yt package change

main.py

@@ -8,7 +8,8 @@ import os
 import requests
 from bs4 import BeautifulSoup
 import validators
-from youtube_transcript_api import YouTubeTranscriptApi
+import yt_dlp
+# from youtube_transcript_api import YouTubeTranscriptApi
 # from cachetools import TTLCache
 # import asyncio
 # import hashlib
@@ -200,36 +201,72 @@ def genetate_gemini_content(prompt,content):
     response=model.generate_content([prompt,content])
     return response.text
 
-def extract_transcript(youtube_link):
-    transcript = "" 
-    ytt_api = YouTubeTranscriptApi()
+# def extract_transcript(youtube_link):
+#     transcript = "" 
+#     ytt_api = YouTubeTranscriptApi()
 
-    try:
-        if not validators.url(youtube_link):
-            return 400, "Enter correct URL"
+#     try:
+#         if not validators.url(youtube_link):
+#             return 400, "Enter correct URL"
 
         
-        if "youtu.be/" in youtube_link:
-            video_id = youtube_link.split("youtu.be/")[1].split("?")[0]
-        else:
-            video_id = youtube_link.split("v=")[1].split("&")[0]
+#         if "youtu.be/" in youtube_link:
+#             video_id = youtube_link.split("youtu.be/")[1].split("?")[0]
+#         else:
+#             video_id = youtube_link.split("v=")[1].split("&")[0]
 
         
-        transcript_data = ytt_api.fetch(video_id)
-        print(transcript_data)
+#         transcript_data = ytt_api.fetch(video_id)
+#         print(transcript_data)
 
         
-        for i in transcript_data.snippets:
-            transcript += " " + i.text
+#         for i in transcript_data.snippets:
+#             transcript += " " + i.text
 
-        return 200, transcript.strip()
+#         return 200, transcript.strip()
 
-    except Exception as e:
-        print("Transcript error:", e)
-        return 404, "No information available"
+#     except Exception as e:
+#         print("Transcript error:", e)
+#         return 404, "No information available"
 
 
-    
+
+
+def extract_transcript(url):
+    transcript = ""
+
+    try:
+        ydl_opts = {
+            "skip_download": True,
+            "quiet": True,
+            "writesubtitles": True,
+            "writeautomaticsub": True,
+            "subtitlesformat": "vtt",
+            "subtitleslangs": ["en"],
+        }
+
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(url, download=False)
+            subs = info.get("subtitles") or info.get("automatic_captions")
+
+            if not subs or "en" not in subs:
+                return 404, "No transcript available"
+
+            vtt_url = subs["en"][0]["url"]
+
+            # download VTT
+            import requests
+            vtt_data = requests.get(vtt_url).text
+
+            # convert VTT → text
+            text = "\n".join([line for line in vtt_data.split("\n") if "-->" not in line and line.strip()])
+            
+            return 200, text
+
+    except Exception as e:
+        print("Error:", e)
+        return 404, "No transcript available"
+