An AI-powered tool that analyzes YouTube videos for content patterns, hooks, themes, and engagement strategies. Perfect for content creators who want to understand what makes videos successful in their niche.

• Video Discovery: Search and find top-performing videos in any niche using YouTube Data API
• Transcript Extraction: Automatically pulls full video transcripts
• AI-Powered Analysis: Uses LLMs (OpenAI/Claude) to extract:
  • Opening hooks and attention grabbers
  • Key themes and topics
  • Content structure and flow
  • Engagement strategies
  • Storytelling techniques
• Batch Processing: Analyze multiple videos at once
• Export Results: Save analysis to JSON, CSV, or markdown reports

• Python 3.9 or higher
• YouTube Data API key
• OpenAI API key or Anthropic API key

1. Clone the repository:

git clone https://github.com/gabubu-dev/youtube-content-analyzer.git
cd youtube-content-analyzer

2. Create a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Configure API keys:

cp config.example.json config.json
# Edit config.json with your API keys

Create a config.json file with your API credentials:

{
  "youtube_api_key": "your-youtube-api-key",
  "openai_api_key": "your-openai-api-key",
  "anthropic_api_key": "your-anthropic-api-key",
  "default_llm": "openai",
  "model": "gpt-4-turbo-preview",
  "max_videos": 10,
  "language": "en"
}

Analyze top videos in a niche:

python -m src.cli search "content creation tips" --max-results 5 --analyze

Analyze a specific video:

python -m src.cli analyze https://www.youtube.com/watch?v=VIDEO_ID

Batch analyze from a list:

python -m src.cli batch video_urls.txt --output results.json

from src.analyzer import YouTubeAnalyzer
from src.config import load_config

# Initialize
config = load_config("config.json")
analyzer = YouTubeAnalyzer(config)

# Search and analyze
results = analyzer.search_and_analyze("productivity tips", max_results=5)

# Analyze specific video
analysis = analyzer.analyze_video("https://www.youtube.com/watch?v=VIDEO_ID")

# Access analysis results
print(analysis.hooks)
print(analysis.themes)
print(analysis.engagement_strategies)

src/
├── __init__.py
├── cli.py              # Command line interface
├── config.py           # Configuration management
├── youtube_client.py   # YouTube API wrapper
├── transcript.py       # Transcript extraction
├── llm_client.py       # LLM API clients (OpenAI/Claude)
├── analyzer.py         # Main analysis orchestration
├── prompts.py          # Analysis prompt templates
└── export.py           # Export functionality

tests/
├── test_youtube_client.py
├── test_transcript.py
├── test_analyzer.py
└── test_export.py

pytest tests/

This project follows PEP 8 style guidelines. Format code with:

black src/ tests/

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Make your changes with clear commit messages
4. Add tests for new functionality
5. Submit a pull request

MIT License - see LICENSE file for details

• Built with YouTube Data API v3
• Uses youtube-transcript-api for transcript extraction
• Powered by OpenAI and Anthropic LLMs