Playwright

Playwright adds rendered web page extraction for pages that need browser execution before their content can be read.

Tools

Tool	Purpose
web-page-content-extractor	Fetch a web page and extract its main text content.

web-page-content-extractor Inputs

Input	Required	Description
url	yes	HTTP or HTTPS URL to fetch.

Properties

Required Playwright properties:

Variable	Description
LIGHTFLARE_TOOLS_PLAYWRIGHT_ENABLED	Set to true.
LIGHTFLARE_TOOLS_PLAYWRIGHT_ENABLED_TOOLS	Comma-separated tool allowlist. Use web-page-content-extractor.

Optional Properties

Variable	Default	Description
LIGHTFLARE_TOOLS_PLAYWRIGHT_ENABLED_TOOLS	[]	Exposed Playwright tools. Empty exposes no Playwright tools.
LIGHTFLARE_TOOLS_PLAYWRIGHT_WORKER_COUNT	2	Playwright worker count.
LIGHTFLARE_TOOLS_PLAYWRIGHT_MAX_PENDING_TASKS_PER_WORKER	8	Max queued Playwright tasks per worker.
LIGHTFLARE_TOOLS_PLAYWRIGHT_QUEUE_ACQUIRE_TIMEOUT_MS	1000	Playwright queue acquire timeout.
LIGHTFLARE_TOOLS_PLAYWRIGHT_PAGE_TIMEOUT_MS	10000	Playwright page timeout.
LIGHTFLARE_TOOLS_PLAYWRIGHT_HEADLESS	true	Run Playwright headless.
LIGHTFLARE_TOOLS_PLAYWRIGHT_ACCEPT_DOWNLOADS	false	Allow Playwright downloads.
LIGHTFLARE_TOOLS_PLAYWRIGHT_BLOCK_PRIVATE_NETWORK_TARGETS	true	Block private network browser targets.
LIGHTFLARE_TOOLS_PLAYWRIGHT_ALLOWED_SCHEMES	http,https	Allowed URL schemes.
LIGHTFLARE_TOOLS_PLAYWRIGHT_ALLOWED_HOSTS	[]	Host allowlist. Empty allows all hosts permitted by the URL policy.