news-hot-hub

新闻热点数据聚合器——整合知乎、今日头条、AIBase三大平台热搜数据。支持单独获取任一平台热榜，也支持一次性获取所有平台数据并汇总输出。当用户提到"热搜聚合"、"全平台热点"、"各平台热门话题"、"热榜整合"、"热点数据采集"、"我要看全网热点"、"刷一下各平台热榜"、"一键获取热榜"、"知乎头条热榜"、"全网...

Security Scan

The skill is an internally consistent scraper/aggregator for Zhihu, Toutiao and AIBase: it includes matching scripts, requires only standard parsing libraries, and its runtime behavior aligns with the stated purpose.

Purpose & Capability

Name/description describe a multi-platform hot-search aggregator and the package contains hub.py plus per-platform scripts (zhihu.py, toutiao.py, aibase.py) that implement that functionality. The declared requirements (requests, beautifulsoup4, lxml) match web-scraping tasks.

Instruction Scope

SKILL.md instructs the agent to run scripts/hub.py and to optionally pip install the local requirements; hub.py dispatches to local platform scripts which perform HTTP GETs to the target sites and output JSON. Nothing in the instructions reads unrelated system files or transmits data to unknown endpoints. One minor mismatch: platform-guide.md documents an optional ZHIHU_COOKIES env var required for some advanced Zhihu commands (hot-question/hot-video/topic), but the skill's top-level environment requirements do not list it — this is an optional/advanced credential and not required for the documented default hot-search behavior.

Install Mechanism

There is no remote install spec embedded in the skill bundle; SKILL.md recommends running pip install -r requirements.txt (standard Python packages). The requirement list is small and uses well-known packages. Risk is typical for any pip install (network download of packages) but no arbitrary remote binary downloads or obscure URLs are used.

Credentials

The skill does not declare required environment variables (only an optional HOT_HUB_LIMIT is documented). The only additional env var mentioned anywhere is ZHIHU_COOKIES in platform-guide.md for specific Zhihu subcommands; that is optional and reasonable for endpoints that require login, but the skill does not list it as a required credential — user should only set such cookies if they understand the privacy implications.

Persistence & Privilege

Skill is not request/always-included (always:false). It does not modify other skills or system-wide agent settings. It invokes local scripts via subprocesses (expected for a dispatcher) and does not request persistent elevated privileges.

Assessment

This skill appears to do what it claims: it runs local Python scripts to fetch hot-search data from Zhihu, Toutiao and AIBase and outputs JSON. Before installing, consider: (1) pip install -r requirements.txt will download packages from PyPI — run in a virtualenv or sandbox. (2) The scripts make outbound HTTP requests to the listed domains (zhihu.com, toutiao.com, news.aibase.cn) — ensure outbound network access is acceptable. (3) You should only set ZHIHU_COOKIES if you understand and trust the code and are comfortable exposing your browser cookie string to the environment (that cookie is sensitive). (4) hub.py executes the bundled scripts via subprocess.run, so the bundled scripts will execute as code on the host — review scripts if you need to verify they match your policy. (5) If you require stronger isolation, run the skill inside an isolated VM/container or review/modify the scripts to remove any functionality you do not want.

news Hot Hub — 中文热点数据聚合器

概述

整合知乎、今日头条、AIBase三大中文平台的热搜/热门数据。采用「调度器 + 独立脚本」插件式架构，每个平台一个独立 Python 脚本，由统一的 hub.py 调度。

目录结构

news-hot-hub/
├── SKILL.md                 # 本文件 — AI Agent 技能指令
├── requirements.txt         # Python 依赖
├── scripts/                 # 可执行脚本
│   ├── hub.py               # 统一调度入口 ★
│   ├── zhihu.py             # 知乎（已实现）
│   ├── toutiao.py           # 今日头条（已实现）
│   └── aibase.py            # AIBase（已实现）
└── references/              # 参考文档
    ├── architecture.md      # 架构设计
    ├── data-schema.md       # 数据格式规范
    └── platform-guide.md    # 平台接入指南

安装

pip install -r ${SKILL_DIR}/requirements.txt

核心依赖：requests, beautifulsoup4, lxml

CLI 使用

统一入口：${SKILL_DIR}/scripts/hub.py

python ${SKILL_DIR}/scripts/hub.py <command> [options]

平台标识

全称	缩写	中文
zhihu	zh	知乎
toutiao	tt	今日头条
aibase	ab	AIBase

命令一览

命令	说明	选项
fetch <platform>	获取指定平台热榜	--limit N
all	并行获取全部平台	--limit N
compare	跨平台热点词频对比	--limit N
status	检查各平台脚本可用性	—

使用示例

# 单平台获取
python ${SKILL_DIR}/scripts/hub.py fetch zhihu
python ${SKILL_DIR}/scripts/hub.py fetch toutiao --limit 20
python ${SKILL_DIR}/scripts/hub.py fetch aibase
python ${SKILL_DIR}/scripts/hub.py fetch aibase daily

# 多平台
python ${SKILL_DIR}/scripts/hub.py fetch zhihu,toutiao

# 全部平台
python ${SKILL_DIR}/scripts/hub.py all

# 跨平台对比
python ${SKILL_DIR}/scripts/hub.py compare

# 检查可用性
python ${SKILL_DIR}/scripts/hub.py status

触发逻辑

Agent 加载本 skill 后，根据用户意图判断调用方式：

1. 只提单一平台 → fetch <platform>
2. 提到多个平台 → fetch <p1>,<p2> 逗号分隔
3. “全部”/“所有”/“一键”/“全平台” → all
4. “对比”/“比较”/“交叉分析” → compare
5. 不明确 → 询问用户需要哪个/哪些平台

AIBase子命令映射

用户意图	子命令
AI新闻	fetch aibase（默认 hot-search → news）
AI日报	fetch aibase daily
AI新闻+日报	fetch aibase all

输出格式

fetch / all

JSON Lines（每行一个平台结果）：

{"platform": "知乎", "success": true, "data": {"type": "hot_search", "count": 25, "data": [...]}}

compare

跨平台词频分析 JSON，包含 top_keywords 和 per_platform 字段。

详细数据格式见 references/data-schema.md

环境变量

变量	说明
HOT_HUB_LIMIT	全局默认 limit，CLI --limit 可覆盖

参考文档

需要深入了解时，按需读取 references/ 目录下的文档：

• 架构设计 → references/architecture.md：系统架构、数据流、扩展机制
• 数据格式 → references/data-schema.md：各平台 JSON 输出字段详细定义
• 接入指南 → references/platform-guide.md：新平台接入步骤、脚本模板、认证说明

快速参考

需求	命令
知乎热搜	fetch zhihu
头条热榜	fetch toutiao
AIBase新闻	fetch aibase
AI日报	fetch aibase daily
全部平台	all
词频对比	compare
可用性检查	status