Scrapling Web Fetch

使用 Scrapling + html2text 获取现代网页正文内容，支持微信公众号文章抓取与尾部噪音清洗，减少无用信息与 token 消耗；适合抓取博客、新闻、公告及许多普通 fetch 不稳定、存在反爬或动态渲染干扰的网页。Supports WeChat article cleanup, markdown...

This skill appears to do what it says: fetch pages, extract body text, convert to Markdown, and clean WeChat noise. Before installing or running it, review the PyPI package 'scrapling' (and its homepage/source) because the script depends on it; a malicious or overly-permissive package could perform network calls or execute code. Run pip installs in a virtualenv or sandbox, inspect installed package source, and avoid passing sensitive local file paths to --batch or --selectors (the script will read those files). If you need stronger assurance, ask for the 'scrapling' package source or use an alternative extractor implemented with well-known libraries (requests + readability / newspaper / browser automation) whose behavior you can audit.

Type: OpenClaw Skill Name: scrapling-web-fetch Version: 1.0.2 The skill is a legitimate web content extraction tool designed to fetch and convert web pages into Markdown using the 'scrapling' and 'html2text' libraries. It features specific logic in 'scripts/scrapling_fetch.py' to clean up UI noise from WeChat articles, which helps reduce token usage for LLM processing. There is no evidence of data exfiltration, malicious execution, or prompt injection; the hardcoded file paths in 'SKILL.md' and 'usage.md' appear to be artifacts of the developer's local environment rather than malicious indicators.