desearch-crawl
由 okradze 提供
Web & Frontend Development简介
Crawl/scrape and extract content from any webpage URL.
描述
该技能的功能
Crawls a webpage by URL and returns its content as clean text or raw HTML. Powered by the Desearch API. Useful when an agent needs to read the full contents of a specific page rather than search for it.
Returns clean, markup-free text by default, which keeps agent context lean compared to raw HTML scrapers.
何时使用
- Reading a documentation page before writing code
- Extracting article text for summarization
- Fetching a competitor's pricing page for comparison
- Pulling release notes from a changelog URL
- Checking the current content of a web page before editing
示例工作流
User asks: summarize the Python 3 tutorial index
- 1
Call crawl with 'https://docs.python.org/3/tutorial/index.html' and default text format
- 2
Receive plain text content of the page
- 3
Parse section headings and descriptions from the text
- 4
Compose a summary from the extracted content
A structured summary of the Python 3 tutorial sections
前置要求
- DESEARCH_API_KEY environment variable
- Desearch account at console.desearch.ai (paid balance required)
安装
clawhub install okradze/desearch-crawl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。