笔记自动化抓取工具

{
  "url": "https://example.com/article",
  "vaultPath": "/Users/yourname/Documents/Obsidian",
  "folderPath": "research/articles",
  "tags": ["ai", "research"],
  "autoTag": true,
  "autoLink": true
}

{
  "urls": [
    "https://site1.com/post",
    "https://site2.com/guide",
    "https://site3.com/tutorial"
  ],
  "vaultPath": "/Users/yourname/Documents/Obsidian",
  "bulkMode": true,
  "usePlaywright": false,
  "cache": "disk",
  "rateLimitDelay": 2000
}

{
  "url": "https://react-app.example.com",
  "vaultPath": "/Users/yourname/Documents/Obsidian",
  "usePlaywright": true,
  "enableStealth": true,
  "playwrightTimeout": 45
}

---
title: "Understanding Machine Learning"
url: https://example.com/ml-guide
scraped: 2024-01-15T10:30:00.000Z
tags: ["machine-learning", "ai", "research", "technology", "example"]
description: "A comprehensive guide to ML fundamentals"
author: "Jane Smith"
---

# Understanding Machine Learning

> 🔗 Source: [https://example.com/ml-guide](https://example.com/ml-guide)

> 📅 Scraped: January 15, 2024

---

## Article Content

Full content converted to Markdown...

---

## Metadata

- **Author:** Jane Smith
- **Description:** A comprehensive guide to ML fundamentals
- **Canonical:** https://example.com/ml-guide
- **Robots:** index,follow

---
folderPath: "research/ai-papers"
autoTag: true
autoLink: true
tags: ["ai", "paper"]
usePlaywright: false
cache: "disk"
---

# AI Paper Scraper Template

This template automatically applies settings when referenced.

{
  "url": "https://arxiv.org/abs/2401.12345",
  "vaultPath": "/path/to/vault",
  "templatePath": "templates/scraper-config"
}

// Memory cache (fast, ephemeral)
const cache = new MemoryCache({ maxSize: 100 });

// Disk cache (persistent across runs)
const cache = new PersistentCache({ cacheDir: './storage' });

// Apify KV store (cloud, for scheduled actors)
const cache = new PersistentScrapeCache('my-scrape-cache');

npm install  # Install dependencies
npm run dev  # Start MCP server with live viewer

{
  "startResultsServer": true,
  "resultsServerPort": 8080
}

# Install globally
npm install -g obsidian-mcp-actor

# Add to Claude config
{
  "mcpServers": {
    "obsidian": {
      "command": "obsidian-mcp-actor",
      "args": ["mcp-server"]
    }
  }
}

# Clone repository
git clone https://github.com/yourusername/obsidian-mcp-actor.git
cd obsidian-mcp-actor

# Install dependencies
npm install

# Run TypeScript compilation
npm run build

# Run tests
npm test

# Start MCP server locally
npm run mcp-server

obsidian-mcp-actor/
├── src/
│   ├── main.js                      # Apify Actor entry point
│   ├── mcp-server.js               # MCP server entry point
│   └── lib/
│       ├── processor/              # Core business logic
│       │   ├── UnifiedScraper.js
│       │   ├── MarkdownConverter.js
│       │   ├── TagExtractor.js
│       │   └── ActorService.js
│       ├── scraper/                # Scraping strategies
│       │   ├── CheerioStrategy.js
│       │   └── PlaywrightStrategy.js
│       ├── vault/                  # Obsidian operations
│       │   ├── NoteManager.js
│       │   └── LinkManager.js
│       ├── cache/                  # Caching implementations
│       │   ├── MemoryCache.js
│       │   ├── PersistentCache.js
│       │   └── PersistentScrapeCache.js
│       ├── utils/                  # Utilities
│       │   ├── url.js
│       │   ├── errors.js
│       │   ├── retry.js
│       │   └── stealth.js
│       └── server/                 # WebSocket server
│           └── ResultsServer.js
├── test/                           # Unit and integration tests
├── input_schema.json               # Apify input schema
├── output_schema.json              # Apify output schema
└── package.json

# Run all tests
npm test

# Run with coverage
npm run test:coverage

# Run specific test file
npm test test/UnifiedScraper.test.js

apify push

APIFY_MEMORY_MBYTES=4096
APIFY_BUILD_TIMEOUT_SECS=300

apify schedule create my-schedule \
  --actor-id your-actor-id \
  --cron "0 9 * * *" \
  --input-json '{"urls": [...], "vaultPath": "/data"}'

# Docker
docker build -t obsidian-mcp-actor .
docker run -v /path/to/vault:/data -p 8080:8080 obsidian-mcp-actor

// Old
const cache = new ScrapeCache();

// New
const cache = new MemoryCache({ maxSize: 100, ttl: 3600000 });