feat: transcribe_yt_video.py

youtube/transcribe_yt_video.py

@@ -0,0 +1,24 @@
+from youtube_transcript_api import YouTubeTranscriptApi
+import os
+
+video_id = "VIDEO_ID_HERE"  # e.g., 'dQw4w9WgXcQ'
+transcript = YouTubeTranscriptApi.get_transcript(video_id)
+
+# Create output directory if it doesn't exist
+output_dir = "captions"
+if not os.path.exists(output_dir):
+    os.makedirs(output_dir)
+
+# Write each caption segment to separate numbered files
+for i, entry in enumerate(transcript, 1):
+    filename = f"cc{i}.txt"
+    filepath = os.path.join(output_dir, filename)
+    
+    with open(filepath, "w", encoding="utf-8") as f:
+        f.write(entry['text'])
+    
+    print(f"Written: {filename} - {entry['text'][:50]}...")
+
+print(f"\nTotal segments: {len(transcript)}")
+print(f"Files saved in: {output_dir}/")
+