AGENT SKILL

apify-ecommerce

Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
apify-ecommerce
risk
unknown
source
community
description
Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool.

02 资源文件 2

03 SKILL.md 正文

E-commerce Data Extraction

Extract product data, prices, reviews, and seller information from any e-commerce platform using Apify's E-commerce Scraping Tool.

When to Use

  • You need product, pricing, review, stock, or seller data from e-commerce sites.
  • The task involves price monitoring, competitor product comparison, MAP enforcement, or review analysis.
  • You need a guided workflow for extracting marketplace data and summarizing findings.

Prerequisites

  • .env file with APIFY_TOKEN (at ~/.claude/.env)
  • Node.js 20.6+ (for native --env-file support)

Workflow Selection

User Need Workflow Best For
Track prices, compare products Workflow 1: Products & Pricing Price monitoring, MAP compliance, competitor analysis. Add AI summary for insights.
Analyze reviews (sentiment or quality) Workflow 2: Reviews Brand perception, customer sentiment, quality issues, defect patterns
Find sellers across stores Workflow 3: Sellers Unauthorized resellers, vendor discovery via Google Shopping

Progress Tracking

Task Progress:
- [ ] Step 1: Select workflow and determine data source
- [ ] Step 2: Configure Actor input
- [ ] Step 3: Ask user preferences (format, filename)
- [ ] Step 4: Run the extraction script
- [ ] Step 5: Summarize results

Workflow 1: Products & Pricing

Use case: Extract product data, prices, and stock status. Track competitor prices, detect MAP violations, benchmark products, or research markets.

Best for: Pricing analysts, product managers, market researchers.

Input Options

Input Type Field Description
Product URLs detailsUrls Direct URLs to product pages (use object format)
Category URLs listingUrls URLs to category/search result pages
Keyword Search keyword + marketplaces Search term across selected marketplaces

Example - Product URLs

{
  "detailsUrls": [
    {"url": "https://www.amazon.com/dp/B09V3KXJPB"},
    {"url": "https://www.walmart.com/ip/123456789"}
  ],
  "additionalProperties": true
}

Example - Keyword Search

{
  "keyword": "Samsung Galaxy S24",
  "marketplaces": ["www.amazon.com", "www.walmart.com"],
  "additionalProperties": true,
  "maxProductResults": 50
}

Optional: AI Summary

Add these fields to get AI-generated insights:

Field Description
fieldsToAnalyze Data points to analyze: ["name", "offers", "brand", "description"]
customPrompt Custom analysis instructions

Example with AI summary:

{
  "keyword": "robot vacuum",
  "marketplaces": ["www.amazon.com"],
  "maxProductResults": 50,
  "additionalProperties": true,
  "fieldsToAnalyze": ["name", "offers", "brand"],
  "customPrompt": "Summarize price range and identify top brands"
}

Output Fields

  • name - Product name
  • url - Product URL
  • offers.price - Current price
  • offers.priceCurrency - Currency code (may vary by seller region)
  • brand.slogan - Brand name (nested in object)
  • image - Product image URL
  • Additional seller/stock info when additionalProperties: true

Note: Currency may vary in results even for US searches, as prices reflect different seller regions.


Workflow 2: Customer Reviews

Use case: Extract reviews for sentiment analysis, brand perception monitoring, or quality issue detection.

Best for: Brand managers, customer experience teams, QA teams, product managers.

Input Options

Input Type Field Description
Product URLs reviewListingUrls Product pages to extract reviews from
Keyword Search keywordReviews + marketplacesReviews Search for product reviews by keyword

Example - Extract Reviews from Product

{
  "reviewListingUrls": [
    {"url": "https://www.amazon.com/dp/B09V3KXJPB"}
  ],
  "sortReview": "Most recent",
  "additionalReviewProperties": true,
  "maxReviewResults": 500
}

Example - Keyword Search

{
  "keywordReviews": "wireless earbuds",
  "marketplacesReviews": ["www.amazon.com"],
  "sortReview": "Most recent",
  "additionalReviewProperties": true,
  "maxReviewResults": 200
}

Sort Options

  • Most recent - Latest reviews first (recommended)
  • Most relevant - Platform default relevance
  • Most helpful - Highest voted reviews
  • Highest rated - 5-star reviews first
  • Lowest rated - 1-star reviews first

Note: The sortReview: "Lowest rated" option may not work consistently across all marketplaces. For quality analysis, collect a large sample and filter by rating in post-processing.

Quality Analysis Tips

  • Set high maxReviewResults for statistical significance
  • Look for recurring keywords: "broke", "defect", "quality", "returned"
  • Filter results by rating if sorting doesn't work as expected
  • Cross-reference with competitor products for benchmarking

Workflow 3: Seller Intelligence

Use case: Find sellers across stores, discover unauthorized resellers, evaluate vendor options.

Best for: Brand protection teams, procurement, supply chain managers.

Note: This workflow uses Google Shopping to find sellers across stores. Direct seller profile URLs are not reliably supported.

Input Configuration

{
  "googleShoppingSearchKeyword": "Nike Air Max 90",
  "scrapeSellersFromGoogleShopping": true,
  "countryCode": "us",
  "maxGoogleShoppingSellersPerProduct": 20,
  "maxGoogleShoppingResults": 100
}

Options

Field Description
googleShoppingSearchKeyword Product name to search
scrapeSellersFromGoogleShopping Set to true to extract sellers
scrapeProductsFromGoogleShopping Set to true to also extract product details
countryCode Target country (e.g., us, uk, de)
maxGoogleShoppingSellersPerProduct Max sellers per product
maxGoogleShoppingResults Total result limit

Supported Marketplaces

Amazon (20+ regions)

www.amazon.com, www.amazon.co.uk, www.amazon.de, www.amazon.fr, www.amazon.it, www.amazon.es, www.amazon.ca, www.amazon.com.au, www.amazon.co.jp, www.amazon.in, www.amazon.com.br, www.amazon.com.mx, www.amazon.nl, www.amazon.pl, www.amazon.se, www.amazon.ae, www.amazon.sa, www.amazon.sg, www.amazon.com.tr, www.amazon.eg

Major US Retailers

www.walmart.com, www.costco.com, www.costco.ca, www.homedepot.com

European Retailers

allegro.pl, allegro.cz, allegro.sk, www.alza.cz, www.alza.sk, www.alza.de, www.alza.at, www.alza.hu, www.kaufland.de, www.kaufland.pl, www.kaufland.cz, www.kaufland.sk, www.kaufland.at, www.kaufland.fr, www.kaufland.it, www.cdiscount.com

IKEA (40+ country/language combinations)

Supports all major IKEA regional sites with multiple language options.

Google Shopping

Use for seller discovery across multiple stores.


Running the Extraction

Step 1: Set Skill Path

SKILL_PATH=~/.claude/skills/apify-ecommerce

Step 2: Run Script

Quick answer (display in chat):

node --env-file=~/.claude/.env $SKILL_PATH/reference/scripts/run_actor.js \
  --actor "apify/e-commerce-scraping-tool" \
  --input 'JSON_INPUT'

CSV export:

node --env-file=~/.claude/.env $SKILL_PATH/reference/scripts/run_actor.js \
  --actor "apify/e-commerce-scraping-tool" \
  --input 'JSON_INPUT' \
  --output YYYY-MM-DD_filename.csv \
  --format csv

JSON export:

node --env-file=~/.claude/.env $SKILL_PATH/reference/scripts/run_actor.js \
  --actor "apify/e-commerce-scraping-tool" \
  --input 'JSON_INPUT' \
  --output YYYY-MM-DD_filename.json \
  --format json

Step 3: Summarize Results

Report:

  • Number of items extracted
  • File location (if exported)
  • Key insights based on workflow:
    • Products: Price range, outliers, MAP violations
    • Reviews: Average rating, sentiment trends, quality issues
    • Sellers: Seller count, unauthorized sellers found

Error Handling

Error Solution
APIFY_TOKEN not found Ensure ~/.claude/.env contains APIFY_TOKEN=your_token
Actor not found Verify Actor ID: apify/e-commerce-scraping-tool
Run FAILED Check Apify console link in error output
Timeout Reduce maxProductResults or increase --timeout
No results Verify URLs are valid and accessible
Invalid marketplace Check marketplace value matches supported list exactly

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1