GitHub projects or visible Amazon price scraping with source-linked results
Give this Amazon price scraper a focused list of product or search URLs. Your coding agent opens them in visible browser Spaces and returns each displayed price with the offer details and source page you need to verify it. If you are comparing a GitHub Amazon scraper with a local browser workflow, this page makes the trade-off explicit: code projects need their own runtime and maintenance, while ego(lite) works in the browser context you authorize. In the recorded demo, ten parallel Spaces produced a validated 100-row CSV. Use this workflow only for sources and methods you are authorized to automate.
Please use /ego-browser to record the displayed price and offer details for , with the source page and check time in a CSV.
A GitHub Amazon scraper can be a useful starting point for learning or building a controlled integration, but it still needs a runtime, dependency updates, error handling, and a source agreement that allows the collection. For a focused, authorized run, give your agent the Amazon URLs and fields you need: ego(lite) opens each group in its own Space, records the offer details on screen, and returns a source-linked CSV or Markdown report for review.
Download ego(lite) and choose a Chrome profile you are authorized to use. Keep the marketplace, delivery location, and account state consistent throughout the run, because those details can change the offer Amazon shows.
Paste Amazon product URLs, a search results page, or a Best Sellers list into one prompt for Codex or Claude Code. Tell the agent which fields to collect, such as the displayed price, list price, coupon, seller, selected variant, currency, and availability text. Then choose CSV or Markdown and tell it to stop when Amazon asks for sign-in, a robot check, or another human decision.
Your agent opens each product or search page in its own ego(lite) Space and records the values the page visibly displays, including the selling price, list price, seller, selected variant, and availability text. The browser stays visible the whole time, so you can see exactly which page state supplied each price.
Give each search, category, marketplace, or product list its own Space and let your agent run them side by side. Keep working in your own tabs while the price collections continue, then open any Space to check progress, pause a task, or take over when Amazon needs you.
Open the finished CSV or Markdown report to compare every price with its source URL, seller, selected variant, marketplace context, and check time. Prices are copied exactly as the page displayed them, unavailable fields stay marked instead of guessed, and you can rerun the same list later to compare what changed between checks.
Use the coding agent you already have in a local browser you can inspect. Parallel Spaces reduce waiting, every report row keeps its source, and ego(lite) has no browser subscription or per-row fee. Your usual Agent or model costs can still apply.
Across our 31-task benchmark on live sites, ego(lite) averaged 398 seconds per task against 605 for agent-browser, 52% faster. ego(lite) uses page snapshots, direct browser actions, and parallel Spaces. Timing varies by Amazon page, list size, workflow, and network conditions.
Open each Amazon search or product group in a separate Space. Several lists can run side by side, and every row still points to the page that supplied it. That lets you compare more offers without losing track of the seller, variant, or marketplace.
Open any Space to watch the agent work, check the active offer, or take over. If the task reaches sign-in, a robot check, a CAPTCHA, or another human decision, your stop rule keeps the agent from pushing past it. You decide what happens next.
ego(lite) runs the browser locally and can optionally import the Chrome profile you choose during setup. Your agent reads the offer shown in that browser context. The report keeps the marketplace, delivery context, seller, variant, and check time that explain the price.
Amazon's Conditions of Use and robots directives may restrict automated collection. Confirm that your source and method are allowed before you run the workflow. If permission is unclear or the page blocks access, stop and use an official API, licensed feed, or another authorized source.
Collect the offer details shown on screen, with a source you can revisit.
This workflow does not bypass access controls, invent missing data, make purchases, or run as an always-on monitor.
Give your agent the Amazon URLs and price fields that matter. ego(lite) opens the work in visible Spaces and returns each price with its seller, variant, source URL, check time, and status, ready for review or comparison.