skillfed

structured-scraping-riveter

Riveter lets you scrape web pages and extract data directly into a structure you define. Set up your output schema in the API request, specify what fields to extract, and retrieve results in your chosen format—supporting text, numbers, JSON, URLs, emails, dates, and more.

Riveter extracts web data into your custom-defined schema, letting you scrape pages and structure the output exactly as needed.

AI-generated summary based on this skill's SKILL.md

1,062 194 MIT updated by gooseworks-ai

Install

gooseworks-ai/goose-skills/structured-scraping-riveter · repository language: Python

CLI (skillfed)coming soon
git clone https://github.com/gooseworks-ai/goose-skills
cp -r goose-skills/skills/research-tools/capabilities/structured-scraping-riveter ~/.claude/skills/structured-scraping-riveter

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

What is structured-scraping-riveter and what can it do?

Structured-scraping-riveter is a web scraping tool that extracts data from websites and returns it in a structure you define. You specify your output schema in the API request, choose which fields to extract, and receive results in your chosen format—supporting text, numbers, JSON, URLs, emails, dates, and more.

Can I extract data from websites into JSON with structured-scraping-riveter?

Yes. Structured-scraping-riveter lets you extract data from websites into JSON by defining your custom schema in the API request. You specify the fields you want to capture, and the tool returns the results in JSON format along with other structured data types you need.

How does structured-scraping-riveter handle scraping multiple web pages?

Structured-scraping-riveter scrapes multiple web pages and retrieves results in a consistent format. You define your schema once, then apply it across multiple URLs. The tool ensures all results follow the same structure, making it easy to process large batches of data uniformly.

Can structured-scraping-riveter monitor competitor prices?

Yes. Structured-scraping-riveter supports monitoring and extracting product or price data from competitor websites. You define the schema for price fields, URLs, and product details, then use the tool to regularly scrape and track changes across multiple competitor sites in a structured format.

What data types does structured-scraping-riveter support in output?

Structured-scraping-riveter supports multiple output data types including text, numbers, JSON, URLs, emails, and dates. When you define your schema, you specify the type for each field, and the tool extracts and formats the data accordingly to match your requirements.

Does structured-scraping-riveter work with job listings and news articles?

Yes. Structured-scraping-riveter can parse job listings and news articles with structured metadata. Define your schema to capture job title, company, salary, publication date, author, and other fields, then the tool extracts and organizes that data consistently across multiple sources.

SKILL.md

rendered from the published skill — quoted content, verbatim

Riveter - Structured Web Scraping

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Scrape web pages and extract data into your defined structure.

Capabilities

  • Scrape: Scrape a webpage and return the text content
  • Run: Copy link Define the structure of your output directly in the API request
  • Run data: Retrieve the processed data from a completed project run (free)
  • Run status: Check the current status of a project run (free)
  • Stop run: Stop a currently running project (free)

Usage

Scrape

Scrape a webpage

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 2 files
skills/research-tools/capabilities/structured-scraping-riveter/SKILL.md
skills/research-tools/capabilities/structured-scraping-riveter/skill.meta.json

Related skills

Tags

schema-driven-extraction web-data-harvesting structured-output-format batch-scraping-api content-parsing-tool data-transformation-pipeline multi-format-export proxy-enabled-scraping async-job-processing