跳到正文
TakoAPI
返回技能列表

crawl-for-ai

由 angusthefuzz 提供

Web & Frontend Development
2.4k下载量由 clawskills.sh 提供
5星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Web scraping using local Crawl4AI instance.

描述

该技能的功能

Fetches full web page content using a local Crawl4AI instance with JavaScript rendering. Offers two endpoints: a proxy for clean markdown output and a direct endpoint for structured data including links, HTML, and media. No usage limits since it runs locally.

Runs on a local instance with no rate limits or API costs, and reliably handles dynamic JavaScript content that simpler fetch-based scrapers miss.

何时使用

  • Scraping JavaScript-rendered single-page applications
  • Extracting article text from JS-heavy or dynamic news sites
  • Collecting product data from e-commerce pages
  • Archiving web pages with full link and media metadata
  • Pulling content from documentation portals that require JS execution

示例工作流

输入

User asks: Get the full content from https://example.com/docs/getting-started

智能体
  1. 1

    Identify the target URL from the user request

  2. 2

    Call crawl4ai.js with the URL via the proxy endpoint for clean output

  3. 3

    Receive the page rendered as structured markdown with metadata

  4. 4

    Return the extracted content to the user

输出

Full page content as clean markdown, including any dynamically loaded text

前置要求

  • Self-hosted Crawl4AI instance running locally or on a server
  • CRAWL4AI_URL environment variable set to the instance URL
  • CRAWL4AI_KEY environment variable if the instance requires authentication

安装

clawhub install angusthefuzz/crawl-for-ai

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接