agentsclimarketplace

Web fetch cce

Skill luochang212/cc-enhance/skills/web-fetch-cce

网页内容提取策略。当需要读取网页内容、爬取页面、提取文章正文、处理JS渲染页面、或绕过反爬限制时,必须使用此技能。三层工具选择:WebFetch(内置)→ Crawl4AI(JS渲染/反爬)→ 原生 Playwright(兜底降级)。From its SKILL.md

Install
npx -y skills add luochang212/cc-enhance --skill web-fetch-cce

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 8 commands, including `conda --version` and 7 more.

SKILL.md

3.4 KB, ~1.2k tokens by cl100k_base, as published. Nobody here has run it

来自 cc-enhance-cce 后缀表示此技能由 cc-enhance 项目安装,避免与本地同名技能冲突。

Web Fetch

搜索拿到 URL 之后,把页面内容提取为 Claude 可读的格式。

工具选择

工具适用场景格式
WebFetch静态页面、文档、博客HTML → Markdown
Crawl4AIJS 渲染、反爬、结构化提取Playwright → Markdown / JSON
原生 PlaywrightCrawl4AI 超时/被检测时的降级inner_text 纯文本

策略

  1. 优先 WebFetch。内置、<1s、零依赖。覆盖 90% 的页面。
  2. Crawl4AI 处理 JS 重/反爬页。Markdown 质量好,magic=True 解微信。
  3. 原生 Playwright 兜底。当 Crawl4AI 超时(阮一峰)或被检测时,手动控制 wait_until 策略。

对比

WebFetchCrawl4AI原生 Playwright
速度<1s2-4s1-5s
JS 渲染
输出质量可用丰富 Markdown纯文本
反爬magic/undetected手动注入
灵活性高(wait_until、stealth)
适合90% 日常JS 重/反爬页Crawl4AI 搞不定时

参考

环境依赖

依赖用途安装方式磁盘必需
Python 环境 + Crawl4AIJS 渲染、反爬绕过见下方「Python 环境检测」~300MB
无(WebFetch 内置)静态页面首选,零依赖0

Python 环境检测

按以下顺序检查,任一项满足即可跳过安装:

  1. conda --version → 已有 conda,直接用 conda 创建环境
  2. uv --version → 已有 uv,用 uv venv && uv pip install
  3. python3 --version → 已有 python3,用 venv + pip

若都没有,按优先级推荐安装:

  • 首选Miniconda — 跨平台、环境隔离好
  • 备选uv — 轻量快速、pip 兼容

安装后执行:

中国大陆使用镜像加速(腾讯云 / 阿里云二选一):

# conda
conda create -n crawl4ai python=3.13 -y && conda activate crawl4ai
pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ crawl4ai  # 腾讯云
pip install -i https://mirrors.aliyun.com/pypi/simple/ crawl4ai          # 阿里云
playwright install chromium

# uv
uv venv && source .venv/bin/activate
uv pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ crawl4ai  # 腾讯云
uv pip install -i https://mirrors.aliyun.com/pypi/simple/ crawl4ai          # 阿里云
playwright install chromium

# venv
python3 -m venv venv && source venv/bin/activate
pip install -i https://mirrors.cloud.tencent.com/pypi/simple/ crawl4ai  # 腾讯云
pip install -i https://mirrors.aliyun.com/pypi/simple/ crawl4ai          # 阿里云
playwright install chromium

What ships with it: 2 files

9.5 KB alongside SKILL.md

references/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.