web-fetch-cce

From cc-enhance。-cce The suffix indicates that this skill was installed by the cc-enhance project, to avoid conflicts with a local skill of the same name.

Web Fetch

After search obtains the URL, extract the page content into a format readable by Claude.

Tool selection

Tool	Applicable scenarios	Format
WebFetch	Static pages, documents, blogs	HTML → Markdown
Crawl4AI	JS rendering, anti-scraping, structured extraction	Playwright → Markdown / JSON
Native Playwright	Fallback when Crawl4AI times out/is detected	inner_text Plain text

Strategy

1. Prioritize WebFetch. Built-in, <1s, zero dependencies. Covers 90% of pages.
2. Crawl4AI handles JS-heavy/anti-scraping pages. Good Markdown quality,magic=True solves WeChat.
3. Native Playwright fallback. When Crawl4AI times out (Ruan Yifeng) or is detected, manually control the wait_until strategy.

Comparison

	WebFetch	Crawl4AI	Native Playwright
Speed	<1s	2-4s	1-5s
JS rendering	No	Yes	Yes
Output quality	Usable	Rich Markdown	Plain text
Anti-scraping	No	magic/undetected	Manual injection
Flexibility	None	Medium	High (wait_until, stealth)
Suitable for	90% of daily use	JS-heavy/anti-scraping pages	When Crawl4AI can't handle it

Reference

• references/crawl4ai.md — Crawl4AI deployment and usage, China site testing matrix
• references/playwright.md — Native Playwright fallback solution

Environment dependencies

Dependency	Purpose	Installation method	Disk	Required
Python environment + Crawl4AI	JS rendering, anti-scraping bypass	See "Python environment detection" below	~300MB	No
None (WebFetch built-in)	First choice for static pages, zero dependencies	—	0	No

Python environment detection

Check in the following order; if any one is satisfied, you can skip installation:

1. conda --version → conda is already available, directly use conda to create the environment
2. uv --version → uv is already available, use uv venv && uv pip install
3. python3 --version → python3 is already available, use venv + pip

If none are available, recommended installation by priority:

• First choice：Miniconda — Cross-platform, good environment isolation
• Alternative：uv — Lightweight and fast, pip-compatible

After installation, run:

For mainland China, use a mirror for acceleration (choose either Tencent Cloud or Alibaba Cloud):

# 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