From 2b1f7a511fdf77ec2ea390adb327a487dd7a08da Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Thu, 17 Sep 2026 11:05:49 +0000
Subject: [PATCH] =?UTF-8?q?=E2=9A=A1=20optimize=20transcript=20processing?=
 =?UTF-8?q?=20in=20app.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Eliminate redundant iteration over transcript data by building both
timestamped and simple text formats in a single pass. This reduces
O(n) overhead and improves architectural efficiency.

Co-authored-by: ertugerata <225387+ertugerata@users.noreply.github.com>
---
 app.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/app.py b/app.py
index be7fb3f..ad8478d 100644
--- a/app.py
+++ b/app.py
@@ -125,12 +125,14 @@ def get_transcript(video_id, language='tr'):
         print(f"Transkript verisi alındı: {len(transcript_data)} satır")
         
         full_transcript = []
+        simple_text_parts = []
         for item in transcript_data:
             timestamp = format_timestamp(item.start)
             text = item.text
             full_transcript.append(f"[{timestamp}] {text}")
+            simple_text_parts.append(text)
         
-        simple_text = ' '.join([item.text for item in transcript_data])
+        simple_text = ' '.join(simple_text_parts)
         
         return {
             'full_text': '\n'.join(full_transcript),