feat: playwright-adblocked toggle #1298 (#1301)

* feat: playwright-adblocked toggle

* lint

* Update src/lib/server/websearch/scrape/playwright.ts

Co-authored-by: Nathan Sarrazin <[email protected]>

* replace regex with equality check

---------

Co-authored-by: Nathan Sarrazin <[email protected]>

.env

@@ -27,6 +27,7 @@ SERPSTACK_API_KEY=#your serpstack api key here
 SEARCHAPI_KEY=#your searchapi api key here
 USE_LOCAL_WEBSEARCH=#set to true to parse google results yourself, overrides other API keys
 SEARXNG_QUERY_URL=# where '<query>' will be replaced with query keywords see https://docs.searxng.org/dev/search_api.html eg https://searxng.yourdomain.com/search?q=<query>&engines=duckduckgo,google&format=json
+PLAYWRIGHT_ADBLOCKER=true
 
 WEBSEARCH_ALLOWLIST=`[]` # if it's defined, allow websites from only this list.
 WEBSEARCH_BLOCKLIST=`[]` # if it's defined, block websites from this list.

src/lib/server/websearch/scrape/playwright.ts

@@ -65,7 +65,7 @@ export async function withPage<T>(
 
 	try {
 		const page = await ctx.newPage();
-		await blocker.enableBlockingInPage(page);
+		process.env.PLAYWRIGHT_ADBLOCKER === "true" && (await blocker.enableBlockingInPage(page));
 
 		const res = await page.goto(url, { waitUntil: "load", timeout: 3500 }).catch(() => {
 			console.warn(`Failed to load page within 2s: ${url}`);