fix: getLinkWithPuppeteer timeout

sjdonado · Nov 24, 2024 · 9fef2e7 · 9fef2e7
1 parent 3c4282d
commit 9fef2e7
Show file tree

Hide file tree

Showing 2 changed files with 43 additions and 23 deletions.
diff --git a/src/adapters/youtube.ts b/src/adapters/youtube.ts
@@ -49,6 +49,8 @@ export async function getYouTubeLink(query: string, metadata: SearchMetadata) {
       };
     });
 
+    return; // TEMPFIX: youtube is blocked
+
     const link = await getLinkWithPuppeteer(
       url.toString(),
       'ytmusic-card-shelf-renderer a',

diff --git a/src/utils/scraper.ts b/src/utils/scraper.ts
@@ -10,42 +10,60 @@ async function launchBrowser(): Promise<Browser> {
   return browser;
 }
 
+async function withTimeout<T>(promise: Promise<T>, timeout: number): Promise<T> {
+  return Promise.race([
+    promise,
+    new Promise<never>((_, reject) =>
+      setTimeout(() => reject(new Error('Operation timed out')), timeout)
+    ),
+  ]);
+}
+
 export async function getLinkWithPuppeteer(
   url: string,
   linkQuerySelector: string,
-  cookies: CookieParam[] = []
+  cookies: CookieParam[] = [],
+  timeout: number = 4000 // Default timeout of 4 seconds
 ) {
   const browser = await launchBrowser();
   const page: Page = await browser.newPage();
 
-  await page.setUserAgent(
-    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:124.0) Gecko/20100101 Firefox/124.0'
-  );
+  try {
+    await page.setUserAgent(
+      'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:124.0) Gecko/20100101 Firefox/124.0'
+    );
 
-  await page.setCookie(...cookies);
-  await page.setRequestInterception(true);
+    await page.setCookie(...cookies);
+    await page.setRequestInterception(true);
 
-  page.on('request', request => {
-    if (request.resourceType() === 'image') {
-      request.abort();
-    } else {
-      request.continue();
-    }
-  });
+    page.on('request', request => {
+      if (request.resourceType() === 'image') {
+        request.abort();
+      } else {
+        request.continue();
+      }
+    });
 
-  await page.setViewport({ width: 768, height: 600 });
-  await page.goto(url, { waitUntil: 'networkidle0' });
+    await page.setViewport({ width: 768, height: 600 });
 
-  const href = await page.evaluate(
-    // eslint-disable-next-line
-    // @ts-ignore
-    selector => document.querySelector(selector)?.href,
-    linkQuerySelector
-  );
+    // Use timeout for the page.goto operation
+    await withTimeout(page.goto(url, { waitUntil: 'networkidle0' }), timeout);
 
-  page.close();
+    // Use timeout for the page.evaluate operation
+    const href = await withTimeout(
+      page.evaluate(
+        // eslint-disable-next-line
+        // @ts-ignore
+        selector => document.querySelector(selector)?.href,
+        linkQuerySelector
+      ),
+      timeout
+    );
 
-  return href;
+    return href;
+  } finally {
+    page.close();
+  }
 }
 
 export function getCheerioDoc(html: string) {