Naver Web, Blog, Cafe & News Results Scraper: MCP config, n8n workflow and API

{
  "mode": "webSearch",
  "searchQueries": [
    "비비바"
  ],
  "maxItems": 3,
  "maxItemsPerQuery": 3,
  "maxPagesPerQuery": 1,
  "sortBy": "relevance",
  "dateRange": "any",
  "includeAds": false,
  "includeContent": false,
  "includeSerpFeatures": false
}

---
name: naver-web-blog-cafe-and-news-results-scraper
description: "Naver results across web, blog, cafe, news, image, video, integrated blocks and autocomplete — exact URLs, titles, snippets, dates, thumbnails, ranks and vertical-specific fields. Runs the Apify Actor vexaloom-labs/naver-web-blog-cafe-and-news-results-scraper. Use when the user needs Naver data with fields such as query, resultType, rank, title, url, date and an Apify token is available."
compatibility: "Needs network access, curl, and an APIFY_TOKEN environment variable. Runs are billed to the token owner's Apify account."
metadata:
  actor: "vexaloom-labs/naver-web-blog-cafe-and-news-results-scraper"
  store-url: "https://apify.com/vexaloom-labs/naver-web-blog-cafe-and-news-results-scraper"
---

# Naver Web, Blog, Cafe & News Results Scraper

Use this skill to fetch Naver data with the Apify Actor `vexaloom-labs/naver-web-blog-cafe-and-news-results-scraper` and work with the returned rows.

## Before running

1. Check that `APIFY_TOKEN` is set in the environment. Never print it or write it to a file.
2. Build `input.json` from the user's request using the fields below. Keep limits small for a first run.
3. Confirm the search terms or URLs with the user if the request is ambiguous.

## Input fields

| Field | Type | Meaning |
| --- | --- | --- |
| `mode` | one of `webSearch`, `blogSearch`, `cafeSearch`, `newsSearch`, `imageSearch`, `videoSearch`, `integratedSearch`, `autocomplete`, required | Which Naver result surface to collect. |
| `searchQueries` | array | One or more Korean or any-language queries, e.g. `비비바` or `서울 맛집`. Duplicates and blank entries are removed. (Legacy `searchQuery` and `query` keys are still accepted.) |
| `maxItems` | integer | Hard cap on all normal result records across every query (error records are extra). |
| `maxItemsPerQuery` | integer | Hard cap on normal result records produced by each query. |
| `maxPagesPerQuery` | integer | Page ceiling for paginated modes (blog, cafe, news, image, video). Collection also stops when Naver runs out of results. |
| `sortBy` | one of `relevance`, `date` | Relevance or newest first. Applies to blog, cafe, news, image and video modes; web and integrated modes use Naver's default order. |
| `dateRange` | one of `any`, `1d`, `1w`, `1m`, `6m`, `1y` | Only return results published inside this window. Applies to blog, cafe, news, image and video modes; web and integrated modes do not support a date filter. |
| `includeAds` | boolean | Keep paid blog placements and integrated-search ads, marked with `isAd`. (Blog and integrated modes.) |
| `includeContent` | boolean | Fetch the post or article body, inline images and author for blog and news results. One extra request per result; unavailable bodies are omitted. (Blog and news modes.) |
| `includeSerpFeatures` | boolean | Include place cards and AI briefing blocks from the integrated results page, when Naver shows them. (Integrated mode.) |

Example `input.json` (the Actor's published prefill):

```json
{
  "mode": "webSearch",
  "searchQueries": [
    "비비바"
  ],
  "maxItems": 3,
  "maxItemsPerQuery": 3,
  "maxPagesPerQuery": 1,
  "sortBy": "relevance",
  "dateRange": "any",
  "includeAds": false,
  "includeContent": false,
  "includeSerpFeatures": false
}
```

## Run

```bash
curl -sS -X POST "https://api.apify.com/v2/acts/vexaloom-labs~naver-web-blog-cafe-and-news-results-scraper/run-sync-get-dataset-items" \
  -H "Authorization: Bearer $APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d @input.json > results.json
```

The call waits for the run to finish and returns the dataset items as a JSON array. If the run needs more than 300 seconds the API answers with HTTP 408; then start the run with `POST /v2/acts/vexaloom-labs~naver-web-blog-cafe-and-news-results-scraper/runs`, poll `GET /v2/actor-runs/{runId}` until `SUCCEEDED`, and read `GET /v2/datasets/{defaultDatasetId}/items`.

## Output

Each item is one record. Published fields include: `query`, `resultType`, `rank`, `title`, `url`, `date`, `sourceName`.

Summarise what was found, cite the record URLs when present, and say how many items came back. Do not invent values for empty fields.