feishu-doc-scraper

Extract Feishu/Lark documents into Markdown via lark-cli API with browser DOM fallback.

4|Updated May 23, 2026

Search Tags:#data scraping #Markdown conversion #Feishu #Lark #document extraction

Ready to run

npx skills add https://github.com/791994545/Deepseek-Reasonix-Autopilot --skill feishu-doc-scraper

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: feishu-doc-scraper
Source: https://github.com/791994545/Deepseek-Reasonix-Autopilot/tree/main/skills/feishu-doc-scraper
Command: npx skills add https://github.com/791994545/Deepseek-Reasonix-Autopilot --skill feishu-doc-scraper

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires lark-cli, python-docx, pandas, requests, browser_cookie3, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of extracting and converting Feishu/Lark documents, including Docs, Wiki pages, Wiki collections/hubs, spreadsheets, and Minutes transcripts, into clean and high-fidelity local Markdown files.

Core Features & Use Cases

Document Extraction: Extracts Feishu/Lark documents into Markdown format with full fidelity.
API-Based Extraction: Utilizes the lark-cli API for programmatic extraction without LLM rewriting, ensuring high fidelity and accurate extraction.
Fallback to Browser DOM: When the lark-cli API is not accessible, falls back to a browser-based DOM extraction method.
Permission Handling: Handles permission-denied paths by converting owner-exported .docx files to Markdown.

Quick Start

Use the feishu-doc-scraper skill to extract a Feishu document:

feishu-doc-scraper [feishu-url-or-output-path]

Frequently Asked Questions about feishu-doc-scraper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I convert Feishu documents to Markdown format locally?▼

To convert Feishu documents to Markdown, this Skill utilizes the lark-cli API for programmatic extraction without LLM rewriting, ensuring high fidelity and accurate text extraction. It processes Docs, Wiki pages, spreadsheets, and Minutes transcripts into clean local Markdown files.

How does browser DOM extraction work for Lark documents?▼

Browser DOM extraction works for Lark documents as a fallback mechanism when the lark-cli API is not accessible. It scrapes the document content directly from the browser interface to ensure extraction succeeds even if API permissions are restricted.

Do I need lark-cli to extract Feishu Wiki pages and spreadsheets?▼

You need lark-cli to extract Feishu Wiki pages and spreadsheets via the primary API method. However, if the API is inaccessible, the Skill falls back to browser DOM extraction or converts owner-exported docx files using pandas and python-docx.

What is the best way to extract Lark Minutes transcripts to Markdown?▼

The best way to extract Lark Minutes transcripts to Markdown is using the lark-cli API for full fidelity conversion. This approach avoids LLM rewriting and accurately captures structured data directly into clean local files.

How do I handle permission-denied errors when scraping Feishu documents?▼

To handle permission-denied errors when scraping Feishu documents, the Skill converts owner-exported .docx files to Markdown. This bypasses API restrictions by utilizing python-docx and pandas to process locally exported files.