Merge pull request 'Fix updateCookies error + context-aware sleep (#7, #18)' (#37) from fix/cookies-error-and-context-sleep into main

playwright.go

@@ -138,6 +138,9 @@ func NewBrowser(ctx context.Context, opts ...BrowserOptions) (Browser, error) {
 func (b playWrightBrowser) updateCookies(_ context.Context, page playwright.Page) error {
 	if b.cookieJar != nil {
 		cookies, err := page.Context().Cookies(page.URL())
+		if err != nil {
+			return fmt.Errorf("error getting cookies from browser: %w", err)
+		}
 
 		for _, cookie := range cookies {
 			// TODO: add support for deleting cookies from the jar which are deleted in the browser

sites/archive/archive.go

@@ -128,15 +128,13 @@ func (c Config) Archive(ctx context.Context, b extractor.Browser, target string)
 		return nil, fmt.Errorf("failed to click submit: %w", err)
 	}
 
-	// wait for the page to load
+	// wait for the page to load, but respect context cancellation
-	time.Sleep(5 * time.Second)
-
 	select {
 	case <-ctx.Done():
-		slog.Debug("context already done before entering the loop", "err", ctx.Err())
+		slog.Debug("context done during initial wait", "err", ctx.Err())
+		_ = doc.Close()
 		return nil, ctx.Err()
-	default:
+	case <-time.After(5 * time.Second):
-		// Proceed with the loop
 	}
 	// now we are waiting for archive.ph to archive the page and redirect us to the archived page
 	// the way we can tell this is happening is by checking the url of the page periodically