GitHub - ThomsenDrake/ainews-source-extractor: Extracts all URLs from the most recent AI News issue (from news.smol.ai) and prepares them for seamless import into Google's NotebookLM
May 22, 2025 - github.com
The AI News Source Extractor is a tool designed to scrape URLs from the latest AI News issue on news.smol.ai and organize them for import into Google's NotebookLM. It creates a timestamped folder for each issue, compiles non-social URLs into a `sources.txt` file, and generates markdown files for quoted tweet content. The `sources.txt` can be directly used with the WebSync for NotebookLM Chrome extension for easy import.
The tool is installed via a GitHub repository and requires setting up a Python virtual environment. Usage involves running the main scraper, which automatically organizes the URLs and tweet content. Future improvements include enhancing URL filtering, developing a Discord scraper, and allowing customization of output paths and source URLs. Contributions to the project are encouraged through GitHub.
Key takeaways:
AI News Link Scraper extracts URLs from AI News issues for import into Google's NotebookLM.
It organizes sources into a folder, separates non-social URLs into a `sources.txt`, and creates markdown files for quoted tweets.
The tool is WebSync Ready, allowing `sources.txt` to be pasted into the WebSync for NotebookLM Chrome extension.
Future improvements include better URL-filtering logic and a `discord_scraper.py` for Discord messages.
