```bash
VIDEO_URL="https://www.youtube.com/watch?v=dQw4w9WgXcQ"
# Get video title for filename
VIDEO_TITLE=$(yt-dlp --print "%(title)s" "$VIDEO_URL" | tr '/' '_' | tr ':' '-' | tr '?' '' | tr '"' '')
OUTPUT_NAME="transcript_temp"
# ============================================
# STEP 1: Check if yt-dlp is installed
# ============================================
if ! command -v yt-dlp &> /dev/null; then
echo "yt-dlp not found, attempting to install..."
if command -v brew &> /dev/null; then
brew install yt-dlp
elif command -v apt &> /dev/null; then
sudo apt update && sudo apt install -y yt-dlp
else
pip3 install yt-dlp
fi
fi
# ============================================
# STEP 2: List available subtitles
# ============================================
echo "Checking available subtitles..."
yt-dlp --list-subs "$VIDEO_URL"
# ============================================
# STEP 3: Try manual subtitles first
# ============================================
echo "Attempting to download manual subtitles..."
if yt-dlp --write-sub --skip-download --output "$OUTPUT_NAME" "$VIDEO_URL" 2>/dev/null; then
echo "β Manual subtitles downloaded successfully!"
ls -lh ${OUTPUT_NAME}.*
else
# ============================================
# STEP 4: Fallback to auto-generated
# ============================================
echo "Manual subtitles not available. Trying auto-generated..."
if yt-dlp --write-auto-sub --skip-download --output "$OUTPUT_NAME" "$VIDEO_URL" 2>/dev/null; then
echo "β Auto-generated subtitles downloaded successfully!"
ls -lh ${OUTPUT_NAME}.*
else
# ============================================
# STEP 5: Last resort - Whisper transcription
# ============================================
echo "β No subtitles available for this video."
# Get file size
FILE_SIZE=$(yt-dlp --print "%(filesize_approx)s" -f "bestaudio" "$VIDEO_URL")
DURATION=$(yt-dlp --print "%(duration)s" "$VIDEO_URL")
TITLE=$(yt-dlp --print "%(title)s" "$VIDEO_URL")
echo "Video: $TITLE"
echo "Duration: $((DURATION / 60)) minutes"
echo "Audio size: ~$((FILE_SIZE / 1024 / 1024)) MB"
echo ""
echo "Would you like to download and transcribe with Whisper? (y/n)"
read -r RESPONSE
if [[ "$RESPONSE" =~ ^[Yy]$ ]]; then
# Check for Whisper
if ! command -v whisper &> /dev/null; then
echo "Whisper not installed. Install now? (requires ~1-3GB) (y/n)"
read -r INSTALL_RESPONSE
if [[ "$INSTALL_RESPONSE" =~ ^[Yy]$ ]]; then
pip3 install openai-whisper
else
echo "Cannot proceed without Whisper. Exiting."
exit 1
fi
fi
# Download audio
echo "Downloading audio..."
yt-dlp -x --audio-format mp3 --output "audio_%(id)s.%(ext)s" "$VIDEO_URL"
# Get the actual audio filename
AUDIO_FILE=$(ls audio_*.mp3 | head -n 1)
# Transcribe
echo "Transcribing with Whisper (this may take a few minutes)..."
whisper "$AUDIO_FILE" --model base --output_format vtt
# Cleanup
echo "Transcription complete! Delete audio file? (y/n)"
read -r CLEANUP_RESPONSE
if [[ "$CLEANUP_RESPONSE" =~ ^[Yy]$ ]]; then
rm "$AUDIO_FILE"
echo "Audio file deleted."
fi
ls -lh *.vtt
else
echo "Transcription cancelled."
exit 0
fi
fi
fi
# ============================================
# STEP 6: Convert to readable plain text with deduplication
# ============================================
VTT_FILE=$(ls ${OUTPUT_NAME}.vtt 2>/dev/null || ls .vtt | head -n 1)
if [ -f "$VTT_FILE" ]; then
echo "Converting to readable format and removing duplicates..."
python3 -c "
import sys, re
seen = set()
with open('$VTT_FILE', 'r') as f:
for line in f:
line = line.strip()
if line and not line.startswith('WEBVTT') and not line.startswith('Kind:') and not line.startswith('Language:') and '-->' not in line:
clean = re.sub('<[^>]*>', '', line)
clean = clean.replace('&', '&').replace('>', '>').replace('<', '<')
if clean and clean not in seen:
print(clean)
seen.add(clean)
" > "${VIDEO_TITLE}.txt"
echo "β Saved to: ${VIDEO_TITLE}.txt"
# Clean up temporary VTT file
rm "$VTT_FILE"
echo "β Cleaned up temporary VTT file"
else
echo "β No VTT file found to convert"
fi
echo "β Complete!"
```
Note: This complete workflow handles all scenarios with proper error checking and user prompts at each decision point.
|