AI coding mission · Web scraper

Generate a Python web scraper that saves data to CSV

Describe the public page and the fields you want, then create a scraper project rather than a single code snippet. A PlushCrew Mission can produce a fetcher, a parser, CSV output and tests. Inspect those files in your browser and read the test results before running the downloaded project.

Try this mission free

Fills the task box; you choose when to send. Guest access: 1 mission per IP in a rolling 24 hours.

Describe the result you need

Give the agents the target page, field names and a small representative HTML sample when possible. Explain whether results span multiple pages and how pagination works. A good project separates the network request from the parser so parsing can be tested against fixed HTML without contacting a live website on every test run. Include the output column order you need.

Example prompt

Build a Python web scraper that saves product name, price, and URL to CSV. Keep fetching separate from parsing, add a request timeout and polite delay, handle missing prices, and test the parser with saved HTML fixtures.

Example project files and output

The exact files depend on your request. A project for this prompt could include:

scraper.pyPage fetching, parsing and CSV export with a command-line interface.
tests/test_scraper.pyTests for selectors, missing fields and failed requests.
requirements.txtDependencies needed when you run the downloaded project.

name,price,url
Example Notebook,12.50,https://example.com/products/notebook
Example Pen,2.00,https://example.com/products/pen

Illustrative CSV output using fictional products and example.com URLs; this is not scraped customer data.

What to check in the tests

Review the test output in the mission report and open the generated test files. Useful checks for this task include:

A saved HTML fixture produces the expected columns and product count.
Missing fields and malformed prices do not silently corrupt the CSV.
Timeouts and HTTP failures produce an understandable error instead of hanging.

Passing tests show what the supplied cases covered. They do not guarantee that every input will work or that generated code is safe.

Inputs and limitations

Choose pages you are allowed to access and respect their access rules. A JavaScript-rendered site may need a browser-based approach rather than a simple HTTP request. Parser tests against fixtures do not prove that a live site is reachable or that its layout will stay unchanged. Tell the agents about these constraints and inspect the generated approach before using it.

Review first, then download

Use Mission for a new project. The existing agent pipeline, sandbox and logic checks run as usual. Open each file in the browser, expand the report to inspect test results, then download the ZIP to use the project locally. A dispatched guest mission consumes the free slot even if it fails or you cancel it.

Chat is for questions; guests have five messages per IP in a rolling 24-hour window. For fixing an existing codebase, Audit accepts a code ZIP from a Pro Max account. See plans and limits for account details.

Fill this example task