feishu-doc-scraper

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.

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.

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.

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.

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.