Automate Zhihu content retrieval and parsing via Playwright browser automation.
npx skills add https://github.com/KunCheng-He/kk-ai --skill zhihu-k-search
Please help me install this Agent Skill. Skill: zhihu-k-search Source: https://github.com/KunCheng-He/kk-ai/tree/main/skills/shared/zhihu-k-search Command: npx skills add https://github.com/KunCheng-He/kk-ai --skill zhihu-k-search
This Skill solves the challenge of manually navigating and scraping high-quality, community-driven content from Zhihu, allowing you to quickly gather insights for research, product analysis, or competitive intelligence.
Use the zhihu-k-search skill to search for the latest discussions on the topic of artificial intelligence and save the results to a file.
High-intent search queries and answers about installing and using this skill.
Automate Zhihu data extraction by using Playwright browser automation to retrieve questions, answers, and articles, converting complex HTML into clean Markdown or JSON output for research workflows.
Scrape Zhihu articles and answers reliably by leveraging playwright-stealth for session persistence and API interception with DOM-based fallback mechanisms to ensure robust data collection.
Yes, this Zhihu web scraping tool supports targeted search queries to extract detailed question-answer pairs, user profiles, and article content, enabling comprehensive product surveys and competitive intelligence.
Convert scraped Zhihu HTML into structured Markdown or JSON by using automated browser scripts that parse complex DOM structures, delivering clean readable output for easy integration into analytical reports.
Web scraping Zhihu can fail when dynamic DOM elements change, but API interception with DOM-based fallback mechanisms captures data directly from network requests to ensure reliable retrieval.
Yes, you need Playwright and playwright-stealth installed because the automated Zhihu search scripts rely on browser automation to execute session persistence and retrieve community-generated content.
KunCheng-HeAutomate Xiaohongshu search, post detail, and comment retrieval with Playwright.
yangliu2060Collect company profiles, pricing data, and user reviews into a markdown competitive analysis report.
handsomelong922Extract and validate LLM responses into Pydantic schemas with automatic retries.
kevinnftExtract structured data from static HTML, JS-rendered pages, and hybrid sites.
