skills.rest
Joresti
JorestiCOMMUNITY
Explore all skills by this author →
GitHub

parse-flyer-highlandpackers

Extract grocery deals from Highland Packers flyer images into structured JSON records.

1|Updated Mar 12, 2026
Search Tags:#ocr#web scraping#meal planning#data normalization#Claude Vision#image-based parsing
One-click install
npx skills add https://github.com/Joresti/grocery-hack --skill parse-flyer-highlandpackers
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: parse-flyer-highlandpackers
Source: https://github.com/Joresti/grocery-hack/tree/main/.claude/skills/parse-flyer-highlandpackers
Command: npx skills add https://github.com/Joresti/grocery-hack --skill parse-flyer-highlandpackers

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill extracts weekly grocery deals from Highland Packers flyers that contain no readable page text, so you can convert image-based product pricing into structured deal records.

Core Features & Use Cases

  • Image-to-OCR Deal Extraction: Collects product image URLs, downloads them, and uses Claude Vision OCR to read product names and prices from JPGs.
  • Section & Category Mapping: Derives canonical grocery categories from image filename/section conventions and assigns each extracted item to the right department.
  • Deal Record Output for Meal Planning: Produces a JSON array of normalized deal fields (name, product type, category, sale price, unit), enabling downstream meal planning and matching.

Quick Start

Ask the Skill to parse the Highland Packers flyer at https://www.highlandpackers.com/weekly-specials-flyer.html and return the extracted deals as JSON.

Frequently Asked Questions about parse-flyer-highlandpackers

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

FAQPage Schema
How do I extract grocery deals from a website flyer that has no readable DOM text?▼

To extract grocery deals from image-based flyers with zero DOM text, you need to inventory image URLs, download the JPG files, and apply OCR to recover product names and sale prices. This Skill automates that entire image-to-JSON workflow.

Can I use Claude Vision for OCR on product images to get structured sale prices?▼

Yes, Claude Vision can perform OCR on downloaded product JPGs to extract and normalize sale prices and units. This Skill uses Claude Vision (Haiku) to read image-based pricing and output structured JSON records.

What's the best way to normalize scraped grocery flyer data for meal planning?▼

Normalizing scraped grocery flyer data for meal planning requires mapping extracted items to canonical grocery categories and validating deal fields like sale price and units. This Skill produces a structured JSON array for that downstream use.

How does a Chrome CDP headed session help with scraping image-based web flyers?▼

A Chrome CDP headed session helps scrape image-based flyers by programmatically inventorying all product image URLs on the page. This Skill uses it to collect JPG links before downloading and running OCR extraction.

Does this OCR web scraping approach work for flyers with zero readable page text?▼

Yes, this OCR web scraping approach is specifically designed for flyers with zero readable page text. It bypasses the lack of DOM text by downloading product images directly and using Claude Vision to recover deal information.

What limitations exist when parsing image-based flyers into structured JSON records?▼

Limitations when parsing image-based flyers include relying on the clarity of product JPGs for accurate OCR extraction and depending on image filename conventions for category mapping. Poor image quality can affect the recovered deal data.

Related Skills

Explore More Software Engineering Skills→
JorestiJoresti
1

parse-flyer-foodbasics

Parse Food Basics flyer product tiles into normalized deal records.

Community
Intermediate
JorestiJoresti
1

parse-flyer-walmart

Parse Walmart Canada flyer deals via the Flipp API into normalized JSON records.

Community
Intermediate
ltdrewltdrew
1

data-research

Gather sources and extract fields into canonical tracker pages.

Community
Advanced
jmaglyjmagly
175

pdf-extractor

Extracts text, tables, and images from PDFs into structured outputs with OCR support.

Community
Advanced