SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsnews

news

Writing & research

View repository

Updated 10-15 20:28

About this skill

News and Information Queries

Fetch Chinese news and global AI information via RSS feeds and web scraping, supporting multiple categories and keyword filtering.

No configuration required

This skill works out of the box and requires no API Key.

Command-line invocation

# 获取热点新闻（默认）
python skills/news/scripts/news.py hot

# AI新闻资讯查询
python skills/news/scripts/news.py category --cat ai --limit 20
Query by category

python skills/news/scripts/news.py category --cat tech python skills/news/scripts/news.py category --cat finance python skills/news/scripts/news.py category --cat ai python skills/news/scripts/news.py category --cat ai-community

Keyword search

python skills/news/scripts/news.py hot --keyword AI python skills/news/scripts/news.py category --cat ai --keyword GPT

Control summary length (default 100 characters)

python skills/news/scripts/news.py category --cat ai --detail 500 # show 500-character summary python skills/news/scripts/news.py category --cat ai --detail -1 # show full text python skills/news/scripts/news.py category --cat ai --detail 0 # do not show summary

Specify the number of returned items

python skills/news/scripts/news.py hot --limit 20

JSON format output (includes the full body, not truncated)

python skills/news/scripts/news.py hot --json

View all supported categories and sources

python skills/news/scripts/news.py sources


## 支持的新闻分类

### 中文新闻

| 分类 | 参数值 | 来源 |
|------|--------|------|
| 热点要闻 | `hot` | 人民网、新华网、澎湃新闻 |
| 时政 | `politics` | 人民网时政、新华网政务 |
| 财经 | `finance` | 新浪财经、东方财富 |
| 科技 | `tech` | 36氪、IT之家 |
| 社会 | `society` | 中国新闻网、澎湃新闻 |
| 国际 | `world` | 环球网、参考消息 |
| 体育 | `sports` | 新浪体育、虎扑 |
| 娱乐 | `entertainment` | 新浪娱乐 |

### AI 技术与资讯

| 分类 | 参数值 | 来源 |
|------|--------|------|
| AI 技术 | `ai` | MIT Tech Review、OpenAI Blog、Google AI Blog、DeepMind Blog、Latent Space、Interconnects、One Useful Thing、KDnuggets |
| AI 社区 | `ai-community` | AI News Daily、Sebastian Raschka、Hacker News、Product Hunt |

AI 源说明：

- MIT Technology Review — MIT 科技评论，AI 与前沿技术深度报道
- OpenAI Blog — OpenAI 官方博客，模型发布与研究动态
- Google AI Blog — Google AI 研究与产品更新
- DeepMind Blog — DeepMind 研究进展
- Latent Space — AI 工程师社区播客与文章
- Interconnects — Nathan Lambert 的 AI 技术深度分析
- One Useful Thing — Ethan Mollick 的 AI 实践应用分享
- KDnuggets — AI/ML 技术文章聚合
- AI News Daily — AI 行业每日新闻汇总
- Sebastian Raschka — 机器学习深度技术博客
- Hacker News — 科技新闻与讨论社区
- Product Hunt — 新产品发现平台（含 AI 产品）

## AI 调用场景

用户说"今天有什么新闻"：

```bash
python skills/news/scripts/news.py hot --limit 10

User says "What's new in AI recently":

python skills/news/scripts/news.py category --cat ai --limit 10

User says "What new AI products are there":

python skills/news/scripts/news.py category --cat ai-community --limit 10

User says "Search for news about GPT":

python skills/news/scripts/news.py category --cat ai --keyword GPT --limit 15

User wants to read an article in depth:

# 使用 --detail -1 获取 RSS 全文内容
python skills/news/scripts/news.py category --cat ai --keyword "关键词" --detail -1 --limit 5

# 或使用 --json 获取完整 JSON（含全文）
python skills/news/scripts/news.py category --cat ai --keyword "关键词" --json --limit 5

After fetching the news, organize it into a concise list and return it to the user, including the title, source, and link. English content may have its summary translated as appropriate.

In-depth Reading Strategy

When the user wants to learn more about a piece of news, fetch the full text in the following order of priority:

  1. First choice:--detail -1 or --json — fetch the full text directly from the RSS source, with no extra network request
  2. Alternative:web_fetch(Chinese news sources only) — Chinese sites such as People's Daily, Xinhua Net, The Paper, and 36Kr usually allow scraping
  3. Do not use web_fetch for AI-type sources — websites such as OpenAI Blog, MIT Tech Review, Google AI Blog, and DeepMind Blog return 403/404 and cannot be scraped

Notes

  • Implemented purely with the Python standard library, no extra dependencies required
  • RSS sources may fail due to website changes; the script automatically skips failed sources
  • AI-type sources are in English; the content may be translated as appropriate when returned to the user
  • Most AI blog websites (OpenAI, Google AI, DeepMind, MIT Tech Review, etc.) block web_fetch direct access (returning 403/404), so in-depth reading of AI articles should use --detail -1 to fetch the full text from RSS, rather than trying to scrape the original link
  • Chinese news sources (People's Daily, The Paper, 36Kr, etc.) usually allow web_fetch to scrape detail pages