News Content Extractor (Pro Version)
This is a news content extraction Skill using a client-server architecture.
Features
- - Zero Local Dependencies: Uses Node.js for the client, so no complex Python libraries need to be installed locally.
- Authentication: Core API calls are protected by
EASYALPHA_API_KEY. - High-Performance Parsing: Powered by a remote backend service based on
trafilatura.
Configuration Requirements
The following environment variables must be set to use this Skill:
- 1.
EASYALPHA_API_KEY: Your authentication token. Obtainable from: https://easyalpha.duckdns.org - INLINECODE3 : (Optional) The backend server address. Defaults to the production API: https://easyalpha.duckdns.org/api/v1/extract
Usage
User: "Scrape the content of this page: https://www.bbc.com/news/uk-12345678"
Agent Behavior:
- - Runs INLINECODE4
- The script automatically includes the Token and sends the request to the server.
- Parses and displays the results.
新闻内容提取器（专业版）
这是一个采用客户端-服务器架构的新闻内容提取技能。
功能特点
- - 零本地依赖：使用Node.js作为客户端，无需在本地安装复杂的Python库。
- 身份验证：核心API调用由EASYALPHAAPIKEY保护。
- 高性能解析：基于trafilatura的远程后端服务驱动。
配置要求
使用此技能需设置以下环境变量：
- 1. EASYALPHAAPIKEY：您的身份验证令牌。获取地址：https://easyalpha.duckdns.org
- NEWSEXTRACTORSERVER_URL：（可选）后端服务器地址。默认为生产环境API：https://easyalpha.duckdns.org/api/v1/extract
使用方法
用户：抓取此页面内容：https://www.bbc.com/news/uk-12345678
智能体行为：
- - 运行 node scripts/extract_news.js https://www.bbc.com/news/uk-12345678
- 脚本自动包含令牌并将请求发送至服务器。
- 解析并显示结果。
