Skip to content
agentusehub
Sign in+ Submit
Research & KnowledgeAny

Have Claude collect names from a Wikipedia page into a file

The poster tried Claude Computer Use to open Firefox, search Wikipedia, find all names on a page and save them to a text file.

Read the experience
Time saved
Not reported
Setup time
Not reported
Running cost
Not reported
Cost range
Not reported

Use case overview

The poster tried Claude Computer Use to open Firefox, search Wikipedia, find all names on a page and save them to a text file.

Read the original report ↗

Reported experience

  1. What they did

    The poster used Claude Computer Use to control Firefox, go to Wikipedia, search for a topic, then identify all the names on the page and save them into a text file. From the comments, they ran Anthropic’s provided Docker image locally with their API key, and the task completed in about a minute with no manual editing described.

  2. How it went

    It seemed to work for this simple extraction task. The main downside was cost: the run used nearly 100,000 tokens and cost about $0.31, which the poster felt was too expensive for hobby use.

  3. Worth knowing

    The clearest catch is cost from screenshots: this trivial, roughly one-minute run was already about 31 cents.

Example prompts

Try with Claude computer use
Open [browser] and go to the Wikipedia page for [topic]. Find every person's name mentioned on the page and save them, one per line with no duplicates, to a text file called [filename] in [folder]. Then tell me how many names you found and stop.

Related use cases

Research & Knowledge

Analyze 170k LLM logs overnight

A user left a Gemini agent running overnight to analyze 170k LLM logs with the llm CLI and a free model, and it finished the job despite limits.

Gemini