Generate a change-tracking scraper for mall directory screens

Arturo Montesinos described a project to ChatGPT and got back a working 527-line Python tool in a ZIP; after one fix it became Curaflow 1.0, which has fed his mall directory screens for a year.

Done withChatGPTGitHub CopilotClaude Code· Nov 12, 2026

What they did

Montesinos maintains content for touch-screen directories in shopping centres and used three scripts that refetched and rebuilt everything on every run. In September 2025 he described to ChatGPT, running GPT-5, a reusable replacement: fetch shop data from the web into YAML, skip unchanged sources, declare dependencies, rebuild only what changed, fetch in parallel and report changes. He expected a design discussion. Instead ChatGPT returned a ZIP with a working skeleton, and a second ZIP with hierarchical fetching when he raised that need. He committed the second ZIP the next morning. GitHub Copilot then helped him tidy, extend and release it, and in November 2026 Claude Code compared the ZIP with the first commit and re-ran the original code against a small test site.

How it went

The committed Python matched the ZIP line for line: 527 lines in nine files. It needed one fix, because it called a Typer function that does not exist. Later cleanup with Copilot added 1,642 lines on day one and introduced two bugs of its own: plugins that were never imported, so runs silently did nothing while checks passed, and a packaging config that left the plugins out of the wheel. Both were fixed by version 1.0.0 on New Year's Eve 2025. He says it has run flawlessly for nearly a year, checking a mall site several times a day and triggering alert emails when tenants change. A planned rules engine and parallel builds were never implemented.

Worth knowing

The generated code worked; the human-directed refactoring is what broke it, and tests did not catch the regression. The article itself was written by ChatGPT from conversations with him, with a closing note in his own words. The code is open source under MIT.

Try it

With ChatGPT· 5 parts to fill in

I want a small reusable command-line tool in [Python]. It should fetch data from [list of sites or APIs], including pages discovered from index pages, normalise it into [YAML or JSON], skip sources that have not changed using HTTP caching and content hashes, rebuild only the output files whose declared inputs changed, fetch up to [10] sources in parallel, and print a report of what changed. Write the code, a sample config for [my use case] and tests that run against a local test site. Run the tests and stop when they pass, then list anything you planned but did not build.

Square brackets are the parts to fill in. The prompt is ours; the story is theirs.

Where they said it

Related