wechat-article

抓取微信公众号文章，提取标题和内容并输出为 Markdown 格式。支持多种提取方式。

Security Scan

The skill's code and runtime instructions match its stated purpose (fetch WeChat article and output Markdown); it requests no credentials and does not perform unexpected file or credential access.

Purpose & Capability

Name/description, runtime instructions, and the included Python script all focus on fetching a WeChat article and outputting Markdown. Required binary (python3) is appropriate and there are no unrelated credentials or config paths.

Instruction Scope

Instructions simply run the included script and describe three extraction strategies. The script implements the jina.ai third‑party extractor and a direct fetch fallback; the 'agent-browser' (browser automation) strategy is mentioned in docs but not implemented in the code. The instructions do cause outbound HTTP requests to the target article and to r.jina.ai (when that mode is used), which is expected for this purpose.

Install Mechanism

No install spec (instruction-only) — lowest file-on-disk risk. However the script depends on the Python 'requests' package even though SKILL.md only declares python3; users must ensure the environment has requests installed. No arbitrary downloads or extract operations are present.

Credentials

The skill requests no environment variables or secrets. It performs network calls to the target mp.weixin.qq.com URL and to r.jina.ai when using that extractor; that external network access is proportional to the stated purpose but has privacy implications (content is sent to a third party).

Persistence & Privilege

The skill does not request permanent presence (always is false) and does not modify other skills or system settings. It is user-invocable and can run autonomously per platform defaults, which is normal.

Assessment

This skill appears to do what it says: it fetches WeChat article content and formats Markdown. Before installing: - Be aware that using the r.jina.ai extractor will send article content to a third-party service (privacy risk for sensitive content). - The SKILL.md mentions a browser-automation fallback, but the included script only implements jina.ai and direct HTTP fetch; it cannot bypass captchas automatically. - Ensure your Python environment has the 'requests' library installed (the skill needs it but doesn't declare it). - No credentials or secret environment variables are requested by the skill. - If you will process private or sensitive articles, avoid the r.jina.ai mode or review/modify the code to use a self-hosted extractor. - If you want full assurance, inspect the script locally (it's short and readable) and run it in a controlled environment before granting it network access.

微信公众号文章抓取

通过公众号链接获取文章的标题和内容，输出为 Markdown 格式。

Usage

python3 skills/wechat-article/scripts/wechat_article.py '<公众号文章链接>'

输出示例

# 文章标题

**发布时间**: 2026-03-04
**公众号**: 某某公众号

---

文章正文内容...

提取策略

按顺序尝试以下方式：

1. r.jina.ai - 第三方内容提取服务（推荐）
2. web_fetch - 直接抓取（可能被拦截）
3. agent-browser - 浏览器自动化（需要处理验证码）

注意事项

• 微信公众号有反爬虫机制，部分文章可能无法获取
• 需要验证码的文章无法自动处理
• 建议优先使用 r.jina.ai 方式

示例

# 基本使用
python3 skills/wechat-article/scripts/wechat_article.py "https://mp.weixin.qq.com/s/xxx"

# 输出到文件
python3 skills/wechat-article/scripts/wechat_article.py "https://mp.weixin.qq.com/s/xxx" > article.md