621dbe008e
Fixed automation-breaking issue where --list mode always returned exit code 0, even when list_available_transcripts() failed due to invalid video ID or network errors. Changes: - extract-transcript.py: Capture return value and exit with proper status code - Before: list_available_transcripts(video_id); sys.exit(0) - After: success = list_available_transcripts(video_id); sys.exit(0 if success else 1) - SKILL.md: Bumped version to 1.2.1 - CHANGELOG.md: Created changelog with v1.2.1 release notes Impact: Automation scripts can now detect failures correctly via exit codes. Identified by Codex automated review in antigravity-awesome-skills PR #62. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
66 lines
2.4 KiB
Python
66 lines
2.4 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Extract YouTube video transcript
|
|
Usage: ./extract-transcript.py VIDEO_ID [LANGUAGE_CODE]
|
|
"""
|
|
|
|
import sys
|
|
from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound
|
|
|
|
def extract_transcript(video_id, language='en'):
|
|
"""Extract transcript from YouTube video"""
|
|
try:
|
|
# Try to get transcript in specified language with fallback to English
|
|
transcript = YouTubeTranscriptApi.get_transcript(
|
|
video_id,
|
|
languages=[language, 'en']
|
|
)
|
|
|
|
# Combine all transcript segments
|
|
full_text = " ".join([entry['text'] for entry in transcript])
|
|
return full_text
|
|
|
|
except TranscriptsDisabled:
|
|
print(f"❌ Transcripts are disabled for video {video_id}", file=sys.stderr)
|
|
sys.exit(1)
|
|
except NoTranscriptFound:
|
|
print(f"❌ No transcript found for video {video_id}", file=sys.stderr)
|
|
sys.exit(1)
|
|
except Exception as e:
|
|
print(f"❌ Error: {e}", file=sys.stderr)
|
|
sys.exit(1)
|
|
|
|
def list_available_transcripts(video_id):
|
|
"""List all available transcripts for a video"""
|
|
try:
|
|
transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
|
|
print(f"✅ Available transcripts for {video_id}:")
|
|
|
|
for transcript in transcript_list:
|
|
generated = "[Auto-generated]" if transcript.is_generated else "[Manual]"
|
|
translatable = "(translatable)" if transcript.is_translatable else ""
|
|
print(f" - {transcript.language} ({transcript.language_code}) {generated} {translatable}")
|
|
|
|
return True
|
|
except Exception as e:
|
|
print(f"❌ Error listing transcripts: {e}", file=sys.stderr)
|
|
return False
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) < 2:
|
|
print("Usage: ./extract-transcript.py VIDEO_ID [LANGUAGE_CODE]")
|
|
print(" ./extract-transcript.py VIDEO_ID --list (list available transcripts)")
|
|
sys.exit(1)
|
|
|
|
video_id = sys.argv[1]
|
|
|
|
# Check if user wants to list available transcripts
|
|
if len(sys.argv) > 2 and sys.argv[2] == "--list":
|
|
success = list_available_transcripts(video_id)
|
|
sys.exit(0 if success else 1)
|
|
|
|
# Extract transcript
|
|
language = sys.argv[2] if len(sys.argv) > 2 else 'en'
|
|
transcript = extract_transcript(video_id, language)
|
|
print(transcript)
|