segscript 0.1.3

Extract, refine, and analyze YouTube video segments with precision

SegScript

A command-line tool for managing, enhancing, and interacting with YouTube transcripts.

• Overview
• Features
• Installation
• Dependencies
• Usage
  • Basic Commands
  • Interactive Mode
• File Structure
• Examples
  • Download a transcript
  • View a transcript for a specific section of a video
  • Interactive browsing
• Next TODOs
• Contributing
• License
• Acknowledgments

Overview

SegScript allows you to download, view, and query YouTube video transcripts directly from your terminal. It provides a clean interface for working with transcripts, including the ability to extract specific time ranges and view enhanced transcript content. I've used the langchain-google-genai package in conjunction with Google's Gemini Flash 2.0 model, which has delivered exceptional results in transcript enhancement.

Features

• Download transcripts from any YouTube video using its ID
• List all downloaded transcripts stored in your local collection
• View full transcripts or segments based on time ranges
• Interactive mode for browsing and working with your transcript collection
• Rich text formatting for improved readability in the terminal

Installation

pip install segscript

For testing purposes,

# Clone the repository
git clone https://github.com/keshavsharma25/segscript.git
cd segscript

# Install dependencies
pip install -r pyproject.toml

# Install the package (optional)
pip install -e .

Dependencies

• youtube-transcript-api: Fetch youtube transcripts with ease
• click: Command-line interface creation kit
• rich: Terminal formatting and styling
• python-dotenv: Load GOOGLE_API_KEY from the command line environment
• pathlib: Object-oriented filesystem paths
• langchain-google-genai: For synthesizing transcript into a well structured format

Usage

Basic Commands

# List all downloaded transcripts
segscript list

# Download a transcript for a YouTube video
segscript download VIDEO_ID

# Get a transcript (downloads if not already available)
segscript get VIDEO_ID

# Get a transcript for a specific time range
segscript get VIDEO_ID --time-range "10:00;20:00"

# Start interactive mode
segscript prompt

Interactive Mode

Interactive mode provides a user-friendly interface for:

1. Browsing your transcript collection
2. Selecting a transcript to work with
3. Viewing full transcripts or specific segments
4. Querying transcripts by time range

File Structure

Transcripts are stored in the ~/.segscript/ directory with the following structure:

~/.segscript/
├── .env                    # Environment variables file
├── VIDEO_ID_1/
│   ├── VIDEO_ID_1.json     # Raw transcript data
│   └── metadata.json       # Video metadata
├── VIDEO_ID_2/
│   ├── VIDEO_ID_2.json
│   └── metadata.json
└── ...

Examples

Download a transcript

segscript download dQw4w9WgXcQ

View a transcript for a specific section of a video

segscript get dQw4w9WgXcQ --time-range "1:30;2:45"

Interactive browsing

segscript prompt

Next TODOs

• Add transcript summary support

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

• A huge thanks to Youtube Transcript API for making transcript retrieval so easy and accessible.
• Also kudos to Langchain Google for the langchain-google-genai.
• Built with Rich for beautiful terminal output.
• Uses Click for command-line interface.

---

Note: SegScript is not affiliated with YouTube or Google.