브리핑) | AI Answers, Cited Sources & Citation Tracking (2026)

**Languages:** English · [한국어](#korean) · [中文](#chinese) · [日本語](#japanese)

[![$0.002 per Naver AI Briefing found; queries with no briefing are saved free](https://raw.githubusercontent.com/experimory-crypto/naver-map-scraper-examples/main/assets/hero-naver-ai-briefing-scraper.png)](https://console.apify.com/actors/S7l8NLVKhGPLFenSE/input)

Enter **search queries** and get Naver's **AI Briefing (AI 브리핑)** for each one: whether it appears, the answer text, every cited source with URL and domain, follow-up questions, and whether your own domains are among the citations. One row per query. No API key, no login, no browser.

Part of a small set of Korean data Actors from one maintainer: [Naver Search](https://apify.com/magenta_courser/naver-search-scraper), [Naver Blog, Cafe & News](https://apify.com/magenta_courser/naver-blog-cafe-search-scraper), [Naver Shopping ranks](https://apify.com/magenta_courser/naver-shopping-rank-tracker) and [Naver Map reviews](https://apify.com/magenta_courser/naver-place-reviews-scraper). Author nicknames are never collected.

> **Free plan:** Apify's $5 monthly credit covers about 2,500 AI Briefings with this Actor. Queries where Naver shows no briefing are not charged.

### What is Naver AI Briefing?

Naver is the largest search engine in South Korea. For many informational queries it now puts an AI-written answer above the regular results, with a short list of cited pages. It is the Korean counterpart of Google's AI Overviews. If you work on Korean SEO, brand monitoring or answer-engine optimization (AEO/GEO), the questions are always the same: *Does my query trigger an AI Briefing? What does it say? Which sites does it cite, and is mine one of them?* This Actor answers them in bulk.

### Why choose this Actor?

**You pay only when there is a briefing.**<br>
$0.002 per query where Naver showed an AI Briefing. Rows with `hasBriefing: false` are still saved, so you can tell "no briefing" from "failed", but they are not charged.

**"Is my domain cited?" is a field, not a script you write.**<br>
Give `targetDomains` and each row returns `isTargetCited`, `citedTargetDomains` and `firstTargetPosition` (the citation number of your first cited page). Subdomains match, and a single Naver blog or cafe can be tracked by path (`blog.naver.com/mybrand`).

**Sources you can analyse.**<br>
Each cited source has its citation number, title, URL, domain, site name, an official-source flag, a snippet and the publish time when Naver gives one. `sourceDomains` and `officialSourceCount` summarise them per query.

**All six briefing types.**<br>
`general`, `knowledge`, `health`, `public` (government and policy), `video` (answer built around a short video) and `place` (answer that recommends businesses, returned in `mentionedPlaces` with Naver Place IDs).

**Measured, not estimated.** 196 Korean queries finished in 324 seconds at 256 MB with 0 retries in run `2DWm7kFhktvbfedk3` (build 0.1.3, 2026-11-11); 131 of them had a briefing. The live build 0.1.4 differs only in how `place` briefings list businesses.

### Quick start

Two queries and one domain to look for. At the Free-plan price this costs at most $0.004.

```json
{
  "queries": ["당뇨병 증상", "연말정산 하는 법"],
  "targetDomains": ["nts.go.kr"]
}
```

[Open the Actor input](https://console.apify.com/actors/S7l8NLVKhGPLFenSE/input), enter your queries one per line, and click **Start**. Export the dataset as JSON, CSV or Excel. `당뇨병 증상` means "diabetes symptoms"; `연말정산 하는 법` means "how to do the year-end tax settlement".

#### Copy to your AI assistant

Paste this into ChatGPT, Claude, Cursor or another assistant so it can call the Actor for you:

```text
Use the Apify Actor magenta_courser/naver-ai-briefing-scraper to check Naver's AI Briefing (the AI answer on Naver search, South Korea) for a list of queries.

Input (JSON): "queries" is a list of search queries, best in Korean and phrased as a user would type them (required). "targetDomains" is an optional list of domains to look for among the cited sources, e.g. "mybrand.co.kr" or "blog.naver.com/mybrand".

Output: one dataset row per query with hasBriefing (boolean), briefingType, briefingText, briefingMarkdown, sourceCount, sources (position, title, url, domain, siteName, isOfficial, snippet, publishedAt), sourceDomains, isTargetCited, citedTargetDomains, firstTargetPosition, followUpQueries, relatedQuestions (question, answer, sources), media and mentionedPlaces. Missing values are null and empty lists are []. Queries without a briefing still return a row with hasBriefing false.

Run it through the Apify API: POST https://api.apify.com/v2/acts/magenta_courser~naver-ai-briefing-scraper/run-sync-get-dataset-items with my Apify token as a Bearer token and the input as the JSON body. Or connect the MCP server https://mcp.apify.com?tools=magenta_courser/naver-ai-briefing-scraper.

Price: $0.002 per query that has a briefing (Free plan); queries without one are free.
```

#### Use it over MCP

Add this server to Claude Desktop, Cursor or any MCP client, authenticated with your Apify token:

```text
https://mcp.apify.com?tools=magenta_courser/naver-ai-briefing-scraper
```

An agent can then answer "what does Naver's AI say about X, and who does it cite?" with one tool call.

### Key features

- **One row per query**, 25 fields, every row has every field.
- **Answer as plain text and as markdown** (`briefingText`, `briefingMarkdown`), with citations as `[1] [2]` that match `sources[].position`.
- **Citation check** against your domains, including path-level targets for Naver blogs and cafes.
- **Follow-up searches** Naver links from inside the answer (`followUpQueries`).
- **Related questions (관련질문)** with their own AI answers and sources, returned even when the query has no briefing.
- **Media** shown with the briefing (images, videos) and **businesses** recommended by `place` briefings.
- **Run summary** in the key-value store (`RUN_SUMMARY`): share of queries with a briefing, queries citing your domains, per-query status.
- **One request per query**, a few queries at a time, on the default Apify datacenter proxy.
- **Clean stop at your cost limit.** Remaining queries are marked `budgetLimited` in `RUN_SUMMARY`.

### How to scrape Naver AI Briefing

#### Does my keyword list trigger AI Briefings?

```json
{
  "queries": ["당뇨병 증상", "연말정산 하는 법", "부산 호텔", "계란 삶는 시간", "선크림 추천"]
}
```

In run `3lBNvO1sBdpblEgrX` (2026-11-11) this exact list returned 4 briefings of 4 different types (`health`, `public`, `place`, `video`) and 1 row without a briefing (`선크림 추천`).

#### Is my site cited?

```json
{
  "queries": ["연말정산 하는 법", "연말정산 간소화", "연말정산 환급"],
  "targetDomains": ["nts.go.kr"]
}
```

Read `isTargetCited` and `firstTargetPosition` on each row.

#### Track one Naver blog or cafe

A bare `blog.naver.com` matches every Naver blog. Add the path to track just yours.

```json
{
  "queries": ["성수 카페 추천", "서울숲 디저트"],
  "targetDomains": ["blog.naver.com/mybrand", "cafe.naver.com/mycafe"]
}
```

#### Which domains does Naver's AI trust in my category?

Run your category's questions without `targetDomains` and count `sourceDomains` across rows (see the Python recipe under Advanced usage).

```json
{
  "queries": ["고혈압 증상", "고혈압 식단", "혈압 낮추는 운동", "고혈압 약 부작용"]
}
```

#### Which businesses does a local AI answer recommend?

For local queries with a `place` briefing, `mentionedPlaces` lists the businesses in the answer.

```json
{
  "queries": ["부산 호텔"]
}
```

From the run above, the first of 6 businesses returned:

```json
{
  "position": 1,
  "name": "시그니엘 부산",
  "placeId": "1857519376",
  "category": "5성급",
  "address": "부산 해운대구 중동",
  "rating": null,
  "reviewCount": 1458,
  "url": "https://map.naver.com/p/entry/place/1857519376"
}
```

Pass `placeId` to [Naver Map Reviews Scraper](https://apify.com/magenta_courser/naver-place-reviews-scraper) to read what customers say about those businesses.

### Input parameters

| Field | Type | Required | Description |
|---|---|---|---|
| `queries` | array of strings | yes | Search queries, one per line, as typed into the Naver search bar. Duplicates are removed. Korean informational, question-style queries trigger briefings most often. |
| `targetDomains` | array of strings | no | Domains to look for among the cited sources, e.g. `mybrand.co.kr`. Subdomains match. `https://`, `www.` and trailing slashes are ignored. To track one Naver blog or cafe, add its path: `blog.naver.com/mybrand`. |
| `proxyConfiguration` | object | no | Defaults to Apify datacenter proxy, which worked for Naver search in all our runs. Switch to `RESIDENTIAL` with country `KR` only if the log shows repeated request errors. |

### What data can you extract from Naver AI Briefing?

One dataset row per query. Every row has every field; missing values are `null` and empty lists are `[]`.

| Field | Type | Meaning |
|---|---|---|
| `query` | string | Your input query. |
| `hasBriefing` | boolean | Naver showed an AI Briefing on the integrated search page. |
| `briefingType` | string / null | `general`, `knowledge`, `health`, `public`, `video`, `place`, or another label Naver introduces. |
| `briefingTemplate` | string / null | Naver's internal template name, e.g. `aibAnswer`, `aibHealth`, `aibPublic`, `aibVideo`, `aibPlace`. |
| `briefingText` | string / null | The answer as plain text. Citations appear as `[1] [2]`. |
| `briefingMarkdown` | string / null | The answer as markdown (headings, bold, lists, tables). |
| `briefingLength` | integer / null | Characters in `briefingText`. |
| `sourceCount` | integer / null | Number of cited sources. |
| `sources` | array | Cited sources: `position` (the `[n]` in the answer), `title`, `url`, `domain`, `siteName`, `isOfficial`, `snippet`, `publishedAt`, `naverOrder`. |
| `sourceDomains` | array | Unique domains of the sources. |
| `officialSourceCount` | integer / null | Sources Naver marks as official (government, hospital, institution). |
| `isTargetCited` | boolean / null | One of your `targetDomains` is cited. `null` when you gave none. |
| `citedTargetDomains` | array | Which of your `targetDomains` are cited. |
| `firstTargetPosition` | integer / null | Lowest citation number among your cited pages. |
| `followUpQueries` | array | Follow-up searches Naver links from keywords inside the answer. |
| `relatedQuestionCount`, `relatedQuestions` | integer / array | Naver's AI-generated related questions: `position`, `question`, `answer`, `sources`. |
| `targetDomainsInRelatedQuestions` | array | Which of your `targetDomains` are cited in the related questions' answers. |
| `media` | array | Images and videos shown with the briefing: `position`, `type`, `title`, `url`, `domain`, `siteName`, `thumbnailUrl`. |
| `mentionedPlaces` | array | Businesses a `place` briefing recommends: `position`, `name`, `placeId`, `category`, `address`, `rating`, `reviewCount`, `url`. |
| `sourceAttribution` | string / null | Data provider line on some briefings. |
| `briefingGeneratedAt` | string / null | Time stamp Naver attaches to the briefing. |
| `searchUrl`, `scrapedAt`, `schemaVersion` | string / integer | The scraped URL, when it was scraped (UTC), output version. |

#### Output example: a query with a briefing

From run `3lBNvO1sBdpblEgrX` (2026-11-11, build 0.1.4), query `연말정산 하는 법` with `targetDomains: ["nts.go.kr"]`. `briefingText`, `briefingMarkdown` and the snippets are cut short here with `…`, and 3 of the 6 sources are shown; everything else is unedited.

```json
{
  "query": "연말정산 하는 법",
  "hasBriefing": true,
  "briefingType": "public",
  "briefingTemplate": "aibPublic",
  "briefingText": "연말정산은 1년 동안 급여에서 원천징수한 세액과 실제 소득에 따른 정확한 세액을 비교하여, 세금을 더 냈다면 돌려받고 적게 냈다면 추가로 납부하는 절차를 말합니다. [2] [3] [4] [5]\n\n연말정산 이용 방법\n\n회사의 업무 환경에 따라 다음과 같은 유형으로 진행됩니다.\n\n- 간소화 자료 출력 제출: 근로자가 국세청 간소화 자료를 출력하여 회사에 제출\n…",
  "briefingMarkdown": "연말정산은 1년 동안 급여에서 원천징수한 세액과 실제 소득에 따른 정확한 세액을 비교하여, … [2] [3] [4] [5]\n\n### 연말정산 이용 방법\n\n…",
  "briefingLength": 734,
  "sourceCount": 6,
  "sources": [
    {
      "position": 1,
      "title": "국세청>국세신고안내>개인신고안내>연말정산>편리한 연말정산 이용방법",
      "url": "https://www.nts.go.kr/nts/cm/cntnts/cntntsView.do?cntntsId=7706&mi=2305",
      "domain": "nts.go.kr",
      "siteName": "국세청",
      "isOfficial": true,
      "snippet": "편리한 연말정산 이용방법 홈 국세신고안내 개인신고안내 연말정산 편리한 연말정산 이용방법 …",
      "publishedAt": null,
      "naverOrder": 5
    },
    {
      "position": 2,
      "title": "연말정산 - 위키백과 한국어",
      "url": "https://ko.wikipedia.org/wiki/%EC%97%B0%EB%A7%90%EC%A0%95%EC%82%B0",
      "domain": "ko.wikipedia.org",
      "siteName": "위키백과 한국어",
      "isOfficial": false,
      "snippet": "연말정산 (年末精算)은 급여소득에서 원천징수한 세액의 과부족을 연말에 정산하는 것을 말한다. …",
      "publishedAt": null,
      "naverOrder": 1
    },
    {
      "position": 3,
      "title": "[머니 마이웨이] 연말정산 환급액 미리 확인···남은 두 달 절세하는 법",
      "url": "https://www.womaneconomy.co.kr/news/articleView.html?idxno=260897",
      "domain": "womaneconomy.co.kr",
      "siteName": "여성경제신문",
      "isOfficial": false,
      "snippet": "9일 국세청에 따르면 지난달 28일 개통한 '연말정산 미리보기' 서비스가 다음 달 18일까지 운영됩니다. …",
      "publishedAt": "2026-11-10T12:26:00+09:00",
      "naverOrder": 2
    }
  ],
  "sourceDomains": ["nts.go.kr", "ko.wikipedia.org", "womaneconomy.co.kr", "n.news.naver.com"],
  "officialSourceCount": 1,
  "isTargetCited": true,
  "citedTargetDomains": ["nts.go.kr"],
  "firstTargetPosition": 1,
  "followUpQueries": ["연말정산 홈택스", "연말정산 체크카드 소득공제", "연말정산 신용카드 소득공제", "연말정산 연금저축", "연말정산 IRP", "연말정산 고향사랑기부제"],
  "relatedQuestionCount": 0,
  "relatedQuestions": [],
  "targetDomainsInRelatedQuestions": [],
  "media": [],
  "mentionedPlaces": [],
  "sourceAttribution": null,
  "briefingGeneratedAt": "2026-11-11T18:44:37+09:00",
  "searchUrl": "https://search.naver.com/search.naver?where=nexearch&ssc=tab.nx.all&query=%EC%97%B0%EB%A7%90%EC%A0%95%EC%82%B0+%ED%95%98%EB%8A%94+%EB%B2%95",
  "scrapedAt": "2026-11-11T09:45:28.047Z",
  "schemaVersion": 1
}
```

#### Output example: a query without a briefing

Same run, query `선크림 추천` ("sunscreen recommendations"). Not charged. Naver showed no briefing but 3 related questions with AI answers. The first question is shown with one of its two sources, cut short.

```json
{
  "query": "선크림 추천",
  "hasBriefing": false,
  "briefingType": null,
  "briefingTemplate": null,
  "briefingText": null,
  "briefingMarkdown": null,
  "briefingLength": null,
  "sourceCount": null,
  "sources": [],
  "sourceDomains": [],
  "officialSourceCount": null,
  "isTargetCited": false,
  "citedTargetDomains": [],
  "firstTargetPosition": null,
  "followUpQueries": [],
  "relatedQuestionCount": 3,
  "relatedQuestions": [
    {
      "position": 1,
      "question": "선크림 고를 때 확인할 기준은 무엇인가요?",
      "answer": "선크림을 고를 때는 SPF와 PA 지수 외에도 자신의 피부 타입과 사용 환경에 맞는 제품을 선택해야 합니다. [1] [2]\n\n…",
      "sources": [
        {
          "position": 2,
          "title": "펄피부과 칼럼 - [분당 펄피부과] 내 피부 타입에 추천하는 선크림은? SPF/PA 지수....",
          "url": "https://www.pearlclinic.co.kr/46136",
          "domain": "pearlclinic.co.kr",
          "siteName": "펄피부과의원",
          "isOfficial": null,
          "snippet": "자외선으로부터 우리 피부를 보호해주는 선크림, 여름뿐만 아니라 365일 꼭 필요한 존재입니다. …",
          "publishedAt": null,
          "naverOrder": null
        }
      ]
    }
  ],
  "targetDomainsInRelatedQuestions": [],
  "media": [],
  "mentionedPlaces": [],
  "sourceAttribution": null,
  "briefingGeneratedAt": null,
  "searchUrl": "https://search.naver.com/search.naver?where=nexearch&ssc=tab.nx.all&query=%EC%84%A0%ED%81%AC%EB%A6%BC+%EC%B6%94%EC%B2%9C",
  "scrapedAt": "2026-11-11T09:45:12.960Z",
  "schemaVersion": 1
}
```

#### Run summary

Stored in the run's key-value store as `RUN_SUMMARY` (not in the dataset, not charged). From the same run, per-query list shortened to one entry:

```json
{
  "source": "naver-ai-briefing",
  "schemaVersion": 1,
  "status": "completed",
  "queriesTotal": 5,
  "queriesCompleted": 5,
  "queriesFailed": 0,
  "queriesBudgetLimited": 0,
  "queriesWithBriefing": 4,
  "queriesWithoutBriefing": 1,
  "briefingRate": 0.8,
  "targetDomains": ["nts.go.kr"],
  "queriesCitingTarget": 1,
  "requests": 5,
  "retries": 0,
  "queries": [
    { "query": "연말정산 하는 법", "status": "completed", "hasBriefing": true, "briefingType": "public", "sourceCount": 6, "citedTargetDomains": ["nts.go.kr"], "errorMessage": null }
  ],
  "finishedAt": "2026-11-11T09:45:29.247Z"
}
```

### Advanced usage

#### Daily citation tracking with an alert

Schedule a daily run over your keyword list with `targetDomains` set, then compare with yesterday:

```python
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("magenta_courser/naver-ai-briefing-scraper").call(run_input={
    "queries": ["연말정산 하는 법", "연말정산 간소화", "연말정산 환급"],
    "targetDomains": ["nts.go.kr"],
})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    if row["hasBriefing"] and not row["isTargetCited"]:
        print("Briefing without us:", row["query"], row["sourceDomains"])
```

#### Share of voice: which domains are cited most

```python
from collections import Counter

rows = list(client.dataset(run["defaultDatasetId"]).iterate_items())
domains = Counter(d for row in rows for d in row["sourceDomains"])
print(domains.most_common(10))
```

In our 196-query test list (run `2DWm7kFhktvbfedk3`), the most cited domain was `blog.naver.com`, in 91 queries. Your category will differ.

#### Content gaps

`followUpQueries` and `relatedQuestions[].question` are what Naver expects users to ask next. Feed them back into `queries` to map a topic one step deeper.

#### Feed the answer to your own LLM

`briefingMarkdown` keeps headings, lists and tables, and the `[n]` markers map to `sources[].position`, so a downstream model can quote Naver's answer with its sources.

#### One call from the command line

```bash
curl -X POST "https://api.apify.com/v2/acts/magenta_courser~naver-ai-briefing-scraper/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"queries": ["당뇨병 증상"], "targetDomains": ["amc.seoul.kr"]}'
```

### How much does it cost to scrape Naver AI Briefing?

Pay per event, no subscription. Prices below are the Free-plan prices; paid Apify plans get the discount shown.

| Event | Price | Bronze / Silver / Gold and above | When |
|---|---|---|---|
| `briefing` | **$0.002** per row | $0.0019 / $0.0018 / $0.0016 | A query for which Naver showed an AI Briefing. |
| Actor start | $0.00005 | — | Once per run. |

Not charged: queries without a briefing (their rows, including related questions, are still saved), failed queries, the run summary.

Worked examples at the Free-plan price. The share of queries with a briefing depends on your keywords, so three rates are shown:

| Job | Briefings found | Cost |
|---|---|---|
| Our test run: 196 informational Korean queries (measured, 66.8% had a briefing) | 131 | **$0.26** |
| 100 queries, half with a briefing | 50 | **$0.10** |
| 1,000 queries, 30% with a briefing | 300 | **$0.60** |
| Daily tracking of 200 queries, half with a briefing | 100 per day | **$0.20 per day**, about $6 per month |

Set **Maximum cost per run** in the console to cap a run. The Actor stops when the limit is reached and keeps what it has stored. Checked in run `nKRov3VGdSC7PtcKr`: with a $0.005 limit and 5 queries, it charged 2 briefings and marked the other 3 queries `budgetLimited`.

**How this compares.** The other Actor on Apify Store for this data, `johnvc/naver-ai-overview-api`, lists a public Free-plan price of $0.018 per query (checked 2026-11-15), and its pricing description, when we read it on 2026-11-11, charged a query whether or not a briefing appeared. For the 196-query list above that is about $3.53 against $0.26 here. It is the more widely used of the two and returns per-paragraph citation blocks (`text_blocks`), which this Actor does not; here the same information is the `[n]` markers at the end of each paragraph.

### Scheduling and integrations

- **Schedules.** Briefings change, so run daily or weekly on the same query list and compare `hasBriefing`, `sourceDomains` and `isTargetCited` over time.
- **Webhooks and automation.** Send results to Slack, Google Sheets, Make, Zapier or n8n with Apify integrations, or call your own endpoint when a run finishes.
- **API clients.** Any HTTP client works; official clients exist for Python and JavaScript (`apify-client`).

```javascript
import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_APIFY_TOKEN' });
const run = await client.actor('magenta_courser/naver-ai-briefing-scraper').call({
    queries: ['연말정산 하는 법'],
    targetDomains: ['nts.go.kr'],
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items.map((r) => [r.query, r.hasBriefing, r.isTargetCited, r.firstTargetPosition]));
```

### FAQ

**Do I need a Naver account or API key?**
No. The Actor reads the public search page.

**How often does Naver show an AI Briefing?**
It depends on the query. In our test list of 196 informational Korean queries, 131 (66.8%) had one. We wrote that list to favour question-style queries, so expect a lower share on a typical keyword list. In that test, brand or person names alone, real-time information (weather, stock prices), local "best restaurant" queries and product recommendations mostly had none.

**Can I use English queries?**
Yes, but Naver shows briefings mostly for Korean queries.

**Why does the same query sometimes have a briefing and sometimes not?**
Naver generates briefings and tunes the feature continuously. In two of our runs 6 minutes apart, the 94 queries present in both agreed on having a briefing 94 out of 94 times, and the source lists matched for all 73 with a briefing; over days, expect changes. Track `RUN_SUMMARY.briefingRate` over time.

**What happens to a query that fails?**
It is tried up to 5 times on a new proxy session. If it still fails it produces no row and no charge, and is listed with an error message in `RUN_SUMMARY`. The run itself fails only if every query failed.

**How many queries can one run take?**
The largest run we have made is 196 queries (324 seconds, peak memory under 130 MB of 256 MB). Larger lists should work the same way but we have not measured them; split very large lists across runs if you want to be safe.

**Does it cover mobile search or AI summaries inside other modules?**
No. It reads the AI Briefing block of the desktop integrated search page (통합검색). AI summaries that Naver loads inside other modules, such as the travel course module, are not covered.

**Do you collect personal data?**
Nicknames of blog, cafe and video authors are not collected; `siteName` is the publisher or platform name. The cited `url` is kept because it is the citation itself, and a Naver blog URL contains the blog's ID.

**What is `naverOrder`?**
Naver's own order value for the source card. It can differ from the citation number in `position`, which is the `[n]` used in the answer text.

### More Korean data Actors

[![Naver Map Reviews Scraper: $0.50 per 1,000 reviews](https://raw.githubusercontent.com/experimory-crypto/naver-map-scraper-examples/main/assets/hero-naver-place-reviews-scraper.png)](https://apify.com/magenta_courser/naver-place-reviews-scraper)

[![Naver Shopping Rank Tracker: top 1,000 ranks for any keyword](https://raw.githubusercontent.com/experimory-crypto/naver-map-scraper-examples/main/assets/hero-naver-shopping-rank-tracker.png)](https://apify.com/magenta_courser/naver-shopping-rank-tracker)

| Actor | What you put in → what you get |
|---|---|
| [Naver Search Scraper](https://apify.com/magenta_courser/naver-search-scraper) | Keywords → the Naver integrated search page as rows: section, rank, ad flag, title, URL, snippet, related searches. |
| [Naver Blog, Cafe & News Search Scraper](https://apify.com/magenta_courser/naver-blog-cafe-search-scraper) | Keywords → blog, cafe and news search results with title, URL, snippet and publish time. |
| [Naver Blog Rank Tracker](https://apify.com/magenta_courser/naver-blog-rank-tracker) | Keywords + your blog IDs or post URLs → your rank in the Naver Blog tab, with change since the last run. |
| [Naver News Scraper](https://apify.com/magenta_courser/naver-news-scraper) | Keywords or article URLs → Naver News articles with publisher, times, URLs and optional full text. |
| [Naver DataLab Search Trends Scraper](https://apify.com/magenta_courser/naver-datalab-trends-scraper) | Korean keywords → search interest (0 to 100) per day, week or month. |
| [Naver Place Rank Tracker](https://apify.com/magenta_courser/naver-place-rank-tracker) | Keywords + your place IDs → your rank in Naver Map search. |
| [Naver Map Reviews Scraper](https://apify.com/magenta_courser/naver-place-reviews-scraper) | Place IDs or Naver Map URLs → visitor reviews with rating, text, dates, keyword codes and owner reply. |
| [Naver Shopping Scraper & Keyword Rank Tracker](https://apify.com/magenta_courser/naver-shopping-rank-tracker) | Shopping keywords → ranked products with price, store, rating, reviews and stock. |

Code examples for these Actors: [github.com/experimory-crypto/naver-map-scraper-examples](https://github.com/experimory-crypto/naver-map-scraper-examples).

### 한국어 안내 (Korean)

검색어를 넣으면 네이버 통합검색의 AI 브리핑을 검색어당 한 행으로 돌려줍니다. 브리핑이 떴는지, 본문(텍스트와 마크다운), 인용된 출처의 제목·URL·도메인·공식 여부, 후속 검색어, 관련질문과 그 답변이 들어 있습니다. `targetDomains`에 내 도메인(또는 `blog.naver.com/아이디`)을 넣으면 인용 여부와 인용 번호를 바로 알려 줍니다. 요금은 브리핑이 뜬 검색어 1건당 $0.002이며, 브리핑이 없는 검색어는 행은 저장되지만 과금되지 않습니다. 로그인·API 키 없이 공개 검색 화면만 읽고, 블로그·카페·영상 작성자의 닉네임은 수집하지 않습니다. 데스크톱 통합검색의 AI 브리핑 블록만 다룹니다.

### 中文说明 (Chinese)

输入搜索词，即可获得 Naver 综合搜索中的 AI 简报（AI 브리핑），每个搜索词一行。包含是否出现 AI 简报、正文（纯文本和 Markdown）、被引用来源的标题、URL、域名和是否为官方来源、后续搜索词，以及相关问题及其回答。在 `targetDomains` 中填入自己的域名（或 `blog.naver.com/账号ID`），即可直接得知是否被引用以及引用序号。费用为每个出现 AI 简报的搜索词 $0.002；没有 AI 简报的搜索词会保存数据行，但不计费。无需登录或 API 密钥，只读取公开的搜索页面，不采集博客、Cafe 和视频作者的昵称。仅支持桌面版综合搜索中的 AI 简报区块。

### 日本語ガイド (Japanese)

検索キーワードを入力すると、Naver 統合検索の AI ブリーフィング（AI 브리핑）がキーワードごとに 1 行で出力されます。ブリーフィングが表示されたかどうか、本文（テキストと Markdown）、引用された出典のタイトル・URL・ドメイン・公式かどうか、フォローアップ検索語、関連質問とその回答が含まれます。`targetDomains` に自分のドメイン（または `blog.naver.com/アカウントID`）を入れると、引用の有無と引用番号がすぐに分かります。料金はブリーフィングが表示されたキーワード 1 件あたり $0.002 で、ブリーフィングのないキーワードは行は保存されますが課金されません。ログインや API キーなしで公開の検索画面のみを読み取り、ブログ・カフェ・動画の投稿者のニックネームは収集しません。デスクトップ版統合検索の AI ブリーフィングブロックのみが対象です。

### Support

Something looks wrong, or you need another field? Open an issue in the **Issues** tab with the query and the run ID. We answer every issue.

# Actor input Schema

## `queries` (type: `array`):

Queries to check on Naver, one per line, exactly as a user would type them into the Naver search bar. Naver shows an AI Briefing mostly for informational, question-style Korean queries, e.g. 당뇨병 증상 (diabetes symptoms), 연말정산 하는 법 (how to do the year-end tax settlement). Each query returns one row; duplicates are removed.

## `targetDomains` (type: `array`):

Domains you want to find among the sources Naver cites, e.g. mybrand.co.kr. Subdomains match too. To track a single Naver blog or cafe, add its path: blog.naver.com/mybrand. Each row then tells you whether these were cited (isTargetCited), which ones (citedTargetDomains) and at which citation number (firstTargetPosition). Leave empty to just collect the briefings.

## `proxyConfiguration` (type: `object`):

Proxy settings. The default Apify datacenter proxy works for Naver search. Switch to RESIDENTIAL with country KR only if the log shows repeated request errors.

## Actor input object example

```json
{
  "queries": [
    "당뇨병 증상",
    "연말정산 하는 법"
  ],
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}
```

# Actor output Schema

## `results` (type: `string`):

One row per query as dataset items.

## `runSummary` (type: `string`):

Per-query status (completed, failed, budgetLimited), how many queries had an AI Briefing and how many cite a target domain. Not billed.

# 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 '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "queries": [
        "당뇨병 증상",
        "연말정산 하는 법"
    ],
    "proxyConfiguration": {
        "useApifyProxy": true
    }
};

// Run the Actor and wait for it to finish
const run = await client.actor("magenta_courser/naver-ai-briefing-scraper").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 '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "queries": [
        "당뇨병 증상",
        "연말정산 하는 법",
    ],
    "proxyConfiguration": { "useApifyProxy": True },
}

# Run the Actor and wait for it to finish
run = client.actor("magenta_courser/naver-ai-briefing-scraper").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 '{
  "queries": [
    "당뇨병 증상",
    "연말정산 하는 법"
  ],
  "proxyConfiguration": {
    "useApifyProxy": true
  }
}' |
apify call magenta_courser/naver-ai-briefing-scraper --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,magenta_courser/naver-ai-briefing-scraper"
        }
    }
}
```

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 <APIFY_API_TOKEN>` 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/S7l8NLVKhGPLFenSE/builds/uc7lbMQu1R6kdrxqh/openapi.json
