web-scraper
Web Scraper (Crawl4AI)
基于 Crawl4AI 的高性能网页爬虫。Crawl4AI 是 2025 年 GitHub #1 Trending 项目(59k+ Stars),专为 AI Agent 和 LLM 设计。
核心优势
| 特性 | 说明 |
|---|---|
| 🏆 业界标杆 | 59k+ GitHub Stars,Apache-2.0 开源 |
| 💰 完全免费 | 无需任何 API Key |
| 🛡️ 强反爬 | Playwright 浏览器引擎 + stealth 模式 + 随机 UA |
| 🚀 极速 | 异步并发 + 内存自适应调度,比替代方案快 6x |
| 🎯 LLM 优化 | 自动输出干净 Markdown,适合 RAG 和 LLM 消费 |
| 📄 动态页面 | 支持 JavaScript 渲染、无限滚动、SPA |
| 🔧 智能提取 | PruningContentFilter 自动去除噪声内容 |
使用场景
More from malue-ai/dazee-small
pywinauto
Automate Windows desktop applications using pywinauto. Discover windows, inspect controls, click buttons, type text, and drive any Win32/UIA application programmatically.
369app-recommender
Recommend the best application for a user task based on installed apps (from app-scanner) and common software knowledge.
17excel-fixer
Auto-detect and fix common Excel formatting issues like merged cells, inconsistent types, duplicate headers, and encoding problems.
15eightctl
Control Eight Sleep pods (status, temperature, alarms, schedules).
14gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
14bluebubbles
Build or update the BlueBubbles external channel plugin for Moltbot (extension package, REST send/probe, webhook inbound).
13