# Korean Web Reader (kr-reader)

> Korean Web Reader (kr-reader) is a paid API for AI agents from x402.pokt-agent.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-12).

Fetches and extracts clean text content from Korean web pages and news sources, returning structured metadata including title, author, publication date, and article text.

## Facts

- Endpoint: POST https://x402.pokt-agent.com/kr-reader/read?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/korean-web-reader-kr-reader-e765ea25
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_e6Cej8DjmdV4XQM7D2l-J

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability korean-web-reader-kr-reader-e765ea25 -d '<json body>'
```

Example prompt: Fetch and extract the full text from this Naver News article — https://n.news.naver.com/article/001/0014123456 — and give me the title, author, publication date, and up to 3000 characters of content.

## When to prefer this

Use this endpoint when you need to extract readable text and metadata from Korean web pages or news articles without setting up browser automation or a scraping infrastructure. It is purpose-built for Korean content sources (Naver, Daum, Hankyung, etc.) and understands their structure. Prefer it over generic scrapers when Korean-language content fidelity and structured metadata (author, date, title) matter. The pay-per-call x402 model means no API key setup is required.

## Known failure modes

- URL is behind a paywall or login — returns error status
- Page uses heavy JavaScript rendering not supported by the reader — partial or empty text
- URL is not a Korean-language page — may return garbled or empty content
- Invalid or malformed URL input — 400-level error
- max_chars too small — truncates content aggressively, may cut mid-sentence
- Site structure changed — metadata fields like author or date may return null

## How this service works

Pay-per-call Korean company due diligence, company ID crosswalk, sanctions screening with Korean name variants, Upbit/Bithumb risk events, HWP to Markdown, business status, business-day calendar, address normalisation, law, rates, filings and more. No account or API key: pay each call in USDC on Base via x402.

## Output

Returns a JSON object containing the site name (e.g. 'naver_news'), extracted plain text of the article body, character count, article title, author name, HTTP-style status ('OK' or error), and ISO 8601 publication timestamp with Korean timezone offset.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string"
  },
  "max_chars": {
   "type": "integer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "site": "naver_news",
  "text": "…",
  "chars": 2389,
  "title": "…",
  "author": "연합뉴스",
  "status": "OK",
  "published": "2026-10-10T09:12:00+09:00"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/korean-web-reader-kr-reader-e765ea25/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.pokt-agent.com](https://www.zero.xyz/host/x402.pokt-agent.com/llms.txt)