news-content-extractor
输入新闻 URL,通过远程 API 高效提取网页的正文、标题、作者和时间。
Why use this skill?
Extract clean text, titles, and authors from any news URL using this efficient OpenClaw skill. Zero local dependencies, high-speed API.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/fonilye/news-contentWhat This Skill Does
The news-content-extractor is a professional-grade OpenClaw skill designed to streamline the process of gathering textual information from the web. Unlike traditional scrapers that require heavy local dependencies or complex browser emulation, this skill leverages a high-performance remote backend powered by the renowned trafilatura library. It automatically strips away navigation bars, advertisements, footer clutter, and tracking scripts, providing the OpenClaw agent with clean, readable, and structured text including the title, original author, publication timestamp, and core content body. By utilizing an API-driven architecture, it ensures that your agent remains lightweight while maintaining the ability to process dynamic news URLs across various domains reliably.
Installation
To install this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/fonilye/news-content
Once installed, you must configure your environment variables to ensure proper authentication and connectivity. Set EASYALPHA_API_KEY to your assigned token. If you are using a custom instance, define NEWS_EXTRACTOR_SERVER_URL; otherwise, the system will default to the provided testing environment. No additional Python libraries are required on your host machine as all heavy lifting is performed remotely.
Use Cases
This skill is ideal for AI agents performing:
- Research Synthesis: Aggregating articles for daily news briefings or industry intelligence reports.
- Content Monitoring: Automatically tracking developments in specific domains by scraping URLs provided by the user.
- Archive Creation: Converting live, ad-heavy web pages into clean, portable text formats for offline reading or storage.
- Data Pre-processing: Preparing unstructured web data for summarization or sentiment analysis tasks.
Example Prompts
- "抓取这个网页的内容:https://www.bbc.com/news/uk-12345678"
- "解析下面这个新闻地址,只保留正文内容并列出作者:https://techcrunch.com/2023/10/example-article"
- "帮我阅读这个科技新闻链接,总结它的主要观点和发布时间:https://www.theverge.com/example"
Tips & Limitations
- Authentication: Always keep your
EASYALPHA_API_KEYsecure. Do not share the config file containing this key in public repositories. - Error Handling: While the skill handles most standard article layouts, pages heavily protected by JavaScript rendering or sophisticated anti-scraping measures (like Cloudflare challenges) may occasionally fail. If a URL returns no content, try verifying the URL is directly accessible.
- Rate Limiting: Be mindful of your API quota. Rapid-fire requests to the same domain might be flagged by the source website; use this skill responsibly to avoid being blocked by publishers.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-fonilye-news-content": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api, code-execution