xpr-web-scraping
paulgnz 作
Web & Frontend Development概要
Web scraping tools for fetching and extracting data from web pages.
説明
このスキルでできること
Web scraping tools for fetching and extracting data from web pages. Covers single-page content extraction, link discovery with regex filtering, and parallel fetching of up to 10 URLs. Output format is configurable: plain text, markdown, or raw HTML.
Parallel fetching with scrape_multiple and built-in deduplication in extract_links remove boilerplate that would otherwise require chaining multiple fetch-and-parse steps manually.
使いどころ
- Pulling article text from news or blog pages
- Finding all PDF download links on a documentation site
- Comparing pricing or feature pages across multiple competitors at once
- Extracting product descriptions from e-commerce listings
- Archiving web content as evidence in a research or audit job
ワークフロー例
User asks: Summarize and compare the features listed on these three SaaS pricing pages: https://example-a.com/pricing, https://example-b.com/pricing, https://example-c.com/pricing
- 1
Call scrape_multiple with all three URLs and format='text'
- 2
Receive cleaned text content from each page in parallel
- 3
Identify feature lists and pricing tiers from each result
- 4
Compile differences and commonalities across the three pages
A structured comparison table showing features, tiers, and pricing differences across the three products
インストール
clawhub install paulgnz/xpr-web-scrapingCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。