Install any skill in seconds. Free to start, no credit card required.
Get Started Free →clean-content-fetch
获取干净、可读的网页正文内容,适合现代网页、博客、新闻、公告和微信公众号文章抓取;支持网页正文提取、内容清洗、去噪、Markdown 输出,适用于普通 fetch 效果不佳、页面噪音较多或动态渲染干扰的场景。Clean content fetch for modern web pages, article extraction, WeChat article capture, content cleanup, noise reduction, and markdown output when ordinary fetch is not clean enough.
Passed 8 of 19 test cases with the skill, and 1 of 19 without it.
and 5 more in the full report
8 fixed1 passed either way13 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
An engineer ingesting data from scrapling_fetch.py --json expects the extracted body text to be placed under a key named body_html. Which top-level JSON key actually contains the final converted Markdown content?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies content as the JSON key holding the converted Markdown text | Missed | Passed |
The instructions your model reads when the skill loads.
当用户要获取网页内容、正文提取、把网页转成 markdown/text、抓取文章主体时,优先使用此技能。
python3 scripts/scrapling_fetch.py <url> <max_chars>articlemain.post-content[class*="body"]html2text 转 Markdownbodymax_chars 截断输出python3 /Users/zzd/.openclaw/workspace/skills/scrapling-web-fetch/scripts/scrapling_fetch.py <url> 30000
优先检查:
scraplinghtml2textcurl_cffiplaywrightbrowserforge推荐使用独立虚拟环境,避免系统 Python 的 PEP 668 限制:
python3 -m venv /Users/zzd/.openclaw/workspace/.venvs/clean-content-fetch
/Users/zzd/.openclaw/workspace/.venvs/clean-content-fetch/bin/pip install scrapling html2text curl_cffi playwright browserforge
/Users/zzd/.openclaw/workspace/.venvs/clean-content-fetch/bin/python -m playwright install chromium
如直接运行脚本,优先使用该虚拟环境中的 Python:
/Users/zzd/.openclaw/workspace/.venvs/clean-content-fetch/bin/python /Users/zzd/.openclaw/workspace/skills/scrapling-web-fetch/scripts/scrapling_fetch.py <url> 30000
test cases passed, vs 1 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.