Diffgrab

diffgrab

한국어 문서 · llms.txt

通过结构化差异跟踪网页变化。集成 markgrab + snapgrab，原生支持 MCP。

from diffgrab import DiffTracker

tracker = DiffTracker()
await tracker.track("https://example.com")
changes = await tracker.check()
for c in changes:
    if c.changed:
        print(c.summary)     # "3 lines added, 1 lines removed in sections: Introduction."
        print(c.unified_diff) # Standard unified diff output
await tracker.close()

功能

• 变化检测 — 跟踪任意 URL，通过内容哈希检测内容变化
• 结构化差异 — 统一差异 + 章节级分析（哪些标题发生了变化）
• 易读摘要 — “章节 Intro、Methods 中新增 5 行，删除 2 行”
• 快照历史 — 使用 SQLite 存储，浏览任意网页的历史版本
• 由 markgrab 提供支持 — 通过 markgrab 提取 HTML/YouTube/PDF/DOCX 内容
• 视觉差异 — 可选通过 snapgrab 比较截图
• MCP 服务 — 为 Claude Code / MCP 客户端提供 5 种工具
• 附带 CLI — diffgrab track、check、diff、history、untrack

工作原理

flowchart TD
    A["diffgrab track URL"] --> B["Fetch initial snapshot\n(markgrab + snapgrab)"]
    B --> C["Store baseline"]
    C --> D["diffgrab check"]
    D --> E["Fetch current page"]
    E --> F{"Content\nhash match?"}
    F -->|"changed"| G["Compute structured diff\n+ section analysis"]
    F -->|"unchanged"| H["No changes"]
    G --> I["📊 DiffResult\nadded / removed / modified"]

安装

pip install diffgrab

可选扩展：

pip install 'diffgrab[cli]'      # CLI with click + rich
pip install 'diffgrab[visual]'   # Visual diff with snapgrab
pip install 'diffgrab[mcp]'      # MCP server with fastmcp
pip install 'diffgrab[all]'      # Everything

使用方法

Python API

import asyncio
from diffgrab import DiffTracker

async def main():
    tracker = DiffTracker()

    # Track a URL (takes initial snapshot)
    await tracker.track("https://example.com", interval_hours=12)

    # Check for changes
    changes = await tracker.check()
    for change in changes:
        if change.changed:
            print(change.summary)
            print(change.unified_diff)

    # Get diff between specific snapshots
    result = await tracker.diff("https://example.com", before_id=1, after_id=2)

    # Browse snapshot history
    history = await tracker.history("https://example.com", count=20)

    # Stop tracking
    await tracker.untrack("https://example.com")

    await tracker.close()

asyncio.run(main())

便捷函数

from diffgrab import track, check, diff, history, untrack

await track("https://example.com")
changes = await check()
result = await diff("https://example.com")
snaps = await history("https://example.com")
await untrack("https://example.com")

CLI

# Track a URL
diffgrab track https://example.com --interval 12

# Check all tracked URLs for changes
diffgrab check

# Check a specific URL
diffgrab check https://example.com

# Show diff between snapshots
diffgrab diff https://example.com
diffgrab diff https://example.com --before 1 --after 3

# View snapshot history
diffgrab history https://example.com --count 20

# Stop tracking
diffgrab untrack https://example.com

MCP 服务

将以下内容添加到 Claude Code 的 MCP 配置中：

{
  "mcpServers": {
    "diffgrab": {
      "command": "diffgrab-mcp",
      "args": []
    }
  }
}

也可以使用 uvx：

{
  "mcpServers": {
    "diffgrab": {
      "command": "uvx",
      "args": ["--from", "diffgrab[mcp]", "diffgrab-mcp"]
    }
  }
}

MCP 工具：

工具	描述
track_url	注册要跟踪变化的 URL
check_changes	检查已跟踪的 URL 是否发生变化
get_diff	获取快照之间的结构化差异
get_history	浏览快照历史
untrack_url	停止跟踪 URL

DiffResult

每次差异操作都会返回一个 DiffResult：

@dataclass
class DiffResult:
    url: str                           # The tracked URL
    changed: bool                      # Whether content changed
    added_lines: int                   # Lines added
    removed_lines: int                 # Lines removed
    changed_sections: list[str]        # Markdown headings with changes
    unified_diff: str                  # Standard unified diff
    summary: str                       # Human-readable summary
    before_snapshot_id: int | None     # DB ID of older snapshot
    after_snapshot_id: int | None      # DB ID of newer snapshot
    before_timestamp: str              # When older snapshot was taken
    after_timestamp: str               # When newer snapshot was taken

存储

快照存储在 SQLite 数据库 ~/.local/share/diffgrab/diffgrab.db 中（自动创建）。自定义路径：

tracker = DiffTracker(db_path="/path/to/custom.db")

QuartzUnit 生态系统

软件包	用途	PyPI
markgrab	将 HTML/YouTube/PDF/DOCX 转换为 Markdown	pip install markgrab
snapgrab	将 URL 转换为截图 + 元数据	pip install snapgrab
docpick	OCR + 大模型文档提取	pip install docpick
feedkit	RSS 源收集	pip install feedkit
diffgrab	网页变化跟踪	pip install diffgrab
browsegrab	面向大模型的浏览器 Agent	即将推出

使用项目

• newswatch — RSS 新闻监控流水线（feedkit → markgrab → embgrep → diffgrab）
• watchdeck — 带视觉差异和安全防护的网页监控

许可证

MIT

---

_{属于 QuartzUnit 生态系统 — 用于数据收集、提取、搜索和 AI Agent 安全防护的可组合 Python 库。}