원클릭으로
claude-webscraping-skills
claude-webscraping-skills에는 zytelabs에서 수집한 skills 5개가 있으며, 저장소 수준 직업 범위와 사이트 내 skill 상세 페이지를 제공합니다.
이 저장소의 skills
Build a self-contained single-file Scrapy spider for scraping an ecommerce category (product list pages + product detail pages) using Zyte API AI extraction. Use this skill whenever the user wants to quickly scrape an ecommerce site, crawl a product category, extract product data, or build a Scrapy spider fast without a full project setup. Triggers include: "scrape this category", "build a spider for", "crawl products from", "get all products from", "scrape product listings", or any request to extract ecommerce data from a URL. The output is a ready-to-run Python script — no project scaffolding needed.
Extract structured product data from e-commerce URLs using the Zyte API and generate side-by-side comparison tables with intelligent purchase recommendations. Use this skill whenever the user wants to compare products from different e-commerce websites, asks "which product should I buy", wants a product comparison table, needs help deciding between product options, or provides multiple product URLs and wants them analyzed. Also trigger when the user says things like "compare these products", "which is the better deal", "help me pick between these", "product showdown", or pastes 2+ e-commerce URLs. Requires ZYTE_API_KEY in the environment.
Fetches raw HTML from a URL using httpx, with automatic fallback to Zyte API if blocked.
Extracts structured product data from raw HTML. Tries JSON-LD via Extruct first, falls back to CSS selectors via Parsel.
Capture a full-page screenshot of any public URL using the Zyte API. Use this skill whenever the user provides a URL and asks to take a screenshot, capture a page, grab a visual snapshot, or see what a website looks like. Also trigger when the user says things like "screenshot this", "capture this page", "show me what this site looks like", or "get a screenshot of [URL]". Requires ZYTE_API_KEY in the environment. After capturing, the skill saves the screenshot as a PNG file named after the website, reports the file location, and gives a 1-line description of what's visible in the screenshot.