Use Web Fetch to extract content from a public webpage as structured JSON without creating a Browser Session. Use Web Fetch to extract the main text, links, images, and other content from a public webpage as structured JSON without creating a Browser Session, ready for integration into knowledge bases or data pipelines.
Prerequisite:
Fetch and fully execute the official Lexmount Setup Prompt returned by https://browser.lexmount.com/api/agent-setup/webfetch-cli.
Continue only after installation, authentication, and environment validation all pass; otherwise stop and report the failure truthfully.
Task:
Use webfetch-cli only to extract https://docs.python.org/3/tutorial/introduction.html as structured JSON and save it in artifacts/python-introduction.json.
Data:
Preserve the requested URL, final URL, status code, title, description, body, author, publication time, language, links, images, engine, timing, and warnings. Use null, an empty string, or an empty array for missing fields, and never invent data.
Constraints:
Do not create a Browser Session or switch to a local crawler, custom browser code, Playwright, Puppeteer, or an SDK. If the page requires login or human interaction, report that the task is not applicable.
Acceptance:
The command must succeed and the result must be non-empty, parseable JSON. The title must contain "Introduction to Python," the body must be non-empty, and the language must indicate English when available. The generated JSON must be available as a clickable file in the final Codex response. Report timeouts, API errors, non-JSON responses, or missing structured results truthfully.
Return:
Report only the status, final URL, title, key-field count, warnings, and sanitized error summary, then provide the generated JSON file as the final item. Never return only a plain-text file path. Do not expose API keys, authentication data, or internal connection URLs.