Upload 57 files

src/utils/helper.py

@@ -11,6 +11,7 @@ from youtube_transcript_api import YouTubeTranscriptApi
 from youtube_comment_downloader import YoutubeCommentDownloader
 from src.utils.logger import logger
 import requests
+import os
 
 State = TypeVar("State", bound=Dict[str, Any])
 
@@ -108,29 +109,34 @@ async def preprocess_messages(query: str, attachs: list[UploadFile]):
     return messages
 
 
+def extract_video_id(video_link: str):
+
+    return video_link.replace("\u2069", "").split("v=")[1].strip()
+
+
 # def extract_transcript(video_link: str):
 #     ytt_api = YouTubeTranscriptApi()
 #     # extract video id from video link
-#     video_id = video_link.split("v=")[1]
+
+#     video_id = extract_video_id(video_link)
+#     logger.info(f"Video ID: {video_id}")
 #     transcript = ytt_api.fetch(video_id)
 #     transcript_str = ""
 #     for trans in transcript:
 #         transcript_str += trans.text + " "
 #     logger.info(f"Transcript: {transcript_str}")
 #     return transcript_str
-def extract_video_id(video_link: str):
 
-    return video_link.replace("\u2069", "").split("v=")[1].strip()
-import os
+
 def extract_transcript(video_link: str):
     try:
         # extract video id from video link
         video_id = extract_video_id(video_link)
-        
+
         api_key = os.getenv("SUPADATA_API_KEY")
         if not api_key:
             raise ValueError("SUPADATA_API_KEY environment variable is not set")
-        
+
         # Call Supadata API
         url = f"https://api.supadata.ai/v1/youtube/transcript"
         headers = {
@@ -139,20 +145,20 @@ def extract_transcript(video_link: str):
         params = {
             "videoId": video_id
         }
-        
+
         response = requests.get(url, headers=headers, params=params)
         response.raise_for_status()  # Raise exception for non-200 status codes
-        
+
         data = response.json()
         logger.info(f"Data: {data}")
         if not data.get("content"):
             raise ValueError("No transcript content found in the API response")
-            
+
         text = ""
         for item in data["content"]:
             if "text" in item:
                 text += item["text"] + " "
-        
+
         logger.info(f"Transcript: {text}")
         return text
     except requests.exceptions.RequestException as e: