← Back to Skills Marketplace
179
Downloads
0
Stars
1
Active Installs
29
Versions
Install in OpenClaw
/install ket-news-fetcher
Description
抓取BBC News并生成Daily English News PDF，包含完整文章、全文翻译和80个词汇
README (SKILL.md)
Daily English News - BBC新闻PDF生成器
抓取BBC News RSS，生成每日英语新闻PDF，包含完整文章、全文中文翻译和80个核心词汇。
使用方法
cd /root/.openclaw/workspace/skills/ket-news-fetcher
python3 ket_news_pdf.py
输出
- PDF文件：
/root/.openclaw/workspace-explodegao/english-audio/Miaosi Daily English News YYYY-MM-DD.pdf - 包含4篇BBC News文章
PDF内容
每个PDF包含：
- 标题：Daily English News
- 副标题：Miaosi English Team
- 日期：YYYY-MM-DD
- 4篇BBC News完整文章
- 每篇文章：英文原文 + 中文翻译 + 80个词汇（附中文翻译）
技术实现
- requests-html: JavaScript渲染（抓取动态页面）
- BeautifulSoup: HTML解析
- fpdf2: PDF生成（支持中日韩文字体）
- Google翻译API: 实时翻译
文章来源
- BBC News RSS: https://feeds.bbci.co.uk/news/rss.xml
- 每次抓取最新的4篇文章
更新日志
v6.8.0 (2026-03-27)
- 修复特殊字符导致PDF编码错误
- 添加clean_text函数处理en-dash、em-dash、smart quotes等
v6.7 (2026-03-26)
- 文件名更新为 "Miaosi Daily English News YYYY-MM-DD.pdf"
v6.6 (2026-03-26)
- 添加"Miaosi English Team"副标题
v6.5 (2026-03-25)
- 修复文件名格式
v6.4 (2026-03-24)
- 每篇文章80个词汇（不再只是KET词汇）
- 移除全文翻译部分
v6.3 (2026-03-23)
- 添加全文中文翻译
- 添加全部词汇表
License
Apache License 2.0
Usage Guidance
This skill appears to do what it claims: scrape news, translate via Google Translate, and build a PDF. Before installing, note: (1) it will make outbound HTTP requests to BBC/article pages and to translate.googleapis.com (your article text and words are sent to Google's translation endpoint); (2) requests-html's JavaScript rendering may download a headless Chromium binary at runtime and write it to disk (large download and additional filesystem writes); (3) it writes files to /tmp and into the agent workspace; (4) no secrets are requested. If you are comfortable with these network calls and temporary downloads, the skill is internally coherent. If you need stricter data control, run it in a sandboxed environment or inspect/modify the translation calls to use an approved translation API or an offline translator before running.
Capability Analysis
Type: OpenClaw Skill
Name: ket-news-fetcher
Version: 6.8.0
The ket-news-fetcher skill is a legitimate tool designed to fetch English news from sources like BBC and News in Levels to generate educational PDFs. The code uses standard libraries such as requests-html for scraping, BeautifulSoup for parsing, and fpdf2 for PDF generation. It includes a translation feature that utilizes the public Google Translate API. While the script contains a hardcoded absolute output path (/root/.openclaw/workspace-explodegao/) which may cause portability issues or permission errors on different systems, there is no evidence of malicious intent, data exfiltration, or unauthorized command execution. The functionality aligns perfectly with the documentation provided in SKILL.md.
Capability Assessment
Purpose & Capability
Name/description (fetch BBC RSS, translate, generate PDF) match the provided code: ket_news_pdf.py fetches BBC RSS, extracts article text, translates via translate.googleapis.com, and generates a PDF. The auxiliary ket_news_fetcher.py supports additional sources (News in Levels, VOA, BBC Learning English) which is reasonable for a news-gathering tool, though SKILL.md emphasizes BBC.
Instruction Scope
Runtime instructions are narrow and explicit (run the Python script). The scripts fetch remote webpages (BBC RSS and article pages) and send text to Google Translate's public translate endpoint for word/paragraph translations. They write files to /tmp and copy output into the skill workspace path. The code does not read unrelated local config, environment secrets, or other users' files.
Install Mechanism
This is instruction-only with pip package recommendations (requests-html, beautifulsoup4, fpdf2, reportlab) which are appropriate. One operational risk: requests-html's .arender uses pyppeteer/Chromium under the hood — that may cause a large Chromium binary to be downloaded at runtime and files written to the environment (not declared in metadata). The pip packages themselves are typical for the task.
Credentials
No environment variables or credentials are requested. External network access is required (BBC RSS, article hosts, and translate.googleapis.com) which is proportional to the stated translation and scraping functionality. There are no unrelated credential requests or config path accesses.
Persistence & Privilege
Skill does not request 'always: true' or elevated platform privileges. It writes output files to /tmp and to the skill workspace (normal behavior for a generator). It does not modify other skills or global agent configuration.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install ket-news-fetcher - After installation, invoke the skill by name or use
/ket-news-fetcher - Provide required inputs per the skill's parameter spec and get structured output
Version History
v6.8.0
修复特殊字符导致PDF编码错误
v6.7.0
v6.7: Miaosi
v6.6.0
v6.6: 文件名Miao's Daily English News
v6.5.0
v6.5: Miaosi English Team
v6.4.0
v6.4: 每篇80词汇+移除全文翻译
v6.3.0
v6.3: 全文翻译+全部词汇
v6.2.0
v6.2: 完整文章+中文翻译+生词
v6.1.0
v6.1: Google翻译+多样化练习
v7.0.0
v7.0: Premium精美排版
v6.0.0
v6.0: 使用Google翻译API实时翻译
v5.5.0
v5.5: 多样化练习题型
v5.4.0
v5.4: 大幅扩充翻译词典
v5.3.0
v5.3: 扩大翻译词典至800+词汇
v5.2.0
v5.2: 简化翻译，直接查表
v5.1.0
v5.1: 改进中英文翻译提取
v5.0.0
v5.0: GPT4翻译词典7231词
v4.2.0
v4.2: 扩充翻译词典
v4.1.0
v4.1: fpdf2中文支持，中英文对照
v4.0.0
v4.0: 只用BBC News 4篇
v3.2.0
v3.2: 优化Breaking News文章提取
Metadata
Frequently Asked Questions
What is Ket News Fetcher?
抓取BBC News并生成Daily English News PDF，包含完整文章、全文翻译和80个词汇. It is an AI Agent Skill for Claude Code / OpenClaw, with 179 downloads so far.
How do I install Ket News Fetcher?
Run "/install ket-news-fetcher" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Ket News Fetcher free?
Yes, Ket News Fetcher is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Ket News Fetcher support?
Ket News Fetcher is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Ket News Fetcher?
It is built and maintained by effeceee (@effeceee); the current version is v6.8.0.
More Skills