shopify-supplier-extract

Extract structured product data from supplier HTML into canonical JSON.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/redbananastudios/ai-library --skill shopify-supplier-extract
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: shopify-supplier-extract
Source: https://github.com/redbananastudios/ai-library/tree/main/generated/claude/skills/shopify-supplier-extract
Command: npx skills add https://github.com/redbananastudios/ai-library --skill shopify-supplier-extract

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of manually scraping supplier pages and converting messy HTML and images into structured, consistent product data for downstream importing.

Core Features & Use Cases

  • CSV-driven extraction workflow: Takes a products.csv with required supplier and SKU fields, filters invalid/blocked rows, and processes each product deterministically.
  • Structured raw JSON output: Cleans supplier HTML and extracts factual content into a canonical raw JSON format (tables kept structured, descriptions/bullets/specs/FAQ separated).
  • Media asset harvesting: Downloads hi-res images and datasheets into per-product output folders for traceable publishing.
  • Standard project workflow: Uses a known input location, produces output in a predictable output/{slug}-{our_sku}/ structure, and reports success/failure totals.

Quick Start

Ask the AI to run shopify-supplier-extract against your products CSV at ./brand-memory/input/products.csv (or ./input/products.csv) to produce output/raw.json plus downloaded images and datasheets for each non-amazon supplier row.

Frequently Asked Questions about shopify-supplier-extract

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract structured product data from supplier HTML pages?

You can extract structured product data from supplier HTML by providing a CSV with supplier and SKU columns. The tool fetches each URL, cleans the HTML, and normalizes factual content into a canonical JSON schema.

Can I download supplier product images and datasheets automatically?

Yes, you can download supplier product images and datasheets automatically. The tool harvests media assets during the extraction process and saves them into per-product output folders for traceable publishing.

How do I normalize messy supplier website content into canonical JSON?

Normalizing messy supplier website content into canonical JSON involves separating tables, descriptions, bullet points, specs, and FAQs into structured fields. The tool outputs this cleaned data as a raw.json file in a predictable directory structure.

Does the supplier scraping workflow skip Amazon suppliers or empty SKUs?

Yes, the supplier scraping workflow explicitly skips Amazon suppliers and empty supplier SKUs. It validates required CSV columns before processing and reports success and failure totals to ensure data integrity.

What happens when product extraction encounters fetch or extraction errors?

When product extraction encounters fetch or extraction errors, the tool handles them gracefully without stopping the entire workflow. It logs the failures and continues processing subsequent rows to ensure robust batch completion.