Korean Web Reader: Naver Blog & News to Clean Text avatar

Korean Web Reader: Naver Blog & News to Clean Text

Pricing

from $4.00 / 1,000 page reads

Try for free
Go to Apify Store
Korean Web Reader: Naver Blog & News to Clean Text

Korean Web Reader: Naver Blog & News to Clean Text

Try for free

Read Korean web pages as clean text: Naver Blog posts (inside the iframe), Naver News and Daum News articles and generic pages, returned as title, author, published date, paragraphs, images and links. Deterministic extraction, no LLM. Pay only for pages read.

Pricing

from $4.00 / 1,000 page reads

Rating

0.0

(0)

Developer

Seung-yeop Chun

Seung-yeop Chun

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

11 days ago

Last modified

Categories

Share

Give it Korean page URLs and get clean, structured text back. Use it to feed RAG, translation, monitoring or analysis.

SiteWhat is handled
Naver Blog (blog.naver.com, m.blog.naver.com)The post body inside Naver's iframe, title, author, date, images
Naver News (n.news.naver.com)Article body, press name, published time
Daum News (v.daum.net)Article body, press name, published time
Other public pagesMain text by readability-style extraction
Naver CafeReported as UNSUPPORTED (login wall), not charged

Extraction is deterministic: no LLM, so the same page gives the same text.

Output

One row per URL:

{
  "url": "https://n.news.naver.com/article/001/0016369438",
  "site": "naver_news",
  "status": "OK",
  "title": "...",
  "author": "연합뉴스",
  "published": "2026-10-10T09:12:00+09:00",
  "text": "...",
  "chars": 2389,
  "images": ["..."],
  "links": ["..."],
  "billed": true
}

status is one of these:

  • OK (charged)
  • UNSUPPORTED, NOT_FOUND, FETCH_FAILED or BAD_INPUT (not charged)

Pricing

Pay per event: $0.004 per page read with status OK. Every other status is free.

Free Apify plan: at most 10 pages per run.

Limits and notes

  • Public pages only. The Actor does not log in, bypass paywalls or read Naver Cafe.
  • You are responsible for how you use the text; respect the original authors' copyright.
  • Pages over 3 MB or slower than about 30 seconds return FETCH_FAILED.
  • The same reader is also sold per call over x402 (USDC on Base): https://x402.pokt-agent.com/
  • Questions or bugs: hello@pokt-agent.com

You might also like

Web Crawler & Semantic Schema-Enhanced Extractor avatar

Web Crawler & Semantic Schema-Enhanced Extractor

devil_port369-owner/web-crawler

Depth-controlled web crawler that transforms websites into structured analytics-ready data. Starting from one or more URLs, it crawls internal links up to a configurable depth and outputs detailed JSON records per page

User avatar

DataFusionX

45

5.0

(8)

NB

Naver Blog Scraper - Clean Content & Review Intelligence

hanpro/naver-blog-scraper

Scrapes titles of websites using Crawlee and BeautifulSoup.The only Naver Blog scraper that properly extracts clean content from Naver's iframe architecture. Sponsor detection, metadata, engagement stats, and Google Sheets integration.

User avatar

한프로

30

KR

Korean Real-time News MCP Server

lurid_alley/noos-korean-news-mcp

MCP server for searching real-time Korean news from 54 major media outlets. Search by keyword, get trending articles, and view news statistics — all via MCP tools. Updated every minute.

User avatar

Indo Yoon

4

Ai Ready Web Page To Markdown Converter avatar

Ai Ready Web Page To Markdown Converter

mustafa.irshaid.113/ai-ready-web-page-to-markdown-converter

Convert any webpage into structured Markdown and HTML using just a URL. Get the page title, link, and content—perfect for SEO, devs, and AI crawlers. Fast, clean, and ideal for repurposing or analysis. Start turning websites into Markdown instantly.

User avatar

Mustafa Irshaid

16

Website Content Crawler — Markdown for LLM & RAG avatar

Website Content Crawler — Markdown for LLM & RAG

brilliant_gum/web-content-crawler

Deep-crawl websites and extract LLM-ready Markdown with OG tags, JSON-LD, author, dates, token estimates, native RAG chunking, language filtering, content-hash dedup, and per-page error reporting. Enforced timeouts. Zero silent failures.

User avatar

Yuliia Kulakova

24

Web Page to Markdown & Text - URL Reader for LLMs & RAG avatar

Web Page to Markdown & Text - URL Reader for LLMs & RAG

entranced_gelato/ai-web-page-reader

Read any web page as clean text + Markdown for LLMs and automations. Strips ads, nav, and scripts; returns the main content, metadata (title, author, date, word count), and an optional AI TL;DR + key points. The web-reading primitive for AI agents, RAG pipelines, and no-code flows.

User avatar

AIDevs

5

RF

RSS Feed Reader — Blogs, News, Podcasts & YouTube

hichemdev/rss-feed-reader

Read and monitor any RSS or Atom feed into clean structured items: title, link, author, date, categories, summary and media. Works for blogs, news, podcasts and YouTube channels.

User avatar

Hichem Ben Moussa

3

WT

Web to LLM Spanish — RAG-ready content extractor

fanciful_geode/web-to-llm-es

Crawls Spanish-language websites and extracts clean markdown content optimized for LLM RAG pipelines. Handles Spanish character encoding, removes boilerplate, and outputs structured chunks ready for embedding.

User avatar

Ernesto de Armas

3

Naver News Scraper — Korean News & Headlines avatar

Naver News Scraper — Korean News & Headlines

huggable_quote/naver-news-scraper

Scrape Korean news from Naver News, Korea's #1 news platform with 30M+ daily users. Search by keyword, filter by date, get article titles, sources, links and summaries. No API key needed. From the maker of Naver Map Scraper.

User avatar

OrbitData Labs

17

Naver Place Review Scraper (한국어) avatar

Naver Place Review Scraper (한국어)

parsebird/naver-place-review-scraper-korean

네이버 플레이스 리뷰 추출: 방문자 리뷰 본문, 별점, 방문일, 방문자 선택 키워드, 사장님 답글, 사진, 네이버 블로그 리뷰까지. JSON, CSV, Excel로 내보내기.

User avatar

ParseBird

7