feishu-doc-scraper

{
  "name": "feishu-doc-scraper",
  "description": "Extract Feishu (Lark) Docs, Wiki pages, Wiki collections/hubs, spreadsheets (including cell-attachment file download), and Minutes (妙记) transcripts into clean high-fidelity local Markdown. The primary path is the lark-cli API — programmatic extraction with no LLM rewriting of the body — which recursively follows a collection's reference graph (mention-doc / sheet / cross-tenant links) and uses error codes to resolve permission boundaries precisely; a browser-DOM path is the fallback only when lark-cli cannot reach the content. Use this whenever the source is a Feishu/Lark URL and fidelity matters — including 导出飞书文档/合集/妙记转写, 把飞书 wiki/知识库转 markdown, scraping or archiving a Feishu collection, exporting a Feishu Minutes/妙记 transcript, or saving a Feishu page locally — even if the user only says clipping, archiving, converting, or \"save this\". Also covers the permission-denied path (owner-exported .docx → faithful Markdown with heading/highlight restoration).",
  "source": "./feishu-doc-scraper",
  "strict": false,
  "version": "1.4.0",
  "category": "productivity",
  "keywords": [
    "feishu",
    "lark",
    "lark-cli",
    "markdown",
    "wiki",
    "minutes",
    "transcript",
    "collection",
    "api",
    "docx",
    "scraping",
    "browser",
    "archival"
  ]
}