chore: Update everything

youtube_transcript_v2.py

@@ -0,0 +1,99 @@
+#!/usr/bin/env -S uv run --script
+# /// script
+# dependencies = [
+#   "youtube-transcript-api",
+# ]
+# ///
+
+import argparse
+import logging
+import sys
+from pathlib import Path
+from urllib.parse import urlparse, parse_qs
+
+from youtube_transcript_api import YouTubeTranscriptApi
+
+
+logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s: %(message)s")
+
+
+def extract_video_id(url: str) -> str:
+    parsed = urlparse(url)
+
+    if parsed.hostname in ("youtu.be", "www.youtu.be"):
+        return parsed.path.lstrip("/")
+
+    if parsed.hostname in ("youtube.com", "www.youtube.com", "m.youtube.com"):
+        if parsed.path == "/watch":
+            return parse_qs(parsed.query)["v"][0]
+        elif parsed.path.startswith("/embed/"):
+            return parsed.path.split("/")[2]
+        elif parsed.path.startswith("/v/"):
+            return parsed.path.split("/")[2]
+
+    raise ValueError(f"Could not extract video ID from URL: {url}")
+
+
+def format_timestamp(seconds: float) -> str:
+    hours = int(seconds // 3600)
+    minutes = int((seconds % 3600) // 60)
+    secs = int(seconds % 60)
+    millis = int((seconds % 1) * 1000)
+    return f"{hours:02d}:{minutes:02d}:{secs:02d},{millis:03d}"
+
+
+def transcript_to_srt(transcript: list[dict]) -> str:
+    srt_lines = []
+    for i, entry in enumerate(transcript, start=1):
+        start_time = format_timestamp(entry["start"])
+        end_time = format_timestamp(entry["start"] + entry["duration"])
+        text = entry["text"]
+
+        srt_lines.append(f"{i}")
+        srt_lines.append(f"{start_time} --> {end_time}")
+        srt_lines.append(text)
+        srt_lines.append("")
+
+    return "\n".join(srt_lines)
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Fetch YouTube video transcripts",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
+    parser.add_argument("url", help="YouTube video URL")
+    parser.add_argument(
+        "--save-srt",
+        type=Path,
+        metavar="FILE_PATH",
+        help="Save transcript as SRT file to the specified path",
+    )
+    return parser.parse_args()
+
+
+def main() -> None:
+    args = parse_args()
+
+    try:
+        video_id = extract_video_id(args.url)
+        logging.info(f"Fetching transcript for video ID: {video_id}")
+
+        ytt_api = YouTubeTranscriptApi()
+        transcript = ytt_api.fetch(video_id)
+
+        if args.save_srt:
+            srt_content = transcript_to_srt(transcript.to_raw_data())
+            args.save_srt.write_text(srt_content)
+            logging.info(f"SRT file saved to: {args.save_srt}")
+        else:
+            text = "\n".join(snippet.text for snippet in transcript)
+            print(text)
+
+    except Exception as e:
+        logging.error(f"Failed to fetch transcript: {e}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()