Kition
Download
AI agent deep dives

Browser agent in practice: scraping Xiaohongshu into Kition

Xiaohongshu has no public API. Kition’s real Chromium browser agent logs in, scrapes content, and files it.

Kition Team·Feb 16, 2026·7 min read

First login

`browser_open https://www.xiaohongshu.com` opens a session — scan the QR with your phone once. Cookies persist; the agent reuses that login.

A scraping flow

Open xiaohongshu.com.
Search "本地优先".
For top 10 results:
  - open note
  - extract title, author, hashtags, body, like_count
  - save into Tables/xhs_notes
  - download images to Resources/xhs/<note_id>/

Heads up

  • Respect ToS — personal research is fine; scraping at scale needs legal review
  • Use Hooks to rate-limit browser tool calls
  • Don’t republish scraped content as your own
← Back to blogMore in AI agent deep dives →

Related reading

AI agent deep dives

Save any web page to your vault, in one prompt

`web_article_save` extracts the article, lands it as Markdown, files it in your vault.

Creators

A Kition + AI SOP for Xiaohongshu copy that lands

Six steps: study viral posts → extract framework → 5 titles → body → image suggestions → captions.

Ready when you are.

Kition is a local-first AI workspace. Markdown documents, structured tables, and an AI agent — running on your own machine, against the model provider you choose.

Download KitionPricing