WeChat Article Fetcher

获取微信公众号文章内容。当用户提供 mp.weixin.qq.com 链接时提取正文。

Security Scan

The skill's code and instructions match its stated purpose (fetch and render WeChat article pages via a browser automation library); required resources and outputs are coherent with that goal.

Purpose & Capability

Name/description, SKILL.md, and the included Python script all align: the tool launches a Chromium instance (via DrissionPage), loads a mp.weixin.qq.com URL, extracts #js_content, takes a screenshot, and writes Markdown and PNG files. There are no unrelated credentials, system paths, or external services requested.

Instruction Scope

Runtime instructions are limited and specific: run the provided Python script with a WeChat article URL and optional output directory/headless flag. The script only fetches the provided URL, extracts text, takes a screenshot, writes output files, and prints the Markdown to stdout for the agent. It does not read other system files or access environment variables.

Install Mechanism

No formal install spec in registry (instruction-only), but SKILL.md requires pip installing scripts/requirements.txt which pulls DrissionPage from PyPI. DrissionPage itself may perform a network download of a matching ChromeDriver on first run (documented in SKILL.md). This is expected for browser automation but does mean the skill will cause additional network downloads and write executables to disk at runtime.

Credentials

The skill requests no environment variables or credentials. It does require a local Chrome browser to be installed (documented) and writes output files to a user-specified directory (default current working directory). These are proportional to the scraping/rendering purpose.

Persistence & Privilege

The skill is not force-included (always: false) and does not modify other skills or global agent settings. It runs only when invoked and does not ask to persist credentials or enable autonomous always-on behavior.

Assessment

This skill appears to do exactly what it claims: render a WeChat article in a real Chromium instance and extract text plus a screenshot. Before installing, note: (1) you must pip-install the DrissionPage dependency and have Chrome installed; DrissionPage may download a ChromeDriver binary at first run (external network download and writing an executable to disk). (2) The script will launch a full browser and render remote page content, so remote JavaScript/resources will execute in that browser session (expected for scraping but can trigger trackers or additional network activity). (3) The skill writes files to the chosen output directory (default = current working directory), so avoid running it with a sensitive directory as the output path. If you want added assurance, review the DrissionPage package source and verify its ChromeDriver download behavior before use.

微信公众号文章获取

触发条件

• 用户发送 mp.weixin.qq.com 链接
• 用户要求获取/提取微信公众号文章内容

用法

python "{skill_dir}/scripts/fetch_weixin.py" "<文章URL>" -o "<输出目录>"

参数说明：

• <文章URL> — 微信公众号文章链接
• -o <输出目录> — 可选，输出文件保存目录（默认当前工作目录）
• --headless — 可选，无头模式（微信文章通常需要完整浏览器，慎用）

输出文件：

• article_content_weixin.md — 文章标题 + 正文（Markdown 格式）
• article_screenshot_weixin.png — 页面截图

示例

# 获取文章，输出到工作区
python "{skill_dir}/scripts/fetch_weixin.py" "https://mp.weixin.qq.com/s/EVdnYEzlrT3BZZUmlbxHQQ" -o "C:\Users\David\.qclaw\workspace"

# 无头模式（可能加载失败，慎用）
python "{skill_dir}/scripts/fetch_weixin.py" "https://mp.weixin.qq.com/s/xxxxx" --headless

依赖

首次使用前安装：pip install -r {skill_dir}/scripts/requirements.txt

工作原理

1. 启动 Chrome（默认有头模式），URL 追加 ?_t=毫秒时间戳 绕过微信 CDN 缓存
2. 等待 #js_content 加载，提取正文文本
3. 输出 Markdown 文件 + 截图到指定目录

注意事项

• 需要系统已安装 Chrome 浏览器
• 首次运行会自动下载匹配的 ChromeDriver