Feishu Doc Scraper
Extract Feishu (Lark) Docs, Wiki collections, spreadsheets, and Minutes transcripts into faithful local Markdown via lark-cli — no LLM rewriting of the body.
Feishu content is trapped behind a proprietary viewer, and copy-paste mangles tables and structure. This playbook extracts it faithfully to Markdown you own.
Who it's for: knowledge workers, PKM builders, researchers, documentation teams
Example
"Convert this Feishu wiki collection to Markdown" → Faithful per-page Markdown following the collection's reference graph, tables intact
CLAUDE.md Template
New here? 3-minute setup guide → | Already set up? Copy the template below.
npx ccplaybooks add feishu-doc-scraper# Feishu Doc Scraper
Extract a Feishu/Lark source into faithful local Markdown. **Prefer the lark-cli API** — it extracts the body programmatically (no model paraphrasing), follows a collection's reference graph, and reads permission boundaries from error codes instead of guessing. Treat the rendered browser page as a *fallback*, not the source of truth: in real collection-scraping work the API path consistently does the whole job while the browser path is never needed.
## Scope (read this first)
This skill's contract is **faithful per-source Markdown + a record of what was extracted**. It does *not* decide how the resulting files are named, indexed, deduplicated against existing notes, or organized into a knowledge base — that belongs to the host PKM / the user's own conventions. Stopping at faithful extraction keeps this skill orthogonal and reusable. When the user wants the output filed into a vault, extract first, then hand the clean Markdown to their organizing workflow.
## Choose the path
```
Is the source a Feishu/Lark URL (wiki / docx / sheets / minutes / base)?Get new playbooks like this one
One email a week with new Claude Code workflows. Free, like everything here.
No spam. Unsubscribe anytime.
What This Does
Extract Feishu (Lark) Docs, Wiki collections, spreadsheets, and Minutes transcripts into faithful local Markdown via lark-cli — no LLM rewriting of the body.
What's Inside
The template covers:
- Scope (read this first)
- Choose the path
- Path A — lark-cli API extraction (primary)
- Path B — permission denied → owner-exported .docx
- Path C — Feishu Minutes (妙记) transcript
- Path D — browser DOM fallback (last resort)
Quick Start
Step 1: Create a Project Folder
Make a dedicated folder for this workflow and open it in Claude Code.
Step 2: Download the Template
Click Download above to save the template, then drop it into your project as CLAUDE.md (or paste it into your existing one).
Step 3: Start Working
Tell Claude what you need in plain language — it will follow the template's workflow automatically. For example:
Convert this Feishu wiki collection to Markdown
Claude reads the template and runs the steps for you.