Lewati ke konten
TakoAPI
Kembali ke skill

anycrawl

oleh techlaai

Browser & Automation
2.4kUnduhan dilaporkan oleh clawskills.sh
1Bintang
0Tayangan
0 sukaMasuk untuk menyukai skill ini
—Belum ada penilaian
Penilaian Anda

Ringkasan

AnyCrawl API integration for OpenClaw - Scrape, Crawl, and Search web.

Deskripsi

Apa yang Dilakukan Skill Ini

AnyCrawl provides an API for scraping individual URLs, crawling entire websites, and searching Google. It converts web content into markdown, HTML, or structured JSON for use in AI workflows. Supports static pages via Cheerio and JavaScript-rendered apps via Playwright or Puppeteer.

One API handles both static HTML and JavaScript-rendered pages, removing the need to maintain separate scraping tools for different site types.

Kapan Menggunakannya

  • Extracting product prices from e-commerce pages
  • Crawling a documentation site to build a local knowledge base
  • Searching Google and scraping top results for research summaries
  • Pulling structured job listing data from career sites
  • Monitoring a competitor blog for new content

Contoh Alur Kerja

INPUT

User asks: What are the current pricing plans on this SaaS website?

AGENT
  1. 1

    Call anycrawl_scrape with the pricing page URL and cheerio engine

  2. 2

    Pass json_options with a schema for plan name, price, and features

  3. 3

    Receive structured JSON with extracted pricing tiers

  4. 4

    Return formatted pricing data to the user

OUTPUT

Structured list of pricing plans with names, prices, and included features

Persyaratan

  • ANYCRAWL_API_KEY environment variable
  • AnyCrawl account at anycrawl.dev

Instalasi

clawhub install techlaai/anycrawl

Jalankan perintah CLI-nya, atau tempel prompt ke Claude Code, Cursor, Codex, atau coding agent apa pun yang Anda pakai.

Tautan