headless-scraping

Extracts web content from Xiaohongshu and Zhihu via headless browsers for AI analysis.

56|4|Updated Oct 29, 2025
One-click install
npx skills add https://github.com/MimicHunterZ/PocketMind --skill headless-scraping
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: headless-scraping
Source: https://github.com/MimicHunterZ/PocketMind/tree/main/.claude/skills/headless-scraping
Command: npx skills add https://github.com/MimicHunterZ/PocketMind --skill headless-scraping

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of capturing content from various web platforms like Xiaohongshu and Zhihu, even from within other apps, and prepares it for AI-driven summarization and Q&A.

Core Features & Use Cases

  • Effortless Sharing: Share content from any app directly to PocketMind via the share sheet.
  • Intelligent Scraping: Utilizes headless browsers and platform-specific strategies to extract rich content (text, images, metadata).
  • AI Integration: Enables AI summarization and question-answering on the scraped content.
  • Use Case: When you find an interesting Xiaohongshu post, share it to PocketMind. The Skill will automatically scrape the content, and you can later ask an AI to summarize it or answer questions about it.

Quick Start

Share the current article URL to the headless-scraping skill.

Frequently Asked Questions about headless-scraping

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

FAQPage Schema
How do I scrape Xiaohongshu content for AI analysis?

To scrape Xiaohongshu content for AI analysis, share the post URL directly from the app; the skill uses a headless browser and platform-specific logic to extract rich text and images for summarization.

Can I extract web content from Zhihu using a headless browser?

Yes, you can extract web content from Zhihu using a headless browser by sharing the article link, which triggers platform-specific scraping logic to capture the text for AI processing.

How do I scrape articles from other apps into a Flutter application?

You can scrape articles from other apps into a Flutter application by using the share sheet to send the URL, which launches a foreground service to execute background scraping and content extraction.

Does headless scraping handle cookie management for platform-specific content extraction?

Yes, headless scraping handles cookie management for platform-specific content extraction, ensuring reliable access to platforms like Xiaohongshu and Zhihu during the automated scraping process.

What is the best way to automate web scraping for AI summarization?

The best way to automate web scraping for AI summarization is sharing a URL to trigger a headless browser, which extracts the content and prepares it for immediate AI-driven question-answering.

Why does background scraping need a foreground service on mobile platforms?

Background scraping needs a foreground service on mobile platforms to maintain the headless browser execution alive, ensuring uninterrupted content extraction and cookie management when the app runs in the background.