xhs-k-search

Automate Xiaohongshu search, post detail, and comment retrieval with Playwright.

8|3|Updated Apr 18, 2026
One-click install
npx skills add https://github.com/KunCheng-He/kk-ai --skill xhs-k-search
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: xhs-k-search
Source: https://github.com/KunCheng-He/kk-ai/tree/main/skills/shared/xhs-k-search
Command: npx skills add https://github.com/KunCheng-He/kk-ai --skill xhs-k-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, playwright-stealth, pydantic, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the challenge of manually searching and extracting data from Xiaohongshu (Little Red Book), enabling efficient product research, trend analysis, and content monitoring without repetitive manual browsing.

Core Features & Use Cases

  • Keyword Search: Automatically retrieve lists of posts, including titles, author details, and engagement metrics like likes, comments, and collections.
  • Deep Content Extraction: Access full post descriptions, image lists, tags, and comment threads for detailed qualitative analysis.
  • Use Case: A product manager can use this Skill to aggregate user feedback and sentiment for a specific skincare category, identifying top-performing products and common user pain points in minutes.

Quick Start

Use the xhs-k-search skill to search for the latest posts about 'mechanical keyboards' and save the results to a file.

Frequently Asked Questions about xhs-k-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scrape Xiaohongshu search results and comments automatically?

You can scrape Xiaohongshu search results and comments automatically by using Playwright-based browser automation to retrieve post lists, engagement metrics, and comment threads without manual browsing.

What is the best way to extract Xiaohongshu post details like tags and images for market research?

The best way to extract Xiaohongshu post details for market research is using browser automation that accesses full descriptions, image lists, and tags for qualitative analysis.

Does Playwright work with Xiaohongshu web scraping and anti-crawler compliance?

Yes, Playwright works with Xiaohongshu web scraping when combined with playwright-stealth to ensure robust data extraction and anti-crawler compliance during automated retrieval.

Can I reuse an existing browser session for Xiaohongshu data extraction?

Yes, you can reuse an existing browser session for Xiaohongshu data extraction by utilizing CDP-based session reuse mode alongside standalone launch options for diverse research environments.

What dependencies do I need to automate Xiaohongshu data retrieval with Python?

You need Playwright, playwright-stealth, and Pydantic as dependencies to automate Xiaohongshu data retrieval, ensuring robust extraction and structured data validation.

Why does my Xiaohongshu web scraping script get blocked during data extraction?

Your Xiaohongshu web scraping script may get blocked during data extraction if it lacks anti-crawler compliance, which requires playwright-stealth to mimic human browsing behavior.