Chinese to Markdown｜微信公众号 / 头条 / 新浪 / 知乎 → RAG-ready MD

Turn Chinese articles into clean, LLM-ready Markdown with metadata. Paste URLs from WeChat Official Accounts (微信公众号), Toutiao (今日头条), Sina (新浪) and Zhihu (知乎) — ads, sidebars, follow-me footers and QR codes stripped.

Built for RAG pipelines, LLM datasets and AI agents. Pure HTTP — no headless browser. Charged only on success.

把中文网页文章转成干净 Markdown（去广告/侧栏/关注文案/二维码），面向 RAG 知识库、数据集、AI 智能体。纯 HTTP，失败不计费。

Positioning: This Actor is for known article URLs you already have. It does not search WeChat accounts or scrape full history lists (that’s a different product category).

Supported sites｜支持站点

Site	Status	Notes
WeChat 公众号 (mp.weixin.qq.com)	✅	Author/account cleaned; footer/QR removed; images kept
Sina 新浪	✅	Main body only
Toutiao 今日头条	⚠️ Limited	Text OK; videos / 微头条 / deleted no; signed image URLs expire
Zhihu 知乎专栏	⚠️ Limited	Some work; many blocked
Douban 豆瓣	❌	Error row; not charged

Use cases｜用例

• RAG / knowledge bases — feed 公众号 & news into vector DBs（optional built-in chunking）
• AI agents / MCP tools — “read this Chinese URL as Markdown”
• LLM datasets — Chinese corpora with source fields
• Brand & media monitoring in China（when you already have links）

Why this Actor｜对比（诚实）

	This Actor	zen-studio WeChat scraper（品类头部）	technicaldost wechat→MD
Primary job	URL → clean Markdown（+ optional chunks）	Account search / history / read counts	WeChat → MD（+ optional Sogou discovery）
Sites	公众号 + 头条 + 新浪 + 知乎	WeChat-focused acquisition	WeChat-focused
Price (public)	$0.002/success article（~$2/1k）	Higher PPE on search/history events	~$0.005/item class
Failures	Error row, $0	—	—
Best when	You already have links for RAG	You need to discover articles	WeChat-only MD

We don’t claim #1 for 公众号 search — we claim cheap, clean MD for known URLs.

Pricing｜定价（与线上一致）

Event	Price
article-extracted	$0.002 / successful article
article-chunked	$0.003 / successful article（instead of extracted; per article, not per chunk）
Failed / blocked / unsupported	$0
apify-actor-start	≈ $0.00005 / run

Input｜输入

Field	Required	Description
startUrls	yes	Article URLs
outputFormat	no	markdown | json | jsonl
maxConcurrency	no	default 5
chunking	no	default false
chunkSize / chunkOverlap	no	512 / 64（cl100k）

Output example

{
  "inputUrl": "https://mp.weixin.qq.com/s/...",
  "title": "...",
  "author": "量子位",
  "date": "2025-05-18",
  "word_count": 3804,
  "markdown": "# ...\\n\\n..."
}

Failed: { "inputUrl": "...", "error": "...", "status": "..." } — not charged.

RAG chunking｜切块

chunking: true → token-based chunks（heading → paragraph → sentence）, OpenAI-compatible cl100k, overlap only within the same section. Also writes RESULTS.jsonl to the key-value store.

Agents / MCP

Use as an agent tool: input URL list → Markdown / chunk rows. Enable Apify Agents category + Console MCP block. Prompt tip: “Convert these 公众号 URLs to Markdown chunks for embedding.”

FAQ

Q: Can it search a 公众号 and list all history?
A: No. Paste article URLs you already have. For discovery, use a WeChat search/history Actor.

Q: Why did Zhihu / Toutiao fail?
A: Anti-bot / limited support. You get an error row and pay $0.

Q: Does chunking cost more per chunk?
A: No — $0.003 per successfully chunked article, regardless of chunkSize.

Q: Browser / login?
A: Pure HTTP, public pages only.

Notes｜注意

Public pages only. WeChat verification pages: one automatic retry; still failing → free. Lower concurrency if rate-limited. Respect source ToS & copyright.

You might also like｜同矩阵

• Web to Markdown Extractor (RapidAPI) — same Chinese-first MD idea as an HTTP API
• YouTube Transcript｜字幕→MD
• Bilibili Scraper
• Weibo Snapshot