Xiaohongshu Session Reader
Apps & Automationxiaohongshu-session-readerXiaohongshu Session Reader is an Agent Skill for apps & automation published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use this skill to read Xiaohongshu (小红书) via HTTP/API first with local logged-in Chrome cookies, and only use Playwright as fallback. Supports profile card extraction, note detail extraction, and conditional comment fallback when API is blocked.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/integration/xiaohongshu-session-reader-codingsamss-all-my-ai-needs/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/xiaohongshu-session-reader, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Xiaohongshu Session Reader
Scope
- Reuse local Chrome logged-in session only.
- Prefer HTTP/API extraction for stability and speed.
- Use Playwright only when HTTP/API path is blocked (captcha / risk control).
- Support:
- profile card titles (for 谁是卧底词组 collection)
- note detail (title/desc/author)
- comments when API permits; otherwise explicit fallback signal
- Do not forge identity, bypass captcha, or brute-force anti-bot checks.
Prerequisite Check
Before extraction:
python3 --version
Fallback-only prerequisite:
codex mcp get playwright-ext
Workflow
- Run HTTP-first reader:
python3 <skill_dir>/scripts/xhs_http_reader.py \
--url "<xhslink_or_xiaohongshu_url>" \
--mode auto \
--max-items 40 \
--max-comments 20 \
--pretty
- If response has
fallback.required=false, use returned data directly. - If response has
fallback.required=true, switch to Playwright fallback:- profile: open profile page and read visible card titles.
- note comments: open note detail and read comments from DOM snapshot.
- Normalize four-word groups with
scripts/undercover_parser.py. - Persist progress in
.cache/xhs_undercover_progress.jsonfor batch tasks.
Block Handling Rules
- If HTTP returns captcha or risk code (for example
300011), do not keep retrying aggressively. - Degrade once to Playwright fallback and continue extraction.
- If Playwright also lands on captcha/login gate, request user to refresh local login session.
- Never claim detail/comments were obtained via HTTP when response marks fallback required.
Output Contract
Use this structure:
{
"source": "<xhs link>",
"captured_at": "YYYY-MM-DD",
"groups": [
{ "id": 1, "words": ["词A", "词B", "词B", "词B"], "odd": "词A" }
]
}
If confidence is low, add note for manual verification.
Resources
- HTTP-first reader:
scripts/xhs_http_reader.py - Cookie exporter (fallback tooling):
scripts/export_xhs_cookies.py - DOM fallback reference:
references/extraction-checklist.md - Group parser:
scripts/undercover_parser.py