From 78301ee63d4927016764407bbeeb8a0ee28c1cb7 Mon Sep 17 00:00:00 2001
From: Esparon1 <136267691+Esparon1@users.noreply.github.com>
Date: Mon, 6 May 2024 18:31:04 +0100
Subject: [PATCH] Add feature to extract timestamps from youtube videos (#1345)

---
 embedchain/loaders/youtube_video.py | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/embedchain/loaders/youtube_video.py b/embedchain/loaders/youtube_video.py
index 764a7d2a..ff0c4d90 100644
--- a/embedchain/loaders/youtube_video.py
+++ b/embedchain/loaders/youtube_video.py
@@ -1,5 +1,12 @@
 import hashlib
-
+import json
+import logging
+try:
+    from youtube_transcript_api import YouTubeTranscriptApi
+except ImportError:
+    raise ImportError(
+        'YouTube video requires extra dependencies. Install with `pip install youtube-transcript-api "`'
+    )
 try:
     from langchain_community.document_loaders import YoutubeLoader
 except ImportError:
@@ -25,6 +32,18 @@ class YoutubeVideoLoader(BaseLoader):
         metadata = doc[0].metadata
         metadata["url"] = url
 
+
+        video_id = url.split("v=")[1].split('&')[0]
+        try:
+            # Fetching transcript data
+            transcript = YouTubeTranscriptApi.get_transcript(video_id,languages=['en'])
+            # convert transcript to json to avoid unicode symboles
+            metadata["transcript"] = json.dumps(transcript, ensure_ascii=True)
+        except Exception as e:
+            logging.exception(f"Failed to fetch transcript for video {url}")
+            metadata["transcript"] = "Unavailable"   
+
+
         output.append(
             {
                 "content": content,