Extract Webpage Data
Extracts structured or raw data from any URL using Olostep, Scrapegraph, and Riveter.
npx goose-skills installDescription
Extracts structured or raw data from any URL using Olostep, Scrapegraph, and Riveter. Each API covers a different extraction mode: bulk, NL-guided, or schema-based structured output.
What this skill does
- 1Scrape any URL and return its content as markdown, HTML, or plain text.
- 2Extract specific structured data from a page using a natural language prompt (e.g., 'get all team members with titles and LinkedIn URLs').
- 3Use a JSON schema to define exactly what fields to pull when you know the data structure in advance.
- 4Crawl multiple linked pages from a starting URL to collect data across an entire site section.
When to use
- You need pricing or feature data from a competitor's website without manual copy-paste.
- You want to extract a team page into a structured contact list for prospecting.
- You need to pull all blog post titles and dates from a publication for content research.
Tools used
Best for
Format
Frequently asked questions
What is Extract Webpage Data?
Extract Webpage Data is a Claude Code skill for sourcing by GooseWorks AI. Extracts structured or raw data from any URL using Olostep, Scrapegraph, and Riveter.
When should I use Extract Webpage Data?
You need pricing or feature data from a competitor's website without manual copy-paste. You want to extract a team page into a structured contact list for prospecting.
How do I install Extract Webpage Data?
Run the install command (npx goose-skills install). Once the skill is in place, Claude Code loads it automatically whenever a task matches what it does.
Is Extract Webpage Data free to use?
The author distributes it as MIT, but the repository has no LICENSE file. The source is public on GitHub (gooseworks-ai/goose-skills).