extract_youtube_id

app.py

@@ -15,6 +15,9 @@ import os
 from google.oauth2 import service_account
 from googleapiclient.discovery import build
 
+from urllib.parse import urlparse, parse_qs
+
+
 # 假设您的环境变量或Secret的名称是GOOGLE_APPLICATION_CREDENTIALS_JSON
 credentials_json_string = os.getenv("GOOGLE_APPLICATION_CREDENTIALS_JSON")
 credentials_dict = json.loads(credentials_json_string)
@@ -86,10 +89,24 @@ def format_seconds_to_time(seconds):
     seconds = int(seconds % 60)
     return f"{hours:02}:{minutes:02}:{seconds:02}"
 
+def extract_youtube_id(url):
+    parsed_url = urlparse(url)
+    
+    if "youtube.com" in parsed_url.netloc:
+        # 对于标准链接，视频ID在查询参数'v'中
+        query_params = parse_qs(parsed_url.query)
+        return query_params.get("v")[0] if "v" in query_params else None
+    elif "youtu.be" in parsed_url.netloc:
+        # 对于短链接，视频ID是路径的一部分
+        return parsed_url.path.lstrip('/')
+    else:
+        return None
+
 def process_youtube_link(link):
     # 使用 YouTube API 获取逐字稿
     # 假设您已经获取了 YouTube 视频的逐字稿并存储在变量 `transcript` 中
-    video_id = link.split("=")[-1]
+    video_id = extract_youtube_id(link)
+
     # 先下載 video
     download_youtube_video(video_id, output_path=OUTPUT_PATH)
     # 再取得 transcript