scrape

SKILL.md

Bright Data — Scrape

Get clean content (markdown, HTML, JSON, screenshot) from one or more URLs via the Bright Data CLI. This skill owns the "fetch raw or lightly-structured content" job. For platform-specific structured data (Amazon, LinkedIn, TikTok, etc.), stop and use data-feeds instead — you'll get clean JSON without selector logic.

Setup gate (run first)

Before any scrape, verify the CLI is installed and authenticated:

if ! command -v bdata >/dev/null 2>&1; then
    echo "bdata CLI not installed — see bright-data-best-practices/references/cli-setup.md"
elif ! bdata zones >/dev/null 2>&1; then
    echo "bdata not authenticated — run: bdata login  (or: bdata login --device for SSH)"
fi

If either check fails, halt and route the user to skills/bright-data-best-practices/references/cli-setup.md. Do not attempt the legacy curl fallback silently — ask the user first.

Pick your path