微信文章格式转换

微信公众号文章抓取与转换，支持 Markdown/HTML/Text/JSON/Excel 五种格式。 触发条件：用户发送微信文章链接（https://mp.weixin.qq.com/s/xxx）、 多链接（换行分隔）、或「帮我转这篇文章」「保存微信文章」等表达。 格式选择前必须询问用户，支持单选或多选。

What to consider before installing: - Functional coherence: The scripts do what the description says (download article HTML and assets, convert and save). However SKILL.md lists only html5lib while the code imports BeautifulSoup (bs4) and likely an Excel library — confirm and install required Python packages (beautifulsoup4, html5lib, and the Excel writer such as openpyxl/xlsxwriter) from trusted sources before running. - Network safety: The tool downloads all asset URLs it finds in the article HTML without domain restriction. A malicious or crafted article could include links to internal network addresses (127.0.0.1, 192.168.x.x) or other unexpected hosts; consider running the tool in a network-restricted or sandboxed environment if you are concerned about internal service access. - Filesystem impact: It writes output under your home Desktop by default. If you allow it, it will create directories and save binary assets — review the save location and run in a directory you control. - Code review/validation: Review the rest of fetch_article.py (the truncated portion) and save_article implementation to confirm there is no telemetry, hidden remote endpoints, or unexpected behavior (e.g., uploading files elsewhere). The provided excerpts show no evidence of exfiltration, but the file is truncated so complete review is recommended. - Safe testing: Run first on a single, benign article in an isolated environment; inspect downloaded assets and logs to confirm behavior before bulk use. If you want, I can: (1) list precise Python packages this code requires by scanning the rest of fetch_article.py, (2) extract and show the save_article function and Excel code for review, or (3) suggest command-line steps to create a safe virtualenv and run one test fetch.

Type: OpenClaw Skill Name: wechat-article-conversion Version: 1.0.0 The skill bundle is a functional tool for scraping and converting WeChat articles into Markdown, HTML, Excel, and other formats. The Python scripts (fetch_article.py and batch_fetch.py) use standard libraries like BeautifulSoup and urllib to retrieve content exclusively from mp.weixin.qq.com, including logic to localize images/CSS and sanitize HTML by removing script tags. There is no evidence of data exfiltration, malicious execution, or harmful prompt injection; the code is well-structured and aligns perfectly with its stated purpose.