Предварительный рендеринг страниц для краулеров

// Only render pages you control. This prevents the Worker from becoming
// an open browser-rendering proxy for arbitrary websites.
const ALLOWED_HOSTNAMES = new Set(["example.com", "www.example.com"]);

const getTargetUrl = (request) => {
	const requestUrl = new URL(request.url);
	const target = requestUrl.searchParams.get("url");

	if (!target) {
		throw new Error("Missing url query parameter");
	}

	const targetUrl = new URL(target);

	// Only render HTTP(S) pages. Other protocols are not valid web pages.
	if (!["http:", "https:"].includes(targetUrl.protocol)) {
		throw new Error("Only HTTP and HTTPS URLs are allowed");
	}

	if (!ALLOWED_HOSTNAMES.has(targetUrl.hostname)) {
		throw new Error("This hostname is not allowed");
	}

	return targetUrl;
};

const renderHtml = async (env, targetUrl) => {
	// The /content Quick Actions endpoint loads the page in Browser Run and returns
	// a JSON envelope containing the rendered HTML in the result field.
	const response = await env.BROWSER.quickAction("content", {
		url: targetUrl.toString(),
		gotoOptions: {
			waitUntil: "networkidle2",
			timeout: 30000,
		},
		// If your page has a specific readiness signal, use waitForSelector
		// instead of relying only on network activity.
		// waitForSelector: { selector: "[data-prerender-ready='true']", timeout: 30000 },
	});

	if (!response.ok) {
		const detail = (await response.text()).slice(0, 500);
		throw new Error(`Browser Run failed with ${response.status}: ${detail}`);
	}

	const data = await response.json();

	if (!data.success || typeof data.result !== "string") {
		throw new Error("Browser Run returned an unsuccessful response");
	}

	return data.result;
};

export default {
	async fetch(request, env) {
		try {
			// Read and validate the URL before sending it to Browser Run.
			const targetUrl = getTargetUrl(request);
			const html = await renderHtml(env, targetUrl);

			// Return the rendered HTML to the crawler or integration.
			return new Response(html, {
				headers: {
					"content-type": "text/html; charset=utf-8",
				},
			});
		} catch (error) {
			return Response.json(
				{ error: error instanceof Error ? error.message : "Unknown error" },
				{ status: 400 },
			);
		}
	},
};

interface Env {
	BROWSER: BrowserRun;
}

// Only render pages you control. This prevents the Worker from becoming
// an open browser-rendering proxy for arbitrary websites.
const ALLOWED_HOSTNAMES = new Set(["example.com", "www.example.com"]);

const getTargetUrl = (request: Request) => {
	const requestUrl = new URL(request.url);
	const target = requestUrl.searchParams.get("url");

	if (!target) {
		throw new Error("Missing url query parameter");
	}

	const targetUrl = new URL(target);

	// Only render HTTP(S) pages. Other protocols are not valid web pages.
	if (!["http:", "https:"].includes(targetUrl.protocol)) {
		throw new Error("Only HTTP and HTTPS URLs are allowed");
	}

	if (!ALLOWED_HOSTNAMES.has(targetUrl.hostname)) {
		throw new Error("This hostname is not allowed");
	}

	return targetUrl;
};

const renderHtml = async (env: Env, targetUrl: URL) => {
	// The /content Quick Actions endpoint loads the page in Browser Run and returns
	// a JSON envelope containing the rendered HTML in the result field.
	const response = await env.BROWSER.quickAction("content", {
		url: targetUrl.toString(),
		gotoOptions: {
			waitUntil: "networkidle2",
			timeout: 30000,
		},
		// If your page has a specific readiness signal, use waitForSelector
		// instead of relying only on network activity.
		// waitForSelector: { selector: "[data-prerender-ready='true']", timeout: 30000 },
	});

	if (!response.ok) {
		const detail = (await response.text()).slice(0, 500);
		throw new Error(`Browser Run failed with ${response.status}: ${detail}`);
	}

	const data = (await response.json()) as {
		success: boolean;
		result?: string;
	};

	if (!data.success || typeof data.result !== "string") {
		throw new Error("Browser Run returned an unsuccessful response");
	}

	return data.result;
};

export default {
	async fetch(request, env): Promise<Response> {
		try {
			// Read and validate the URL before sending it to Browser Run.
			const targetUrl = getTargetUrl(request);
			const html = await renderHtml(env, targetUrl);

			// Return the rendered HTML to the crawler or integration.
			return new Response(html, {
				headers: {
					"content-type": "text/html; charset=utf-8",
				},
			});
		} catch (error) {
			return Response.json(
				{ error: error instanceof Error ? error.message : "Unknown error" },
				{ status: 400 },
			);
		}
	},
} satisfies ExportedHandler<Env>;