feishu-content-extraction

Name: feishu-content-extraction
Availability: InStock
Author: rnben

Extract Feishu article content from embedded JSON via curl.

1|Updated Apr 18, 2026

Search Tags:#curl #web-scraping #blog-content #summarize #feishu #json-parse #richtext

Ready to run

npx skills add https://github.com/rnben/hermes-skills --skill feishu-content-extraction

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: feishu-content-extraction
Source: https://github.com/rnben/hermes-skills/tree/main/plugins/productivity-skills/skills/feishu-content-extraction
Command: npx skills add https://github.com/rnben/hermes-skills --skill feishu-content-extraction

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Feishu/Hera blog articles render content via JS; when the browser tool times out, this skill enables extraction and parsing of the article content.

Core Features & Use Cases

Curl fetches the Feishu article HTML and retrieves embedded JSON structures (window._defaultTemplateValue and window._templateValue) to access text and rich content.
Parses plain text and Quill delta content to assemble a coherent summary and key metadata (title, description, keywords).
Use Case: Convert a Feishu article URL into a structured summary for knowledge bases, newsletters, or CMS imports.

Quick Start

Provide a Feishu article URL to have the tool fetch the page, extract embedded JSON, and output a concise summary.

Frequently Asked Questions about feishu-content-extraction

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

FAQPage Schema

How do I extract Feishu blog content when the browser tool times out?▼

To extract Feishu blog content when the browser times out, you can use curl to fetch the article HTML and parse the embedded JSON structures in window._defaultTemplateValue and window._templateValue. This skill retrieves the text and rich content directly from the page source without relying on browser rendering.

What is the best way to parse Quill delta content from a Feishu article URL?▼

The best way to parse Quill delta content from a Feishu article is to fetch the page via curl, extract the embedded JSON data structures, and assemble the rich text components into a coherent summary. This approach bypasses JavaScript rendering issues by accessing the raw data directly.

How does curl fetch structured JSON from Feishu articles for summarization?▼

Curl fetches structured JSON from Feishu articles by retrieving the raw HTML document and reading the specific embedded JavaScript variables, window._defaultTemplateValue and window._templateValue. This allows direct access to the article's plain text and rich content for summarization.

Can I convert a Feishu article URL into a structured summary for a knowledge base?▼

Yes, you can convert a Feishu article URL into a structured summary suitable for knowledge bases. The skill parses the extracted JSON and Quill delta content to assemble key metadata, including the title, description, and keywords, for CMS imports or newsletters.

Why does web scraping fail to retrieve text from JS-rendered Feishu blog pages?▼

Web scraping fails to retrieve text from JS-rendered Feishu pages because standard tools often wait for browser execution to time out. This skill avoids that by using curl to fetch the static HTML and directly extracting the embedded JSON structures containing the pre-rendered content.