This project retrieves the latest video metadata from a specified YouTube channel (Currently ITPM), extracts transcripts from selected videos, and generates insights using the Anthropic Claude API. The insights are then saved in Markdown format for easy access and readability. Currently its setup to get the latest videos from the ITPM youtube channel, transcribe only the Flash videos and parse them through a LLM to summarise and gainm insights
- Fetches the latest videos from a YouTube channel.
- Extracts transcripts from videos containing "ITPM Flash" in the title.
- Analyzes transcripts to generate actionable insights.
- Saves insights in a Markdown file.
-
Clone the repository:
git clone this repo cd this-repo-name
-
Install the required packages:
pip install -r requirements.txt
-
Create a
.env
file in the root directory and add your API keys and the target directory where the .md file will be saved:YOUTUBE_API_KEY=your_youtube_api_key ANTHROPIC_API_KEY=your_anthropic_api_key TARGET_DIRECTORY=/path/to/your/directory
-
Run the script:
python main.py
-
Output:
- The insights will be saved in a Markdown file in the specified directory (
TARGET_DIRECTORY
). - The filename will be based on the video title, formatted to be URL-friendly.
- The insights will be saved in a Markdown file in the specified directory (
This project is licensed under the MIT License.