Add feature: website-metadata-extractor

[arisha8809]

Add Website Metadata Extractor Agent
Summary:

This pull request introduces a new agent for extracting metadata from websites. The WebsiteMetadataAgent fetches and returns essential metadata for a given URL, including the title, description, and keywords (if available). This agent handles edge cases where metadata might be missing and ensures that meaningful default values are returned.

Key Features:

1. Fetches metadata from the given website URL.
2. Retrieves the title, meta description, and meta keywords.
3. Handles missing metadata gracefully by returning default values.
4. Implements a health_check method to verify the operational status of the agent by attempting to fetch metadata from a test URL.

Changes Made:

1. Created the WebsiteMetadataAgent class under agents/website_metadata_extractor/.
2. Implemented the execute method to fetch metadata from websites.
3. Added the health_check method to test if the agent is functional.
4. Added appropriate error handling for invalid URLs and failed requests.

Testing:

1. Unit tests were added to ensure that the agent behaves correctly:
2. Tests for successful metadata extraction.
3. Tests for handling invalid URLs.
4. Simulated network errors for health check failure scenarios.

How to Use:
Execute the agent via the PlugFlow CLI with the following parameters:

python main.py execute website-metadata-extractor --params '{"url": "https://example.com"}'

The agent will return the website metadata in the following format:
{
"Title": "Example Domain",
"Meta Description": "No description found",
"Meta Keywords": "No keywords found"
}

[kanishksaleria]

checks have failed please try to resolve it