hermes-agent/skills/media/youtube-content/scripts/fetch_transcript.py
ethernet 5e4a2a3d24 refactor(pm): remove legacy dependency and launch managers
Competing installers and checkout-local venv assumptions bypassed PM
selection, install consent, and generation lifetimes. Route consumers
through PM and installation-bound launchers. Refresh source launchers
before obsolete Python entries can be collected.

Remove Node, browser, and CUA acquisition engines, obsolete venv-holder
handling, detached sync, and unused PM APIs. Keep historical updater
exports inert and preserve external tool ownership and native integration.

Share product freshness and prepared inputs across builders. Align plugin
admission, Docker provisioning, setup instructions, and behavioral tests.

Verified targeted Python and JavaScript tests, desktop and web typechecks,
scoped lint, real product builds, and the Docker frontend smoke test.
The missed post-setup test cleanup is included and verified.

Native Windows/macOS execution, full Rust compilation, and the complete
repository suite remain unverified. Historical compatibility requirements
were preserved and extended, not fully rescanned.
2026-09-12 14:57:38 -04:00

124 lines
4 KiB
Python

#!/usr/bin/env python3
"""
Fetch a YouTube video transcript and output it as structured JSON.
Usage:
python fetch_transcript.py <url_or_video_id> [--language en,tr] [--timestamps]
Output (JSON):
{
"video_id": "...",
"language": "en",
"segments": [{"text": "...", "start": 0.0, "duration": 2.5}, ...],
"full_text": "complete transcript as plain text",
"timestamped_text": "00:00 first line\n00:05 second line\n..."
}
Use the isolated helper interpreter prepared by this skill's PM setup recipe.
"""
import argparse
import json
import re
import sys
def extract_video_id(url_or_id: str) -> str:
"""Extract the 11-character video ID from various YouTube URL formats."""
url_or_id = url_or_id.strip()
patterns = [
r'(?:v=|youtu\.be/|shorts/|embed/|live/)([a-zA-Z0-9_-]{11})',
r'^([a-zA-Z0-9_-]{11})$',
]
for pattern in patterns:
match = re.search(pattern, url_or_id)
if match:
return match.group(1)
return url_or_id
def format_timestamp(seconds: float) -> str:
"""Convert seconds to HH:MM:SS or MM:SS format."""
total = int(seconds)
h, remainder = divmod(total, 3600)
m, s = divmod(remainder, 60)
if h > 0:
return f"{h}:{m:02d}:{s:02d}"
return f"{m}:{s:02d}"
def fetch_transcript(video_id: str, languages: list = None):
"""Fetch transcript segments from YouTube.
Returns a list of dicts with 'text', 'start', and 'duration' keys.
Compatible with youtube-transcript-api v1.x.
"""
try:
from youtube_transcript_api import YouTubeTranscriptApi
except ImportError:
print("Error: youtube-transcript-api not installed. Use the isolated PM helper environment described in youtube-content/SKILL.md.",
file=sys.stderr)
sys.exit(1)
api = YouTubeTranscriptApi()
if languages:
result = api.fetch(video_id, languages=languages)
else:
result = api.fetch(video_id)
# v1.x returns FetchedTranscriptSnippet objects; normalize to dicts
return [
{"text": seg.text, "start": seg.start, "duration": seg.duration}
for seg in result
]
def main():
parser = argparse.ArgumentParser(description="Fetch YouTube transcript as JSON")
parser.add_argument("url", help="YouTube URL or video ID")
parser.add_argument("--language", "-l", default=None,
help="Comma-separated language codes (e.g. en,tr). Default: auto")
parser.add_argument("--timestamps", "-t", action="store_true",
help="Include timestamped text in output")
parser.add_argument("--text-only", action="store_true",
help="Output plain text instead of JSON")
args = parser.parse_args()
video_id = extract_video_id(args.url)
languages = [l.strip() for l in args.language.split(",")] if args.language else None
try:
segments = fetch_transcript(video_id, languages)
except Exception as e:
error_msg = str(e)
if "disabled" in error_msg.lower():
print(json.dumps({"error": "Transcripts are disabled for this video."}))
elif "no transcript" in error_msg.lower():
print(json.dumps({"error": "No transcript found. Try specifying a language with --language."}))
else:
print(json.dumps({"error": error_msg}))
sys.exit(1)
full_text = " ".join(seg["text"] for seg in segments)
timestamped = "\n".join(
f"{format_timestamp(seg['start'])} {seg['text']}" for seg in segments
)
if args.text_only:
print(timestamped if args.timestamps else full_text)
return
result = {
"video_id": video_id,
"segment_count": len(segments),
"duration": format_timestamp(segments[-1]["start"] + segments[-1]["duration"]) if segments else "0:00",
"full_text": full_text,
}
if args.timestamps:
result["timestamped_text"] = timestamped
print(json.dumps(result, ensure_ascii=False, indent=2))
if __name__ == "__main__":
main()