Tools / Web search and scraping / Scraper
Pass an Amazon product URL (the /dp/ link) to web.scrape and get the public page as markdown: the product title, the listed price, the star rating, the rating count and the star split as a shopper sees them. RouterGrowth is independent and is not Amazon's API. It reads the public page, so the fields sit in the text, not in typed JSON.
Ask your agent
Scrape these 12 Amazon product pages and give me a table of title, price, star rating and rating count.
Connect RouterGrowth once, then ask in plain words. New workspaces start with $1 of credit. Get a key or read the setup guide.
A real run
One call to web.scrape (website scrape), run through RouterGrowth on October 26, 2026. These are the first rows it returned; fields that name a person are masked.
| field | value |
|---|---|
| title | Amazon Echo Dot (newest model) - Vibrant sounding speaker, Designed for Alexa+, Great for bedrooms, dining rooms and offices, Charcoal |
| price | $79.99 |
| rating | 4.7 out of 5 stars, 201,399 global ratings |
One scrape of the Echo Dot product page: status 200 and 145,502 characters of markdown; the rows were read from that text, where price and rating sit just under the title.
Step by step
The short form amazon.com/dp/ followed by the ASIN is enough.
Send the url. The page comes back as markdown with its title and status code.
Find the # title line, the first price after it and the out of 5 stars line, in code or with a model.
One call per product page; store the run date with each price.
Price
List prices on this call, read from the catalog when this page was built. The exact figure is quoted before every run, and a monthly plan lowers it.
In practice
You describe the job; the agent picks the calls, shows the price and runs them.
Scrape these 12 Amazon product pages and give me a table of title, price, star rating and rating count.
Find the Amazon listings that rank in Google for best smart speaker, then scrape each one for price and rating.
Connect
One MCP server for Claude, ChatGPT, Claude Code, Codex and Cursor, or the same call over the CLI and REST with the input above.
claude mcp add --transport http routergrowth https://api.routergrowth.com/mcp
npm install -g routergrowth && routergrowth setup
routergrowth run -c web.scrape -i '{"url": "https://www.amazon.com/dp/B09B8V1LZ3"}'curl -X POST https://api.routergrowth.com/v1/run \
-H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
-d '{"capability": "web.scrape", "input": {"url": "https://www.amazon.com/dp/B09B8V1LZ3"}}'Worth knowing
RouterGrowth is independent of Amazon and does not use its Product Advertising or seller APIs. It reads the public page.
A product page runs past 100,000 characters with ads, add ons and related items. Cut to the block after the title before you send it to a model.
The page shows the price at the moment of the call. Keep the date with every price you store.
FAQ
No. RouterGrowth is independent and is not Amazon's API; the call reads the public product page.
No. The price is in the markdown, as printed on the page. Parse it in code or with a model.
The rating, rating count and star split shown on the product page come through. It does not page through the full review list.
The call moves to the next provider. If none returns the page, the run fails and says why.
More on Web search and scraping
Reading this as an agent? This page as markdown: /tools/web-scraping/amazon.md
Connect your agent once. The first calls run on the $1 that comes with signup.