Terminal
Terminal/Skill
Compares a product's price and stock across Amazon, Walmart, eBay, Best Buy, and Google Shopping, then recommends where to buy.
By Bright Data
Works with
npx skills add brightdata/skills --skill price-comparisonFind the best place to actually buy a product — lowest price, in stock, from a
reputable seller — using live retailer data, not stale training knowledge.
Combines the Bright Data CLI (bdata) for collection with a normalization +
ranking layer to deliver a single cited comparison table and a clear buy
recommendation.
Never quote prices from training knowledge. Prices and stock change hourly. Always pull live data first, then compare. If a source fails, say so — never fill a price gap with a guess.
curl -fsSL https://cli.brightdata.com/install.sh | bash
bdata login # or: bdata login --device (SSH / headless)
Verify before collecting:
if ! command -v bdata >/dev/null 2>&1; then
echo "bdata CLI not installed — see skills/bright-data-best-practices/references/cli-setup.md"
elif ! bdata zones >/dev/null 2>&1; then
echo "bdata not authenticated — run: bdata login"
fi
Halt and route to setup if either check fails.
amazon_product_search and bdata search --type shopping to resolve it to
concrete product URLs/offers, then pull each retailer's structured data.
Parallelize independent calls.amazon_product_search "<query>" "https://www.amazon.com" and
bdata search "<product>" --type shopping --json to find the exact items,
then feed those URLs to product pipelines.bdata scrape amazon.com — Amazon
blocks scrapers; the pipeline bypasses that reliably.--json when you need to parse or compare output.bdata calls, not 50.
Pull the offers the user asked about, not every seller on the page.Pick the retailers that fit the product and region. US electronics → Amazon + Best Buy + Walmart + Google Shopping; marketplace/used → eBay; non-US → confirm the local Amazon domain and add region-relevant retailers.
bdata pipelines amazon_product "https://www.amazon.com/dp/<ASIN>" --json -o amazon.json
Returns price, final_price, title, availability, rating, review count, ASIN,
seller, images. Use the right domain for the region (amazon.com, amazon.de,
amazon.co.uk, …).
bdata pipelines amazon_product_search "iPhone 17 Pro 256GB" "https://www.amazon.com" --json -o amzn_search.json
Resolve the right ASIN/URL from the results, then call amazon_product on it.
bdata pipelines walmart_product "https://www.walmart.com/ip/<ID>" --json -o walmart.json
bdata pipelines ebay_product "https://www.ebay.com/itm/<ID>" --json -o ebay.json
bdata pipelines bestbuy_products "https://www.bestbuy.com/site/<ID>.p" --json -o bestbuy.json
bdata pipelines google_shopping "<google-shopping-product-url>" --json -o gshopping.json
Best for a fast multi-seller view once you have a Shopping product URL. To find that URL (and a quick price spread) from a name, use SERP shopping:
bdata search "iPhone 17 Pro 256GB" --type shopping --country us --json
bdata scrape "https://retailer.example/product-page"
Then extract price, currency, and stock from the markdown. Use this for local retailers without a dedicated pipeline (e.g. regional electronics chains).
Pipeline names are inconsistent (
amazon_productsingular,bestbuy_productsplural,walmart_product). Confirm with the type list before hardcoding — thedata-feedsskill has the verified list, and keyword/multi-arg pipelines (amazon_product_search) take<keyword> <domain_url>, not a single URL.
--country <code> to bdata search for localized SERP/shopping
results (e.g. --country il for Israel, de, uk).amazon.com with international shipping and via local chains —
cover both and label shipping/import implications.Read references/output-and-pricing.md for: